Deep learning image reconstruction generates thinner slice iodine maps with improved image quality to increase diagnostic acceptance and lesion conspicuity: a prospective study on abdominal dual-energy CT.

BACKGROUND: To assess the improvement of image quality and diagnostic acceptance of thinner slice iodine maps enabled by deep learning image reconstruction (DLIR) in abdominal dual-energy CT (DECT). METHODS: This study prospectively included 104 participants with 136 lesions. Four series of iodine maps were generated based on portal-venous scans of contrast-enhanced abdominal DECT: 5-mm and 1.25-mm using adaptive statistical iterative reconstruction-V (Asir-V) with 50% blending (AV-50), and 1.25-mm using DLIR with medium (DLIR-M), and high strength (DLIR-H). The iodine concentrations (IC) and their standard deviations of nine anatomical sites were measured, and the corresponding coefficient of variations (CV) were calculated. Noise-power-spectrum (NPS) and edge-rise-slope (ERS) were measured. Five radiologists rated image quality in terms of image noise, contrast, sharpness, texture, and small structure visibility, and evaluated overall diagnostic acceptability of images and lesion conspicuity. RESULTS: The four reconstructions maintained the IC values unchanged in nine anatomical sites (all p > 0.999). Compared to 1.25-mm AV-50, 1.25-mm DLIR-M and DLIR-H significantly reduced CV values (all p < 0.001) and presented lower noise and noise peak (both p < 0.001). Compared to 5-mm AV-50, 1.25-mm images had higher ERS (all p < 0.001). The difference of the peak and average spatial frequency among the four reconstructions was relatively small but statistically significant (both p < 0.001). The 1.25-mm DLIR-M images were rated higher than the 5-mm and 1.25-mm AV-50 images for diagnostic acceptability and lesion conspicuity (all P < 0.001). CONCLUSIONS: DLIR may facilitate the thinner slice thickness iodine maps in abdominal DECT for improvement of image quality, diagnostic acceptability, and lesion conspicuity.

Robustness of Quantitative Diffusion Metrics from Four Models: A Prospective Study on the Influence of Scan-Rescans, Voxel Size, Coils, and Observers.

BACKGROUND: Quantitative diffusion metrics provide additional microstructural information of diseases. The robustness of quantitative diffusion metrics should be established before clinical application. PURPOSE: To evaluate the variability and reproducibility of quantitative diffusion MRI metrics. STUDY TYPE: Prospective. POPULATION: 14 volunteers (7 men; median age, range, 28, 26-59 years). FIELD STRENGTH/SEQUENCE: 3.0-T/Diffusion spectrum imaging. ASSESSMENT: Brain MRI studies were performed four times per subject: involving different combinations of coil types and voxel sizes. Regions of interest of 13 brain anatomical sites were drawn by one observer twice and another observer once to allow interobserver and intraobserver reproducibility assessment. Twenty-five quantitative metrics were calculated using four diffusion models. STATISTICAL TESTS: The variability was evaluated with coefficients of variation (CV), and quartile coefficient of dispersion (QCD). The reproducibility was assessed with intraclass correlation coefficient (ICC), and concordance correlation coefficient (CCC). Wilcoxon signed rank test was used to compare the influence of factors on robustness of quantitative diffusion metrics. A two-tailed P < 0.05 was considered statistically significant. RESULTS: The variability of quantitative diffusion metrics showed CV of 2.4%-68.2%, and QCD of 0.6%-48.2%, respectively. The reproducibility of scans using 20-channel coils with voxels of 2 × 2 × 2 mm3 and 3 × 3 × 3 mm3 , respectively (ICC 0.03-0.84, CCC 0.03-0.84) was significantly worse than that of repeated scans using a 20-channel coil with a voxel size of 2 × 2 × 2 mm3 (ICC of 0.74-0.97, CCC 0.74-0.97) and that of scans using 20- and 64-channel coils, respectively, with a voxel size of 2 × 2 × 2 mm3 (ICC 0.59-0.95, CCC 0.59-0.95). The intraobserver reproducibility (ICC 0.49-0.94, CCC 0.49-0.94) was significantly better than the interobserver reproducibility (ICC 0.28-0.91, CCC 0.28-0.91). DATA CONCLUSION: Our study indicated that the voxel size has a greater influence on the reproducibility of quantitative diffusion metrics than scan-rescans and coils. The reproducibility within one observer was higher than that between two observers. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.

Nomogram to predict recurrent chest pain in patients with myocardial bridging.

OBJECTIVE: Patients with myocardial bridging (MB) frequently experience recurrent chest pain, even in those without coronary heart disease. This study aims to predict the risk of recurrent chest pain in patients with MB by using a novel predictive nomogram. METHODS: This retrospective study enrolled 250 patients with acute chest pain who underwent coronary computed tomography angiography (CCTA) between January and December 2018, including 111 patients with MB and 139 control patients. Least absolute shrinkage and selection operator (LASSO) and multivariable Cox regression analyses were used to screen for significant parameters that were included to develop a novel predictive nomogram model. Receiver operating characteristic curve, calibration curve, and decision curve analyses were used to evaluate the performance and clinical utility of the nomogram. RESULTS: A predictive nomogram was constructed in 111 patients with MB, 34 of whom (30.9%) had recurrent chest pain. The significant predictors screened out by the LASSO regression included age, sex, branch type MB, and systolic compression index. The area under the curves (AUCs) for recurrent chest pain at 12, 24, and 36 months were 0.688, 0.742, and 0.729, respectively, indicating remarkable accuracy of the nomogram. The calibration curve and decision curve analyses indicated a good agreement with the observations and utility of the nomogram. CONCLUSIONS: This study presents a high-accuracy nomogram to predict recurrent chest pain in patients with MB. This model incorporates clinical risk factors and CT imaging features and can be conveniently used to facilitate the individualised prediction. KEY POINTS: • Symptomatic patients with myocardial bridging often present with recurrent chest pain. • The potential predictors of recurrent chest pain in patients with myocardial bridging were age, sex, branch type MB, and systolic compression index. • Nomogram based on clinical CT imaging features is valuable to predict recurrent chest pain in patients with myocardial bridging.

A systematic review of radiomics in chondrosarcoma: assessment of study quality and clinical value needs handy tools.

OBJECTIVE: To evaluate the study quality and clinical value of radiomics studies on chondrosarcoma. METHODS: PubMed, Embase, Web of Science, China National Knowledge Infrastructure, and Wanfang Data were searched for articles on radiomics for evaluating chondrosarcoma as of January 31, 2022. The study quality was assessed according to Radiomics Quality Score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, Image Biomarker Standardization Initiative (IBSI) guideline, and modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The level of evidence supporting clinical use of radiomics on chondrosarcoma differential diagnosis was determined based on meta-analyses. RESULTS: Twelve articles were included. The median RQS was 10.5 (range, -3 to 15), with an adherence rate of 36%. The adherence rate was extremely low in domains of high-level evidence (0%), open science and data (17%), and imaging and segmentation (35%). The adherence rate of the TRIPOD checklist was 61%, and low for section of title and abstract (13%), introduction (42%), and results (56%). The reporting rate of pre-processing steps according to the IBSI guideline was 60%. The risk of bias and concern of application were mainly related to the index test. The meta-analysis on differential diagnosis of enchondromas vs. chondrosarcomas showed a diagnostic odds ratio of 43.90 (95% confidential interval, 25.33-76.10), which was rated as weak evidence. CONCLUSIONS: The current scientific and reporting quality of radiomics studies on chondrosarcoma was insufficient. Radiomics has potential in facilitating the optimization of operation decision-making in chondrosarcoma. KEY POINTS: • Among radiomics studies on chondrosarcoma, although differential diagnostic models showed promising performance, only pieces of weak level of evidence were reached with insufficient study quality. • Since the RQS rating, the TRIPOD checklist, and the IBSI guideline have largely overlapped with each other, it is necessary to establish one widely acceptable methodological and reporting guideline for radiomics research. • The TRIPOD model typing, the phase classification of image mining studies, and the level of evidence category are useful tools to assess the gap between academic research and clinical application, although their modifications for radiomics studies are needed.

Deep learning image reconstruction algorithm reduces image noise while alters radiomics features in dual-energy CT in comparison with conventional iterative reconstruction algorithms: a phantom study.

OBJECTIVES: To compare image quality between a deep learning image reconstruction (DLIR) algorithm and conventional iterative reconstruction (IR) algorithms in dual-energy CT (DECT) and to assess the impact of these algorithms on radiomics robustness. METHODS: A phantom with clinical-relevant densities was imaged on seven DECT scanners with the same voxel size using typical abdominal-pelvis examination protocols. On one DECT scanner, raw data were reconstructed using both conventional IR (adaptive statistical iterative reconstruction-V, ASIR-V) and DLIR. Nine sets of corresponding images were generated on other six DECT scanners using scanner-equipped conventional IR. Regions of interest were delineated through rigid registrations. Image quality was compared. Pyradiomics platform was used for radiomics feature extraction. Test-retest repeatability was assessed by Bland-Altman analysis for repeated scans. Inter-reconstruction algorithm reproducibility between conventional IR and DLIR was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). Robust features were identified. RESULTS: DLIR significantly improved image quality. Ninety-four radiomics features were extracted and nine features were considered as robust. 93.87% features were repeatable between repeated scans. ASIR-V images showed higher reproducibility to other conventional IR than DLIR (ICC mean, 0.603 vs 0.558, p = 0.001; CCC mean, 0.554 vs 0.510, p = 0.004). 7.45% and 26.83% features were reproducible among scanners evaluated by CV and QCD, respectively. CONCLUSIONS: DLIR improves quality of DECT images but may alter radiomics features compared to conventional IR. Nine robust DECT radiomics features were identified. KEY POINTS: • DLIR improves DECT image quality in terms of signal-to-noise ratio and contrast-to-noise ratio compared with ASIR-V and showed the highest noise reduction rate and lowest peak frequency shift. • Most of radiomics features are repeatable between repeated DECT scans, while inter-reconstruction algorithm reproducibility between conventional IR and DLIR, and inter-scanner reproducibility, are low. • Although DLIR may alter radiomics features compared to IR algorithms, nine radiomics features survived repeatability and reproducibility analysis among DECT scanners and reconstruction algorithms, which allows further validation and clinical-relevant analysis.

The prognostic value of myocardial salvage index by cardiac magnetic resonance in ST-segment elevation myocardial infarction patients: a systematic review and meta-analysis.

OBJECTIVE: To assess the prognostic value of myocardial salvage index (MSI) by cardiac magnetic resonance (CMR) in ST-segment elevation myocardial infarction (STEMI) patients. METHODS: We systematically searched PubMed, Embase, Web of Science, Cochrane Central, China National Knowledge Infrastructure, and Wanfang Data to identify primary studies reporting MSI in STEMI patients with major adverse cardiovascular events (MACE) comprised of death, myocardial reinfarction, and congestive heart failure. The MSI and MACE rates were pooled. The bias of risk was assessed using the Quality In Prognosis Studies tool. The evidence level was rated based on the meta-analysis of hazard ratio (HR) and 95% confidence interval (CI) of MSI for predicting MACE. RESULTS: Eighteen studies were included covering twelve unique cohorts. Eleven cohorts measured MSI using T2-weighted imaging and T1-weighted late gadolinium enhancement, while one cohort applied T2-mapping and T1-mapping. The pooled MSI (95% CI) was 44% (39 to 49%; 11 studies, 2946 patients), and the pooled MACE rate (95% CI) was 10% (7 to 14%; 12 studies, 311/3011 events/patients). Seven prognostic studies overall showed low risk of bias. The HR (95% CI) per 1% increase of MSI for MACE was 0.95 (0.92 to 0.98; 5 studies, 150/885 events/patients), and HR (95% CI) of MSI < median versus MSI > median for MACE was 5.62 (3.74 to 8.43; 6 studies, 166/1570 events/patients), both rated as weak evidence. CONCLUSIONS: MSI presents potential in predicting MACE in STEMI patients. The prognostic value of MSI using advanced CMR techniques for adverse cardiovascular events needs further investigation. CLINICAL RELEVANCE STATEMENT: Seven studies supported the MSI to serve as a predictor for MACE in STEMI patients, indicating its potential as a risk stratification tool to help manage expectations for these patients in clinical practice. KEY POINTS: • The pooled infarct size (95% CI) and area at risk (95% CI) were 21% (18 to 23%; 11 studies, 2783 patients) and 38% (34 to 43%; 10 studies, 2022 patients), respectively. • The pooled rates (95% CI) of cardiac mortality, myocardial reinfarction, and congestive heart failure were 2% (1 to 3%; 11 studies, 86/2907 events/patients), 4% (3 to 6%; 12 studies, 127/3011 events/patients), and 3% (1 to 5%; 12 studies, 94/3011 events/patients), respectively. • The HRs (95% CI) per 1% increase of MSI for cardiac mortality and congestive heart failure were 0.93 (0.91 to 0.96; 1 study, 14/202 events/patients) and 0.96 (0.93 to 0.99; 1 study, 11/104 events/patients), respectively, but the prognostic value of MSI for myocardial re-infraction has not been measured.

Improving lesion conspicuity in abdominal dual-energy CT with deep learning image reconstruction: a prospective study with five readers.

OBJECTIVES: To evaluate image quality, diagnostic acceptability, and lesion conspicuity in abdominal dual-energy CT (DECT) using deep learning image reconstruction (DLIR) compared to those using adaptive statistical iterative reconstruction-V (Asir-V) at 50% blending (AV-50), and to identify potential factors impacting lesion conspicuity. METHODS: The portal-venous phase scans in abdominal DECT of 47 participants with 84 lesions were prospectively included. The raw data were reconstructed to virtual monoenergetic image (VMI) at 50 keV using filtered back-projection (FBP), AV-50, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H). A noise power spectrum (NPS) was generated. CT number and standard deviation values of eight anatomical sites were measured. Signal-to-noise (SNR), and contrast-to-noise ratio (CNR) values were calculated. Five radiologists assessed image quality in terms of image contrast, image noise, image sharpness, artificial sensation, and diagnostic acceptability, and evaluated the lesion conspicuity. RESULTS: DLIR further reduced image noise (p < 0.001) compared to AV-50 while better preserved the average NPS frequency (p < 0.001). DLIR maintained CT number values (p > 0.99) and improved SNR and CNR values compared to AV-50 (p < 0.001). DLIR-H and DLIR-M showed higher ratings in all image quality analyses than AV-50 (p < 0.001). DLIR-H provided significantly better lesion conspicuity than AV-50 and DLIR-M regardless of lesion size, relative CT attenuation to surrounding tissue, or clinical purpose (p < 0.05). CONCLUSIONS: DLIR-H could be safely recommended for routine low-keV VMI reconstruction in daily contrast-enhanced abdominal DECT to improve image quality, diagnostic acceptability, and lesion conspicuity. KEY POINTS: • DLIR is superior to AV-50 in noise reduction, with less shifts of the average spatial frequency of NPS towards low frequency, and larger improvements of NPS noise, noise peak, SNR, and CNR values. • DLIR-M and DLIR-H generate better image quality in terms of image contrast, noise, sharpness, artificial sensation, and diagnostic acceptability than AV-50, while DLIR-H provides better lesion conspicuity than AV-50 and DLIR-M. • DLIR-H could be safely recommended as a new standard for routine low-keV VMI reconstruction in contrast-enhanced abdominal DECT to provide better lesion conspicuity and better image quality than the standard AV-50.

The endorsement of general and artificial intelligence reporting guidelines in radiological journals: a meta-research study.

BACKGROUND: Complete reporting is essential for clinical research. However, the endorsement of reporting guidelines in radiological journals is still unclear. Further, as a field extensively utilizing artificial intelligence (AI), the adoption of both general and AI reporting guidelines would be necessary for enhancing quality and transparency of radiological research. This study aims to investigate the endorsement of general reporting guidelines and those for AI applications in medical imaging in radiological journals, and explore associated journal characteristic variables. METHODS: This meta-research study screened journals from the Radiology, Nuclear Medicine & Medical Imaging category, Science Citation Index Expanded of the 2022 Journal Citation Reports, and excluded journals not publishing original research, in non-English languages, and instructions for authors unavailable. The endorsement of fifteen general reporting guidelines and ten AI reporting guidelines was rated using a five-level tool: "active strong", "active weak", "passive moderate", "passive weak", and "none". The association between endorsement and journal characteristic variables was evaluated by logistic regression analysis. RESULTS: We included 117 journals. The top-five endorsed reporting guidelines were CONSORT (Consolidated Standards of Reporting Trials, 58.1%, 68/117), PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses, 54.7%, 64/117), STROBE (STrengthening the Reporting of Observational Studies in Epidemiology, 51.3%, 60/117), STARD (Standards for Reporting of Diagnostic Accuracy, 50.4%, 59/117), and ARRIVE (Animal Research Reporting of In Vivo Experiments, 35.9%, 42/117). The most implemented AI reporting guideline was CLAIM (Checklist for Artificial Intelligence in Medical Imaging, 1.7%, 2/117), while other nine AI reporting guidelines were not mentioned. The Journal Impact Factor quartile and publisher were associated with endorsement of reporting guidelines in radiological journals. CONCLUSIONS: The general reporting guideline endorsement was suboptimal in radiological journals. The implementation of reporting guidelines for AI applications in medical imaging was extremely low. Their adoption should be strengthened to facilitate quality and transparency of radiological study reporting.

Characterization of the substernal space with computed tomography imaging in patients with and without median sternotomy: Assessing a novel implant location for extravascular defibrillation lead placement.

BACKGROUND: Implantable cardioverter-defibrillators (ICDs) provide clinically significant therapy for the prevention of sudden cardiac death. This study aimed to characterize the substernal space using computed tomography (CT) in patients with and without prior midline sternotomy to investigate the feasibility of substernal ICD lead implantation in post-sternotomy patients. METHODS: High-quality electrocardiogram-gated CT images from 100 patients (71% male, average body mass index 23.5 ± 2.9) were retrospectively collected, including 50 patients with prior midline sternotomy (S-group) and 50 patients with no prior sternotomy (NS-group). Distances were measured from the retrosternal surface to the epicardial surface of the heart and segmented into four regions from the xiphoid tip and superiorly along the sternum. RESULTS: Results generally showed a measurable but narrower average sternum-to-heart distance in the prior sternotomy group compared to the non-sternotomy group in all four regions (p < .05). In the S-group, the sternum-to-heart distances across all regions ranged from 0 to 32.0 mm, while in the NS-group, the distances ranged from 0 to 39.9 mm. CONCLUSION: Small but measurable separations between the heart and sternum were observed in patients with prior sternotomy, particularly near the xiphoid region, indicating the potential viability of extravascular substernal ICD lead implantation in post-sternotomy patients.

Association among peripatellar fat pad edema and related patellofemoral maltracking parameters: a case-control magnetic resonance imaging study.

BACKGROUND: The peripatellar fat pads are critical for protective cushioning during movement, and their endocrine function has been shown to affect osteoarthritis. Magnetic resonance imaging (MRI) is frequently used to visualize edema of the peripatellar fat pads due to injury. In this study, we aimed to assess the relationship between peripatellar fat pad edema and patellofemoral maltracking MRI parameters and investigate the association among cases of peripatellar fat pad edema. METHODS: Age- and sex-matched peripatellar fat pad edema cases were identified and divided into superolateral Hoffa, quadriceps, and prefemoral groups. Images were assessed according to tibial tuberosity lateralization, trochlear dysplasia, patellar alta, patellar tilt, and bisect offset. McNemar's test or paired t-tests and Spearman's correlation were used for statistical analysis. Interobserver agreement was assessed with the intraclass correlation coefficient. RESULTS: Of 1210 MRI scans, 50, 68, and 42 cases were in the superolateral Hoffa, quadriceps, and prefemoral groups, respectively. Subjects with superolateral Hoffa fat pad edema had a lower lateral trochlear inclination (p = 0.028), higher Insall-Salvati (p < 0.001) and modified Insall-Salvati (p = 0.021) ratios, and lower patellotrochlear index (p < 0.001) than controls. The prefemoral group had a lower lateral trochlear inclination (p = 0.014) and higher Insall-Salvati (p < 0.001) and modified Insall-Salvati (p = 0.004) ratios compared with the control group. In contrast, the patellotrochlear index (p = 0.001) was lower. Mean patellar tilt angle (p = 0.019) and mean bisect offset (p = 0.005) were significantly different between cases and controls. The quadriceps group showed no association. Superolateral Hoffa was positively correlated with prefemoral (p < 0.001, r = 0.408) and negatively correlated with quadriceps (p < 0.001, r = -0.500) fat pad edema. CONCLUSIONS: Superolateral Hoffa and prefemoral fat pad edemas were associated with patellar maltracking parameters. Quadriceps fat pad edema and maltracking parameters were not associated. Superolateral Hoffa fat pad edema was positively correlated with prefemoral and negatively correlated with quadriceps fat pad edema.

Evaluation of Image Quality and Detectability of Deep Learning Image Reconstruction (DLIR) Algorithm in Single- and Dual-energy CT.

This study is aimed to evaluate effects of deep learning image reconstruction (DLIR) on image quality in single-energy CT (SECT) and dual-energy CT (DECT), in reference to adaptive statistical iterative reconstruction-V (ASIR-V). The Gammex 464 phantom was scanned in SECT and DECT modes at three dose levels (5, 10, and 20 mGy). Raw data were reconstructed using six algorithms: filtered back-projection (FBP), ASIR-V at 40% (AV-40) and 100% (AV-100) strength, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H), to generate SECT 120kVp images and DECT 120kVp-like images. Objective image quality metrics were computed, including noise power spectrum (NPS), task transfer function (TTF), and detectability index (d'). Subjective image quality evaluation, including image noise, texture, sharpness, overall quality, and low- and high-contrast detectability, was performed by six readers. DLIR-H reduced overall noise magnitudes from FBP by 55.2% in a more balanced way of low and high frequency ranges comparing to AV-40, and improved the TTF values at 50% for acrylic inserts by average percentages of 18.32%. Comparing to SECT 20 mGy AV-40 images, the DECT 10 mGy DLIR-H images showed 20.90% and 7.75% improvement in d' for the small-object high-contrast and large-object low-contrast tasks, respectively. Subjective evaluation showed higher image quality and better detectability. At 50% of the radiation dose level, DECT with DLIR-H yields a gain in objective detectability index compared to full-dose AV-40 SECT images used in daily practice.

Deep learning in knee imaging: a systematic review utilizing a Checklist for Artificial Intelligence in Medical Imaging (CLAIM).

PURPOSE: Our purposes were (1) to explore the methodologic quality of the studies on the deep learning in knee imaging with CLAIM criterion and (2) to offer our vision for the development of CLAIM to assure high-quality reports about the application of AI to medical imaging in knee joint. MATERIALS AND METHODS: A Checklist for Artificial Intelligence in Medical Imaging systematic review was conducted from January 1, 2015, to June 1, 2020, using PubMed, EMBASE, and Web of Science databases. A total of 36 articles discussing deep learning applications in knee joint imaging were identified, divided by imaging modality, and characterized by imaging task, data source, algorithm type, and outcome metrics. RESULTS: A total of 36 studies were identified and divided into: X-ray (44.44%) and MRI (55.56%). The mean CLAIM score of the 36 studies was 27.94 (standard deviation, 4.26), which was 66.53% of the ideal score of 42.00. The CLAIM items achieved an average good inter-rater agreement (ICC 0.815, 95% CI 0.660-0.902). In total, 32 studies performed internal cross-validation on the data set, while only 4 studies conducted external validation of the data set. CONCLUSIONS: The overall scientific quality of deep learning in knee imaging is insufficient; however, deep learning remains a promising technology for diagnostic or predictive purpose. Improvements in study design, validation, and open science need to be made to demonstrate the generalizability of findings and to achieve clinical applications. Widespread application, pre-trained scoring procedure, and modification of CLAIM in response to clinical needs are necessary in the future. KEY POINTS: • Limited deep learning studies were established in knee imaging with mean score of 27.94, which was 66.53% of the ideal score of 42.00, commonly due to invalidated results, retrospective study design, and absence of a clear definition of the CLAIM items in detail. • A previous trained data extraction instrument allowed reaching moderate inter-rater agreement in the application of the CLAIM, while CLAIM still needs improvement in scoring items and result reporting to become a wide adaptive tool in reviews of deep learning studies.

Automated prediction of the neoadjuvant chemotherapy response in osteosarcoma with deep learning and an MRI-based radiomics nomogram.

OBJECTIVES: To implement a pipeline to automatically segment the ROI and to use a nomogram integrating the MRI-based radiomics score and clinical variables to predict responses to neoadjuvant chemotherapy (NAC) in osteosarcoma patients. METHODS: A total of 144 osteosarcoma patients treated with NAC were separated into training (n = 101) and test (n = 43) groups. After normalisation, ROIs for the preoperative MRI were segmented by a deep learning segmentation model trained with nnU-Net by using two independent manual segmentations as labels. Radiomics features were extracted using automatically segmented ROIs. Feature selection was performed in the training dataset by five-fold cross-validation. The clinical, radiomics, and clinical-radiomics models were built using multiple machine learning methods with the same training dataset and validated with the same test dataset. The segmentation model was evaluated by the Dice coefficient. AUC and decision curve analysis (DCA) were employed to illustrate the model performance and clinical utility. RESULTS: 36/144 (25.0%) patients were pathological good responders (pGRs) to NAC, while 108/144 (75.0%) were non-pGRs. The segmentation model achieved a Dice coefficient of 0.869 on the test dataset. The clinical and radiomics models reached AUCs of 0.636 with a 95% confidence interval (CI) of 0.427-0.860 and 0.759 (95% CI, 0.589-0.937), respectively, in the test dataset. The clinical-radiomics nomogram demonstrated good discrimination, with an AUC of 0.793 (95% CI, 0.610-0.975), and accuracy of 79.1%. The DCA suggested the clinical utility of the nomogram. CONCLUSION: The automatic nomogram could be applied to aid radiologists in identifying pGRs to NAC. KEY POINTS: • The nnU-Net trained by manual labels enables the use of an automatic segmentation tool for ROI delineation of osteosarcoma. • A pipeline using automatic lesion segmentation and followed by a radiomics classifier could aid the evaluation of NAC response of osteosarcoma. • A predictive nomogram composed of clinical variables and MRI-based radiomics score provides support for individualised treatment planning.

Robustness of CT radiomics features: consistency within and between single-energy CT and dual-energy CT.

OBJECTIVES: To evaluate inter- and intra- scan mode and scanner repeatability and reproducibility of radiomics features within and between single-energy CT (SECT) and dual-energy CT (DECT). METHODS: A standardized phantom with sixteen rods of clinical-relevant densities was scanned on seven DECT-capable scanners and three SECT-only scanners. The acquisition parameters were selected to present typical abdomen-pelvic examinations with the same voxel size. Images of SECT at 120 kVp and corresponding 120 kVp-like virtual monochromatic images (VMIs) in DECT which were generated according to scanners were analyzed. Regions of interest were drawn with rigid registrations to avoid variations due to segmentation. Radiomics features were extracted via Pyradiomics platform. Test-retest repeatability was evaluated by Bland-Altman analysis for repeated scans. Intra-scanner reproducibility for different scan modes was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility among different scanners for same scan mode was assessed by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). RESULTS: The test-retest analysis presented that 92.91% and 87.02% of the 94 assessed features were repeatable for SECT 120kVp and DECT 120 kVp-like VMIs, respectively. The intra-scanner analysis for SECT 120kVp vs DECT 120 kVp-like VMIs demonstrated that 10.76% and 10.28% of features were with ICC > 0.90 and CCC > 0.90, respectively. The inter-scanner analysis showed that 17.09% and 27.73% of features for SECT 120kVp were with CV < 10% and QCD < 10%, and 15.16% and 32.78% for DECT 120 kVp-like VMIs, respectively. CONCLUSIONS: The majority of radiomics features were non-reproducible within and between SECT and DECT. KEY POINTS: • Although the test-retest analysis showed high repeatability for radiomics features, the overall reproducibility of radiomics features within and between SECT and DECT was low. • Only about one-tenth of radiomics features extracted from SECT images and corresponding DECT images did match each other, even their average photon energy levels were considered alike, indicating that the scan mode potentially altered the radiomics features. • Less than one-fifth of radiomics features were reproducible among multiple SECT and DECT scanners, regardless of their fixed acquisition and reconstruction parameters, suggesting the necessity of scanning protocol adjustment and post-scan harmonization process.

Multivendor Comparison of Quantification Accuracy of Iodine Concentration and Attenuation Measurements by Dual-Energy CT: A Phantom Study.

BACKGROUND. Studies comparing accuracy of quantification by dual-energy CT (DECT) scanners have been limited by small numbers of scanners evaluated and narrow ranges of scanning conditions. OBJECTIVE. The purpose of this study was to compare DECT scanners of varying vendors, technologies, and generations in terms of the accuracy of iodine concentration and attenuation measurements. METHODS. A DECT quality-control phantom was designed to contain seven inserts of varying iodine concentrations as well as soft-tissue and fat inserts. The phantom underwent DECT using 12 different scanner configurations based on seven different DECT scanners from three vendors, with additional variation in tube voltage settings. Technologies included rapid-switching, dual-source, and dual-layer detector DECT. Scans also used three radiation dose levels (10, 20, and 30 mGy) and multiple reconstruction algorithms (filtered back projection, medium and high iterative reconstruction, and deep learning image reconstruction [DLIR]). The mean absolute percentage error (MAPE, representing the absolute ratio of measured error to nominal values on average; lower values indicate better accuracy) was calculated for iodine concentration on iodine maps (MAPEiodine) and attenuation on virtual monochromatic images (VMIs) using 40, 70, 100, and 140 keV (MAPEHU). Linear mixed models were used to explore factors affecting quantification accuracy. RESULTS. MAPEiodine and MAPEHU ranged 4.62-28.55% and 10.21-26.33%, respectively, across scanner configurations. Accuracies of iodine concentration and attenuation measurements were higher for third-generation rapid-switching and dual-source scanners in comparison with respective earlier-generation scanners and the single evaluated dual-layer detector scanner. Among all configurations, the third-generation rapid-switching scanner using DLIR had the highest quantification accuracy for iodine concentration (MAPEiodine, 4.62% ± 3.87%) and attenuation (MAPEHU, 10.21% ± 11.43%). Overall, MAPEiodine was significantly affected by scanner configuration (F = 450.0, p < .001) and iodine concentration (F = 211.0, p < .001). Overall, MAPEHU was significantly affected by scanner configuration (F = 233.5, p < .001), radiation dose (F = 14.9, p < .001), VMI energy level (F = 1959.4, p < .001), and material density (F = 411.5, p < .001); radiation dose was significantly associated with MAPEHU for five of 12 individual configurations. CONCLUSION. Quantification accuracy varied among DECT configurations of varying vendors, platforms, and generations and was affected by acquisition and reconstruction parameters. DLIR may improve quantification accuracy. CLINICAL IMPACT. The interscanner differences in DECT-based measurements should be recognized when quantitative evaluation is performed by DECT in clinical practice.

The prevalence and parameters of fabella and its association with medial meniscal tear in China: a retrospective study of 1011 knees.

BACKGROUND: Fabella is a sesamoid bone of knee that has potential biomechanical function. We aimed to examine the fabellar prevalence and parameters in Chinese population and test the hypothesis that fabellar presence and morphology were associated with meniscus tear or ligament injury. METHODS: A total of 1011 knee magnetic resonance imaging scans from 979 patients with knee pain were analyzed retrospectively. The exclusion criteria are postsurgical scans, difficulty in fabella discrimination, conditions not suitable for measurement, and unsatisfied image. The fabellar presence and its parameters (length, width and thickness) were documented. The association between fabellar presence and meniscus tear or ligament injury were assessed by chi-square test, in all knees and subgroups (age, gender, side, lesion part). The correlation of fabellar presence and parameters with advancing age was assessed by Spearman correlation analysis. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated to investigate whether factors related with meniscus tear or ligament injury. Diagnostic performance of risk factors was assessed by receiver operating characteristic (ROC) analysis. RESULTS: The overall prevalence of fabellae was 39.8% (402/1011 knees) and increased with the increasing age (r = 0.237, P < 0.001). The size of the fabellae differed according to genders, age, and presence of articulating grooves. Fabella presented more often in knees with medial meniscus (MM) tears (66.7% vs 33.8%; P < 0.001) with a multivariate OR of 2.960 (95% CI, 1.853-3.903). The association remained in all tear parts (anterior, middle, and posterior), and in younger (age < 50 years) and older patients (age ≥ 50 years). Age, fabellar length, width, length/thickness ratio and width/thickness ratio yielded an area under the ROC curve (AUC) of 0.604-0.766 to predict an MM tear. In combination with age, fabellar width and length/thickness ratio, the AUC was improved 0.791 (95% CI, 0.744-0.837), with a sensitivity of 73.0% and a specificity of 74.6%. CONCLUSION: The presence of fabellae, increased fabellar length and width as well as flatter fabellar morphology, are significantly associated with an increased risk for MM tear. These findings might aid clinicians in identifying patients at risk for a MM tear and informing them.

A systematic review of radiomics in osteosarcoma: utilizing radiomics quality score as a tool promoting clinical translation.

OBJECTIVES: To assess the methodological quality and risk of bias in radiomics studies investigating diagnosis, therapy response, and survival of patients with osteosarcoma. METHODS: In this systematic review, literatures on radiomics in osteosarcoma were included and assessed for methodological quality through the radiomics quality score (RQS). The risk of bias and concern of application was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool. A meta-analysis of studies focusing on predicting osteosarcoma response to neoadjuvant chemotherapy was performed. RESULTS: Twelve radiomics studies exploring osteosarcoma were identified, and five were included in meta-analysis. The RQS reached an average of 20.4% (6.92 of 36) with good inter-rater agreement (ICC 0.95, 95% CI 0.85-0.99). Four studies validated results with an internal dataset, none of which used external dataset; one study was prospectively designed, and another one shared part of the dataset. The risk of bias and concern of application were mainly related to index test aspect. The meta-analysis showed a diagnostic odds ratio of 43.68 (95%CI 13.5-141.31) for predicting response to neoadjuvant chemotherapy with high heterogeneity and low methodological quality. CONCLUSIONS: The overall scientific quality of included studies is insufficient; however, radiomics remains a promising technology for predicting treatment response, which might guide therapeutic decision-making and related to prognosis. Improvements in study design, validation, and open science needs to be made to demonstrate the generalizability of findings and to achieve clinical applications. Widespread application of RQS, pre-trained RQS scoring procedure, and modification of RQS in response to clinical needs are necessary. KEY POINTS: • Limited radiomics studies were established in osteosarcoma with mean RQS of 20.4%, commonly due to unvalidated results, retrospective study design, and absence of open science. • Meta-analysis of radiomics studies predicting osteosarcoma response to neoadjuvant chemotherapy showed high diagnostic odds ratio 43.68, while high heterogeneity and low methodological quality were the main concerns. • A previously trained data extraction instrument allowed reaching moderate inter-rater agreement in RQS applications, while RQS still needs improvement to become a wide adaptive tool in reviews of radiomics studies, in routine self-check before manuscript submitting and in study design.

Chondromyxoid fibroma-like osteosarcoma: a case series and literature review.

BACKGROUND: Chondromyxoid fibroma-like osteosarcoma (CMF-OS) is an exceedingly rare subtype of low-grade central osteosarcoma (LGCO), accounting for up to 10% of cases and making it difficult to diagnose. CMF-OS is frequently misdiagnosed on a radiological examination and biopsy, even after the initial operation. Its treatment is a controversial issue due to its low-grade classification and actual high-grade behavior. CASE PRESENTATION: We retrospectively reviewed the medical charts of more than 2000 osteosarcoma patients between 2008 and 2019; 11 patients with CMF-OS were identified, of which six patients were treated by our institution with complete clinical characteristics, including treatment and prognosis, radiological and pathological features were reviewed. Three males and three females with a median age of 46 (range 22-56) years were pathologically proven to have CMF-OS. The radiological presentation of CMF-OS is variable, thus radiological misdiagnoses are common. However, one must not ignore a malignant radiologic appearance. The most distinctive pathological feature conferring the diagnosis of CMF-OS is the presence of osteoid production directly by the tumor cells under a chondromyxoid fibroma (CMF)-like background. Differential diagnoses based on comprehensive data from CMF, LGCO, chondrosarcoma (CHS), conventional osteosarcoma (COS), etc., are needed. All patients were treated with an operation and chemotherapy, and one patient received additional radiotherapy. Nevertheless, recurrence and metastasis are common in CMF-OS patients. Relatively invasive biological behavior of CMF-OS is against the low-grade classification of this disease. CONCLUSIONS: It is important to recognize CMF-OS and distinguish it from CMF, CHS, COS and other LGCOs. CMF-OS has a relatively poor prognosis despite its low-grade classification.

Relationship between subchondral bone microstructure and articular cartilage in the osteoarthritic knee using 3T MRI.

BACKGROUND: The importance of subchondral bone in the pathogenesis of osteoarthritis (OA) has drawn interest. PURPOSE: To investigate subregional trabecular bone microstructural features and to determine the relationship between cartilage and trabecular bone in the osteoarthritic human knee. STUDY TYPE: Prospective study. SUBJECTS: In all, 92 knees were enrolled and divided into three groups: without OA, mild OA, and severe OA. SEQUENCE: A sagittal 3D balanced fast field echo (3D B-FFE) sequence and FatSat 3D fast field echo (3D-FFE) sequence at 3T MRI. ASSESSMENT: The trabecular bone in 12 sites of the knee joint was evaluated using digital topological analysis, and the cartilage thickness in four sites was calculated. STATISTICAL TEST: Trabecular bone and cartilage parameters between groups were compared using analysis of variance (ANOVA) with Bonferroni adjustment, and their correlations were analyzed using Pearson's correlation coefficient. RESULTS: Within both femoral condyles, the trabecular bone structure deteriorated in mild OA, showing a lower bone volume fraction (BVF) (0.15 to 0.12, P < 0.05), higher erosion index (EI) (2.25 to 2.28, P < 0.01), and a lower plate-to-rod ratio (SCR) (6.22 to 5.96, P < 0.05). Within medial and lateral tibia, deterioration in the trabecular bone was also observed, demonstrating a lower BVF (0.15 to 0.12 P < 0.05) and a higher EI (2.25 to 2.61, P < 0.05). Cartilage attrition mainly occurred in the medial joint. Extensive correlations were found between the medial cartilage thickness and subregional trabecular parameters. There was mainly a positive correlation with both femoral BVFs (r > 0.3, P < 0.05), and a negative correlation with the tibia SCR (r < -0.2, P < 0.05). DATA CONCLUSION: In the early stage of OA, trabecular bone osteoporotic changes were observed in both femoral condyles and the tibia. Based on a strong correlation with the medial cartilage thickness, the trabecular structural topological analysis may be useful for elucidating OA onset and progression. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.

Quantitative evaluation of subchondral bone microarchitecture in knee osteoarthritis using 3T MRI.

BACKGROUND: Osteoarthritis (OA) is now increasingly recognized as being related to the whole joint instead of the cartilage alone. In particular, the importance of subchondral bone in OA pathogenesis has drawn a lot of interest. The aim of this study is to investigate subchondral bone microstructural features in two femoral condyles of human knee osteoarthritis. METHODS: Eighty subjects were enrolled in our study and divided into three groups: without OA (group 0), mild OA (group 1), and severe OA (group 2). Sagittal 3D Balanced Fast Field Echo (3D-FFE) images were obtained by 3T MRI to quantify trabecular bone structure, and sagittal FatSat 3D Fast Field Echo (3D-FFE) images were acquired to assess cartilage thickness. Trabecular bone parameters, including bone volume fraction (BVF), erosion index (EI) and the trabecular plate-to-rod ratio (SCR), and trabecular thickness were evaluated using digital topological analysis. Subchondral bone and cartilage parameters between different groups and different locations were compared, and their correlations were analyzed. RESULTS: Within two femoral condyles, subchondral bone structure was deteriorated in mild OA, showing a lower BVF (-0.011 to -0.014 P < 0.001), a higher EI (0.346 to 0.310 P < 0.001), a lower SCR (-0.581 to -0.542 P < 0.001)) and lower trabecular thickness (-6.588 to -4.759 P < 0.05). In severe OA, BVF was further decreased, but EI, SCR and trabecular thickness showed no significant difference than mild OA(P > 0.05). Moreover, there was a lower BVF, SCR and higher EI in the medial femoral condyle in each group. Interestingly, cartilage attrition mainly occurred in the medial femoral condyle. Medial cartilage thickness was not only positively correlated with the ipsilateral femoral BVF (r = 0.321 P = 0.004) but also with the opposite femoral BVF (r = 0.270 P = 0.015). CONCLUSIONS: Our results indicated that deterioration in the trabecular bone structure in both femoral condyles could more sensitively reveal early OA, and BVF could be a better biomarker to evaluate OA severity.