RESUMEN
BACKGROUND: For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising. PURPOSE: To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI. STUDY TYPE: Retrospective. POPULATION: 133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI. FIELD STRENGTH/SEQUENCE: 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm2 ). ASSESSMENT: DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale. STATISTICAL TESTS: Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant. RESULTS: Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error. DATA CONCLUSION: Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.
RESUMEN
See also the editorial by Dodd and MacDermott in this issue.
Asunto(s)
Anemia , Fotones , Humanos , Fantasmas de Imagen , Tomografía Computarizada por Rayos X , Hemoglobinas , Anemia/diagnóstico por imagenRESUMEN
OBJECTIVES: Image acquisition in ultra-high-resolution (UHR) scan mode does not impose a dose penalty in photon-counting CT (PCCT). This study aims to investigate the dose saving potential of using UHR instead of standard-resolution PCCT for lumbar spine imaging. MATERIALS AND METHODS: Eight cadaveric specimens were examined with 7 dose levels (5-35 mGy) each in UHR (120 × 0.2 mm) and standard-resolution acquisition mode (144 × 0.4 mm) on a first-generation PCCT scanner. The UHR images were reconstructed with 3 dedicated bone kernels (Br68 [spatial frequency at 10% of the modulation transfer function 14.5 line pairs/cm], Br76 [21.0], and Br84 [27.9]), standard-resolution images with Br68 and Br76. Using automatic segmentation, contrast-to-noise ratios (CNRs) were established for lumbar vertebrae and psoas muscle tissue. In addition, image quality was assessed subjectively by 19 independent readers (15 radiologists, 4 surgeons) using a browser-based forced choice comparison tool totaling 16,974 performed pairwise tests. Pearson's correlation coefficient ( r ) was used to analyze the relationship between CNR and subjective image quality rankings, and Kendall W was calculated to assess interrater agreement. RESULTS: Irrespective of radiation exposure level, CNR was higher in UHR datasets than in standard-resolution images postprocessed with the same reconstruction parameters. The use of sharper convolution kernels entailed lower CNR but higher subjective image quality depending on radiation dose. Subjective assessment revealed high interrater agreement ( W = 0.86; P < 0.001) with UHR images being preferred by readers in the majority of comparisons on each dose level. Substantial correlation was ascertained between CNR and the subjective image quality ranking (all r 's ≥ 0.95; P < 0.001). CONCLUSIONS: In PCCT of the lumbar spine, UHR mode's smaller pixel size facilitates a considerable CNR increase over standard-resolution imaging, which can either be used for dose reduction or higher spatial resolution depending on the selected convolution kernel.
Asunto(s)
Cadáver , Vértebras Lumbares , Fotones , Dosis de Radiación , Tomografía Computarizada por Rayos X , Humanos , Vértebras Lumbares/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodosRESUMEN
In the early diagnostic workup of acute pancreatitis (AP), the role of contrast-enhanced CT is to establish the diagnosis in uncertain cases, assess severity, and detect potential complications like necrosis, fluid collections, bleeding or portal vein thrombosis. The value of texture analysis/radiomics of medical images has rapidly increased during the past decade, and the main focus has been on oncological imaging and tumor classification. Previous studies assessed the value of radiomics for differentiating between malignancies and inflammatory diseases of the pancreas as well as for prediction of AP severity. The aim of our study was to evaluate an automatic machine learning model for AP detection using radiomics analysis. Patients with abdominal pain and contrast-enhanced CT of the abdomen in an emergency setting were retrospectively included in this single-center study. The pancreas was automatically segmented using TotalSegmentator and radiomics features were extracted using PyRadiomics. We performed unsupervised hierarchical clustering and applied the random-forest based Boruta model to select the most important radiomics features. Important features and lipase levels were included in a logistic regression model with AP as the dependent variable. The model was established in a training cohort using fivefold cross-validation and applied to the test cohort (80/20 split). From a total of 1012 patients, 137 patients with AP and 138 patients without AP were included in the final study cohort. Feature selection confirmed 28 important features (mainly shape and first-order features) for the differentiation between AP and controls. The logistic regression model showed excellent diagnostic accuracy of radiomics features for the detection of AP, with an area under the curve (AUC) of 0.932. Using lipase levels only, an AUC of 0.946 was observed. Using both radiomics features and lipase levels, we showed an excellent AUC of 0.933 for the detection of AP. Automated segmentation of the pancreas and consecutive radiomics analysis almost achieved the high diagnostic accuracy of lipase levels, a well-established predictor of AP, and might be considered an additional diagnostic tool in unclear cases. This study provides scientific evidence that automated image analysis of the pancreas achieves comparable diagnostic accuracy to lipase levels and might therefore be used in the future in the rapidly growing era of AI-based image analysis.
RESUMEN
PURPOSE: To investigate the diagnostic performance of an automatic pipeline for detection of hydronephrosis on kidney's parenchyma on unenhanced low-dose CT of the abdomen. METHODS: This retrospective study included 95 patients with confirmed unilateral hydronephrosis in an unenhanced low-dose CT of the abdomen. Data were split into training (n = 67) and test (n = 28) cohorts. Both kidneys for each case were included in further analyses, whereas the kidney without hydronephrosis was used as control. Using the training cohort, we developed a pipeline consisting of a deep-learning model for automatic segmentation (a Convolutional Neural Network based on nnU-Net architecture) of the kidney's parenchyma and a radiomics classifier to detect hydronephrosis. The models were assessed using standard classification metrics, such as area under the ROC curve (AUC), sensitivity and specificity, as well as semantic segmentation metrics, including Dice coefficient and Jaccard index. RESULTS: Using manual segmentation of the kidney's parenchyma, hydronephrosis can be detected with an AUC of 0.84, a sensitivity of 75% and a specificity of 82%, a PPV of 81% and a NPV of 77%. Automatic kidney segmentation achieved a mean Dice score of 0.87 and 0.91 for the right and left kidney, respectively. Additionally, automatic segmentation achieved an AUC of 0.83, a sensitivity of 86%, specificity of 64%, PPV of 71%, and NPV of 82%. CONCLUSION: Our proposed radiomics signature using automatic kidney's parenchyma segmentation allows for accurate hydronephrosis detection on unenhanced low-dose CT scans of the abdomen independently of widened renal pelvis. This method could be used in clinical routine to highlight hydronephrosis to radiologists as well as clinicians, especially in patients with concurrent parapelvic cysts and might reduce time and costs associated with diagnosing hydronephrosis.
RESUMEN
OBJECTIVES: Open-access cancer imaging datasets have become integral for evaluating novel AI approaches in radiology. However, their use in quantitative analysis with radiomics features presents unique challenges, such as incomplete documentation, low visibility, non-uniform data formats, data inhomogeneity, and complex preprocessing. These issues may cause problems with reproducibility and standardization in radiomics studies. METHODS: We systematically reviewed imaging datasets with public copyright licenses, published up to March 2023 across four large online cancer imaging archives. We included only datasets with tomographic images (CT, MRI, or PET), segmentations, and clinical annotations, specifically identifying those suitable for radiomics research. Reproducible preprocessing and feature extraction were performed for each dataset to enable their easy reuse. RESULTS: We discovered 29 datasets with corresponding segmentations and labels in the form of health outcomes, tumor pathology, staging, imaging-based scores, genetic markers, or repeated imaging. We compiled a repository encompassing 10,354 patients and 49,515 scans. Of the 29 datasets, 15 were licensed under Creative Commons licenses, allowing both non-commercial and commercial usage and redistribution, while others featured custom or restricted licenses. Studies spanned from the early 1990s to 2021, with the majority concluding after 2013. Seven different formats were used for the imaging data. Preprocessing and feature extraction were successfully performed for each dataset. CONCLUSION: RadiomicsHub is a comprehensive public repository with radiomics features derived from a systematic review of public cancer imaging datasets. By converting all datasets to a standardized format and ensuring reproducible and traceable processing, RadiomicsHub addresses key reproducibility and standardization challenges in radiomics. CRITICAL RELEVANCE STATEMENT: This study critically addresses the challenges associated with locating, preprocessing, and extracting quantitative features from open-access datasets, to facilitate more robust and reliable evaluations of radiomics models. KEY POINTS: - Through a systematic review, we identified 29 cancer imaging datasets suitable for radiomics research. - A public repository with collection overview and radiomics features, encompassing 10,354 patients and 49,515 scans, was compiled. - Most datasets can be shared, used, and built upon freely under a Creative Commons license. - All 29 identified datasets have been converted into a common format to enable reproducible radiomics feature extraction.
RESUMEN
BACKGROUND: Bladder cancer (BC) treatment algorithms depend on accurate tumor staging. To date, computed tomography (CT) is recommended for assessment of lymph node (LN) metastatic spread in muscle-invasive and high-risk BC. However, the diagnostic efficacy of radiologist-evaluated CT imaging studies is limited. OBJECTIVE: To evaluate the performance of quantitative radiomics signatures for detection of LN metastases in BC. DESIGN, SETTING, AND PARTICIPANTS: Of 1354 patients with BC who underwent radical cystectomy (RC) with lymphadenectomy who were screened, 391 with pathological nodal staging (pN0: n = 297; pN+: n = 94) were included and randomized into training (n = 274) and test (n = 117) cohorts. Pelvic LNs were segmented manually and automatically. A total of 1004 radiomics features were extracted from each LN and a machine learning model was trained to assess pN status using histopathology labels as the ground truth. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Radiologist assessment was compared to radiomics-based analysis using manual and automated LN segmentations for detection of LN metastases in BC. Statistical analysis was performed using the receiver operating characteristics curve method and evaluated in terms of sensitivity, specificity, and area under the curve (AUC). RESULTS AND LIMITATIONS: In total, 1845 LNs were manually segmented. Automated segmentation correctly located 361/557 LNs in the test cohort. Manual and automatic masks achieved an AUC of 0.80 (95% confidence interval [CI] 0.69-0.91; p = 0.64) and 0.70 (95% CI: 0.58-0.82; p = 0.17), respectively, in the test cohort compared to radiologist assessment, with an AUC of 0.78 (95% CI 0.67-0.89). A combined model of a manually segmented radiomics signature and radiologist assessment reached an AUC of 0.81 (95% CI 0.71-0.92; p = 0.63). CONCLUSIONS: A radiomics signature allowed discrimination of nodal status with high diagnostic accuracy. The model based on manual LN segmentation outperformed the fully automated approach. PATIENT SUMMARY: For patients with bladder cancer, evaluation of computed tomography (CT) scans before surgery using a computer-based method for image analysis, called radiomics, may help in standardizing and improving the accuracy of assessment of lymph nodes. This could be a valuable tool for optimizing treatment options.
Asunto(s)
Ganglios Linfáticos , Neoplasias de la Vejiga Urinaria , Humanos , Escisión del Ganglio Linfático , Ganglios Linfáticos/patología , Metástasis Linfática/diagnóstico por imagen , Metástasis Linfática/patología , Estadificación de Neoplasias , Neoplasias de la Vejiga Urinaria/diagnóstico por imagen , Neoplasias de la Vejiga Urinaria/cirugía , Neoplasias de la Vejiga Urinaria/patologíaRESUMEN
OBJECTIVES: Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies. METHODS: In this study, 100 lung cancer patients underwent a contrast-enhanced 18F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional "hand-crafted" radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii). RESULTS: In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865-0.878), SBS 35.8 (34.2-37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively). CONCLUSION: Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.
RESUMEN
In photon-counting detector CT (PCD-CT), coronary artery calcium scoring (CACS) can be performed using virtual non-contrast (VNC) series derived from coronary CT angiography (CCTA) datasets. Our study analyzed image characteristics of VNC series in terms of the efficacy of virtual iodine "removal" and image noise to determine whether the prerequisites for calcium quantification were satisfied. We analyzed 38 patients who had undergone non-enhanced CT followed by CCTA on a PCD-CT. VNC reconstructions were performed at different settings and algorithms (conventional VNCConv; PureCalcium VNCPC). Virtual iodine "removal" was investigated by comparing histograms of heart volumes. Noise was assessed within the left ventricular cavity. Calcium was quantified on the true non-contrast (TNC) and all VNC series. The histograms were comparable for TNC and all VNC. Image noise between TNC and all VNC differed slightly but significantly. VNCConv CACS showed a significant underestimation regardless of the reconstruction setting, while VNCPC CACS were comparable to TNC. Correlations between TNC and VNC were excellent, with a higher predictive accuracy for VNCPC. In conclusion, the iodine contrast can be effectively subtracted from CCTA datasets. The remaining VNC series satisfy the requirements for CACS, yielding results with excellent correlation compared to TNC-based CACS and high predicting accuracy.
RESUMEN
OBJECTIVES: The goal of this study is to demonstrate the performance of radiomics and CNN-based classifiers in determining the primary origin of gastrointestinal liver metastases for visually indistinguishable lesions. METHODS: In this retrospective, IRB-approved study, 31 pancreatic cancer patients with 861 lesions (median age [IQR]: 65.39 [56.87, 75.08], 48.4% male) and 47 colorectal cancer patients with 435 lesions (median age [IQR]: 65.79 [56.99, 74.62], 63.8% male) were enrolled. A pretrained nnU-Net performed automated segmentation of 1296 liver lesions. Radiomics features for each lesion were extracted using pyradiomics. The performance of several radiomics-based machine-learning classifiers was investigated for the lesions and compared to an image-based deep-learning approach using a DenseNet-121. The performance was evaluated by AUC/ROC analysis. RESULTS: The radiomics-based K-nearest neighbor classifier showed the best performance on an independent test set with AUC values of 0.87 and an accuracy of 0.67. In comparison, the image-based DenseNet-121-classifier reached an AUC of 0.80 and an accuracy of 0.83. CONCLUSIONS: CT-based radiomics and deep learning can distinguish the etiology of liver metastases from gastrointestinal primary tumors. Compared to deep learning, radiomics based models showed a varying generalizability in distinguishing liver metastases from colorectal cancer and pancreatic adenocarcinoma.
Asunto(s)
Adenocarcinoma , Neoplasias Colorrectales , Aprendizaje Profundo , Neoplasias Hepáticas , Neoplasias Pancreáticas , Humanos , Masculino , Femenino , Estudios Retrospectivos , Neoplasias Pancreáticas/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias PancreáticasRESUMEN
Purpose: Machine learning based on radiomics features has seen huge success in a variety of clinical applications. However, the need for standardization and reproducibility has been increasingly recognized as a necessary step for future clinical translation. We developed a novel, intuitive open-source framework to facilitate all data analysis steps of a radiomics workflow in an easy and reproducible manner and evaluated it by reproducing classification results in eight available open-source datasets from different clinical entities. Methods: The framework performs image preprocessing, feature extraction, feature selection, modeling, and model evaluation, and can automatically choose the optimal parameters for a given task. All analysis steps can be reproduced with a web application, which offers an interactive user interface and does not require programming skills. We evaluated our method in seven different clinical applications using eight public datasets: six datasets from the recently published WORC database, and two prostate MRI datasets-Prostate MRI and Ultrasound With Pathology and Coordinates of Tracked Biopsy (Prostate-UCLA) and PROSTATEx. Results: In the analyzed datasets, AutoRadiomics successfully created and optimized models using radiomics features. For WORC datasets, we achieved AUCs ranging from 0.56 for lung melanoma metastases detection to 0.93 for liposarcoma detection and thereby managed to replicate the previously reported results. No significant overfitting between training and test sets was observed. For the prostate cancer detection task, results were better in the PROSTATEx dataset (AUC = 0.73 for prostate and 0.72 for lesion mask) than in the Prostate-UCLA dataset (AUC 0.61 for prostate and 0.65 for lesion mask), with external validation results varying from AUC = 0.51 to AUC = 0.77. Conclusion: AutoRadiomics is a robust tool for radiomic studies, which can be used as a comprehensive solution, one of the analysis steps, or an exploratory tool. Its wide applicability was confirmed by the results obtained in the diverse analyzed datasets. The framework, as well as code for this analysis, are publicly available under https://github.com/pwoznicki/AutoRadiomics.
RESUMEN
(1) Background: Tumoral heterogeneity (TH) is a major challenge in the treatment of metastatic colorectal cancer (mCRC) and is associated with inferior response. Therefore, the identification of TH would be beneficial for treatment planning. TH can be assessed by identifying genetic alterations. In this work, a radiomics-based approach for assessment of TH in colorectal liver metastases (CRLM) in CT scans is demonstrated. (2) Methods: In this retrospective study, CRLM of mCRC were segmented and radiomics features extracted using pyradiomics. Unsupervised k-means clustering was applied to features and lesions. Feature redundancy was evaluated by principal component analysis and reduced by Pearson correlation coefficient cutoff. Feature selection was conducted by LASSO regression and visual analysis of the clusters by radiologists. (3) Results: A total of 47 patients' (36% female, median age 64) CTs with 261 lesions were included. Five clusters were identified, and the categories small disseminated (n = 31), heterogeneous (n = 105), homogeneous (n = 64), mixed (n = 59), and very large type (n = 2) were assigned based on visual characteristics. Further statistical analysis showed correlation (p < 0.01) of clusters with sex, primary location, T- and N-status, and mutational status. Feature reduction and selection resulted in the identification of four features as a final set for cluster definition. (4) Conclusions: Radiomics features can characterize TH in liver metastases of mCRC in CT scans, and may be suitable for a better pretherapeutic classification of liver lesion phenotypes.
RESUMEN
Background: Imaging-based total kidney volume (TKV) and total liver volume (TLV) are major prognostic factors in autosomal dominant polycystic kidney disease (ADPKD) and end points for clinical trials. However, volumetry is time consuming and reader dependent in clinical practice. Our aim was to develop a fully automated method for joint kidney and liver segmentation in magnetic resonance imaging (MRI) and to evaluate its performance in a multisequence, multicenter setting. Methods: The convolutional neural network was trained on a large multicenter dataset consisting of 992 MRI scans of 327 patients. Manual segmentation delivered ground-truth labels. The model's performance was evaluated in a separate test dataset of 93 patients (350 MRI scans) as well as a heterogeneous external dataset of 831 MRI scans from 323 patients. Results: The segmentation model yielded excellent performance, achieving a median per study Dice coefficient of 0.92-0.97 for the kidneys and 0.96 for the liver. Automatically computed TKV correlated highly with manual measurements (intraclass correlation coefficient [ICC]: 0.996-0.999) with low bias and high precision (-0.2%±4% for axial images and 0.5%±4% for coronal images). TLV estimation showed an ICC of 0.999 and bias/precision of -0.5%±3%. For the external dataset, the automated TKV demonstrated bias and precision of -1%±7%. Conclusions: Our deep learning model enabled accurate segmentation of kidneys and liver and objective assessment of TKV and TLV. Importantly, this approach was validated with axial and coronal MRI scans from 40 different scanners, making implementation in clinical routine care feasible.Clinical Trial registry name and registration number: The German ADPKD Tolvaptan Treatment Registry (AD[H]PKD), NCT02497521.
Asunto(s)
Riñón Poliquístico Autosómico Dominante , Humanos , Riñón Poliquístico Autosómico Dominante/diagnóstico por imagen , Riñón/diagnóstico por imagen , Riñón/patología , Imagen por Resonancia Magnética/métodos , Hígado/diagnóstico por imagen , Hígado/patología , Redes Neurales de la ComputaciónRESUMEN
(1) Background: To evaluate radiomics features as well as a combined model with clinical parameters for predicting overall survival in patients with bladder cancer (BCa). (2) Methods: This retrospective study included 301 BCa patients who received radical cystectomy (RC) and pelvic lymphadenectomy. Radiomics features were extracted from the regions of the primary tumor and pelvic lymph nodes as well as the peritumoral regions in preoperative CT scans. Cross-validation was performed in the training cohort, and a Cox regression model with an elastic net penalty was trained using radiomics features and clinical parameters. The models were evaluated with the time-dependent area under the ROC curve (AUC), Brier score and calibration curves. (3) Results: The median follow-up time was 56 months (95% CI: 48−74 months). In the follow-up period from 1 to 7 years after RC, radiomics models achieved comparable predictive performance to validated clinical parameters with an integrated AUC of 0.771 (95% CI: 0.657−0.869) compared to an integrated AUC of 0.761 (95% CI: 0.617−0.874) for the prediction of overall survival (p = 0.98). A combined clinical and radiomics model stratified patients into high-risk and low-risk groups with significantly different overall survival (p < 0.001). (4) Conclusions: Radiomics features based on preoperative CT scans have prognostic value in predicting overall survival before RC. Therefore, radiomics may guide early clinical decision-making.
RESUMEN
The purpose of this study was to evaluate virtual-non contrast reconstructions of Photon-Counting Detector (PCD) CT-angiography datasets using a novel calcium-preserving algorithm (VNCPC) vs. the standard algorithm (VNCConv) for their potential to replace unenhanced acquisitions (TNC) in patients after endovascular aneurysm repair (EVAR). 20 EVAR patients who had undergone CTA (unenhanced and arterial phase) on a novel PCD-CT were included. VNCConv- and VNCPC-series were derived from CTA-datasets and intraluminal signal and noise compared. Three readers evaluated image quality, contrast removal, and removal of calcifications/stent parts and assessed all VNC-series for their suitability to replace TNC-series. Image noise was higher in VNC- than in TNC-series (18.6 ± 5.3 HU, 16.7 ± 7.1 HU, and 14.9 ± 7.1 HU for VNCConv-, VNCPC-, and TNC-series, p = 0.006). Subjective image quality was substantially higher in VNCPC- than VNCConv-series (4.2 ± 0.9 vs. 2.5 ± 0.6; p < 0.001). Aortic contrast removal was complete in all VNC-series. Unlike in VNCConv-reconstructions, only minuscule parts of stents or calcifications were erroneously subtracted in VNCPC-reconstructions. Readers considered 95% of VNCPC-series fully or mostly suited to replace TNC-series; for VNCConv-reconstructions, however, only 75% were considered mostly (and none fully) suited for TNC-replacement. VNCPC-reconstructions of PCD-CT-angiography datasets have excellent image quality with complete contrast removal and only minimal erroneous subtractions of stent parts/calcifications. They could replace TNC-series in almost all cases.
RESUMEN
In dual-energy CT datasets, the conspicuity of liver metastases can be enhanced by virtual monoenergetic imaging (VMI) reconstructions at low keV levels. Our study investigated whether this effect can be reproduced in photon-counting detector CT (PCD-CT) datasets. We analyzed 100 patients with liver metastases who had undergone contrast-enhanced CT of the abdomen on a PCD-CT (n = 50) or energy-integrating detector CT (EID-CT, single-energy mode, n = 50). PCD-VMI-reconstructions were performed at various keV levels. Identical regions of interest were positioned in metastases, normal liver, and other defined locations assessing image noise, tumor-to-liver ratio (TLR), and contrast-to-noise ratio (CNR). Patients were compared inter-individually. Subgroup analyses were performed according to BMI. On the PCD-CT, noise and CNR peaked at the low end of the keV spectrum. In comparison with the EID-CT, PCD-VMI-reconstructions exhibited lower image noise (at 70 keV) but higher CNR (for ≤70 keV), despite similar CTDIs. Comparing high- and low-BMI patients, CTDI-upregulation was more modest for the PCD-CT but still resulted in similar noise levels and preserved CNR, unlike the EID-CT. In conclusion, PCD-CT VMIs in oncologic patients demonstrated reduced image noise-compared to a standard EID-CT-and improved conspicuity of hypovascularized liver metastases at low keV values. Patients with higher BMIs especially benefited from constant image noise and preservation of lesion conspicuity, despite a more moderate upregulation of CTDI.
RESUMEN
PURPOSE: To analyze the quantitative and qualitative image quality of low-dose CT scans of the abdomen on a novel photon-counting detector CT (PCD-CT) in comparison with a traditional energy-integrating detector CT (EID-CT). METHODS: Consecutive patients with clinically indicated low-dose CT were scanned on a PCD-CT and compared with a BMI-matched EID-CT-cohort scanned during the same timeframe. Radiation dose, image noise, and signal-to-noise ratio (SNR) were measured for each patient. Furthermore, image quality and conspicuity of abdominal structures (adrenal glands, mesenteric vessels, ureters, and renal pelvis) were assessed on 5-point Likert-scales (1 = very poor quality/not detectable; 5 = excellent quality/differentiability). RESULTS: Twenty patients (mean age 46.2 [range: 19-77]; 13 men) were included. Image noise was significantly lower (24.9 ± 3.3 vs. 31.4 ± 5.6 SD HU, p < 0.001) and SNR significantly higher (2.1 ± 0.3 vs. 1.5 ± 0.4; p < 0.001) on the PCD-CT. Subjective image quality was substantially higher (4.0 ± 0.3 vs. 3.1 ± 0.6; p < 0.001) and conspicuity better for the renal pelvis, ureters, and mesenteric vessels on the PCD-CT. There was no significant difference in the conspicuity of the adrenal glands. With increasing BMI (1st-4th BMI quartile), noise increased, and SNR decreased more strongly on the EID-CT than on the PCD-CT (ΔNoise: 39% vs. 2%, ΔSNR: -33% vs. -7% for EID-CT vs. PCD-CT, respectively) while radiation dose increased comparably (70 vs. 59%). CONCLUSIONS: Low-dose CT scans of the abdomen performed on a novel PCD-CT exhibit reduced noise, higher SNR, increased subjective image quality, and superior conspicuity of abdominal fine structures compared to scans in comparable patients on an EID-CT.
Asunto(s)
Fotones , Tomografía Computarizada por Rayos X , Abdomen/diagnóstico por imagen , Humanos , Masculino , Persona de Mediana Edad , Fantasmas de Imagen , Dosis de Radiación , Relación Señal-Ruido , Tomografía Computarizada por Rayos X/métodosRESUMEN
PURPOSE: The aim of this study was to evaluate coronary computed tomography angiography (CCTA)-based in vitro and in vivo coronary artery calcium scoring (CACS) using a novel virtual noniodine reconstruction (PureCalcium) on a clinical first-generation photon-counting detector-computed tomography system compared with virtual noncontrast (VNC) reconstructions and true noncontrast (TNC) acquisitions. MATERIALS AND METHODS: Although CACS and CCTA are well-established techniques for the assessment of coronary artery disease, they are complementary acquisitions, translating into increased scan time and patient radiation dose. Hence, accurate CACS derived from a single CCTA acquisition would be highly desirable. In this study, CACS based on PureCalcium, VNC, and TNC, reconstructions was evaluated in a CACS phantom and in 67 patients (70 [59/80] years, 58.2% male) undergoing CCTA on a first-generation photon counting detector-computed tomography system. Coronary artery calcium scores were quantified for the 3 reconstructions and compared using Wilcoxon test. Agreement was evaluated by Pearson and Spearman correlation and Bland-Altman analysis. Classification of coronary artery calcium score categories (0, 1-10, 11-100, 101-400, and >400) was compared using Cohen κ . RESULTS: Phantom studies demonstrated strong agreement between CACS PureCalcium and CACS TNC (60.7 ± 90.6 vs 67.3 ± 88.3, P = 0.01, r = 0.98, intraclass correlation [ICC] = 0.98; mean bias, 6.6; limits of agreement [LoA], -39.8/26.6), whereas CACS VNC showed a significant underestimation (42.4 ± 75.3 vs 67.3 ± 88.3, P < 0.001, r = 0.94, ICC = 0.89; mean bias, 24.9; LoA, -87.1/37.2). In vivo comparison confirmed a high correlation but revealed an underestimation of CACS PureCalcium (169.3 [0.7/969.4] vs 232.2 [26.5/1112.2], P < 0.001, r = 0.97, ICC = 0.98; mean bias, -113.5; LoA, -470.2/243.2). In comparison, CACS VNC showed a similarly high correlation, but a substantially larger underestimation (24.3 [0/272.3] vs 232.2 [26.5/1112.2], P < 0.001, r = 0.97, ICC = 0.54; mean bias, -551.6; LoA, -2037.5/934.4). CACS PureCalcium showed superior agreement of CACS classification ( κ = 0.88) than CACS VNC ( κ = 0.60). CONCLUSIONS: The accuracy of CACS quantification and classification based on PureCalcium reconstructions of CCTA outperforms CACS derived from VNC reconstructions.
Asunto(s)
Angiografía por Tomografía Computarizada , Enfermedad de la Arteria Coronaria , Algoritmos , Calcio , Angiografía por Tomografía Computarizada/métodos , Angiografía Coronaria/métodos , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Femenino , Humanos , Masculino , Tomografía Computarizada por Rayos X/métodosRESUMEN
Radiomics is an emerging field of image analysis with potential applications in patient risk stratification. This study developed and evaluated machine learning models using quantitative radiomic features extracted from multiparametric magnetic resonance imaging (mpMRI) to detect and classify prostate cancer (PCa). In total, 191 patients that underwent prostatic mpMRI and combined targeted and systematic fusion biopsy were retrospectively included. Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI. Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion. The best performing combination of feature setup and classifier was selected to compare its predictive ability of the radiologist's evaluation (PI-RADS), mean ADC, prostate specific antigen density (PSAD) and digital rectal examination (DRE) using receiver operating characteristic (ROC) analysis. Models were evaluated using repeated 5-fold cross-validation and a separate independent test cohort. In the test cohort, an ensemble model combining a radiomics model, with models for PI-RADS, PSAD and DRE achieved high predictive AUCs for the differentiation of (i) malignant from benign prostatic lesions (AUC = 0.889) and of (ii) clinically significant (csPCa) from clinically insignificant PCa (cisPCa) (AUC = 0.844). Our combined model was numerically superior to PI-RADS for cancer detection (AUC = 0.779; p = 0.054) as well as for clinical significance prediction (AUC = 0.688; p = 0.209) and showed a significantly better performance compared to mADC for csPCa prediction (AUC = 0.571; p = 0.022). In our study, radiomics accurately characterizes prostatic index lesions and shows performance comparable to radiologists for PCa characterization. Quantitative image data represent a potential biomarker, which, when combined with PI-RADS, PSAD and DRE, predicts csPCa more accurately than mADC. Prognostic machine learning models could assist in csPCa detection and patient selection for MRI-guided biopsy.