Deep learning-based reconstruction enhances image quality and improves diagnosis in magnetic resonance imaging of the shoulder joint.

Background: Accelerated magnetic resonance imaging sequences reconstructed using the vendor-provided Recon deep learning algorithm (DL-MRI) were found to be more likely than conventional magnetic resonance imaging (MRI) sequences to detect subacromial (SbA) bursal thickening. However, the extent of this thickening was not extensively explored. This study aimed to compare the image quality of DL-MRI with conventional MRI sequences reconstructed via conventional pipelines (Conventional-MRI) for shoulder examinations and evaluate the effectiveness of DL-MRI in accurately demonstrating the degree of SbA bursal and subcoracoid (SC) bursal thickening. Methods: This prospective cross-sectional study enrolled 41 patients with chronic shoulder pain who underwent 3-T MRI (including both Conventional-MRI and accelerated MRI sequences) of the shoulder between December 2022 and April 2023. Each protocol consisted of oblique axial, coronal, and sagittal images, including proton density-weighted imaging (PDWI) with fat suppression (FS) and oblique coronal T1-weighted imaging (T1WI) with FS. The image quality and degree of artifacts were assessed using a 5-point Likert scale for both Conventional-MRI and DL-MRI. Additionally, the degree of SbA and SC bursal thickening, as well as the relative signal-to-noise ratio (rSNR) and relative contrast-to-noise ratio (rCNR) were analyzed using the paired Wilcoxon test. Statistical significance was defined as P<0.05. Results: The utilization of accelerated sequences resulted in a remarkable 54.7% reduction in total scan time. Overall, DL-MRI exhibited superior image quality scores and fewer artifacts compared to Conventional-MRI. Specifically, DL-MRI demonstrated significantly higher measurements of SC bursal thickenings in the oblique sagittal PDWI sequence compared to Conventional-MRI [3.92 (2.83, 5.82) vs. 3.74 (2.92, 5.96) mm, P=0.028]. Moreover, DL-MRI exhibited higher detection of SbA bursal thickenings in the oblique coronal PDWI sequence [2.61 (1.85, 3.46) vs. 2.48 (1.84, 3.25) mm], with a notable trend towards significant differences (P=0.071). Furthermore, the rSNRs of the muscle in DL-MRI images were significantly higher than those in Conventional-MRI images across most sequences (P<0.001). However, the rSNRs of bone on Conventional-MRI of oblique axial and oblique coronal PDWI sequences showed adverse results [oblique axial: 1.000 (1.000, 1.000) vs. 0.444 (0.367, 0.523); and oblique coronal: 1.000 (1.000, 1.000) vs. 0.460 (0.387, 0.631); all P<0.001]. Additionally, all DL-MRI images exhibited significantly greater rSNRs and rCNRs compared to accelerated MRI sequences reconstructed using traditional pipelines (P<0.001). Conclusions: In conclusion, the utilization of DL-MRI enhances image quality and improves diagnostic capabilities, making it a promising alternative to Conventional-MRI for shoulder imaging.

Atrophy patterns in hippocampus and amygdala subregions of depressed patients with Parkinson's disease.

We aimed to explore the subregional atrophy patterns of the amygdala and hippocampus in Parkinson's disease (PD) with depression and their correlation with the severity of the depressive symptom. MRI scans were obtained for 34 depressed PD patients (DPD), 22 nondepressed PD patients (NDPD), and 28 healthy controls (HC). Amygdala and hippocampal subregions were automatically segmented, and the intergroup volume difference was compared. The relationships between the volumes of the subregions and depression severity were investigated. Logistic analysis and Receiver operator characteristic curve were used to find independent predictors of DPD. Compared with the HC group, atrophy of the bilateral lateral nucleus, left accessory basal nucleus, right cortical nucleus, right central nucleus, and right medial nucleus subregions of the amygdala were visible in the DPD group, while the right lateral nucleus subregion of the amygdala was smaller in the DPD group than in the NDPD group. The DPD group showed significant atrophy in the left molecular layer, left GC-DG, left CA3, and left CA4 subregions compared with the HC group for hippocampal subregion volumes. Also, the right lateral nuclei volume and disease duration were independent predictors of DPD. To sum up, DPD patients showed atrophy in multiple amygdala subregions and left asymmetric hippocampal subregions. The decreased amygdala and hippocampal subregion volumes were correlated with the severity of depressive symptoms. The volume of right lateral nuclei and disease duration could be used as a biomarker to detect DPD.

Association Between MRI Radiomics and Intratumoral Tertiary Lymphoid Structures in Intrahepatic Cholangiocarcinoma and Its Prognostic Significance.

BACKGROUND: Tertiary lymphoid structures (TLSs) have prognostic value in intrahepatic cholangiocarcinoma (ICC) patients. Noninvasive tool to preoperatively evaluate TLSs is still lacking. PURPOSE: To explore the association between TLSs status of ICC and preoperative MRI radiomics analysis. STUDY TYPE: Retrospective. SUBJECTS: One hundred and ninety-two patients with ICC, divided into training (T = 105), internal validation groups (V1 = 46), and external validation group (V2 = 41). SEQUENCE: Coronal and axial single-shot fast spin-echo T2-weighted, diffusion-weighted imaging, T1-weighted, and T1WI fat-suppressed spoiled gradient-recall echo LAVA sequence at 3.0 T. ASSESSMENT: The VOIs were drawn manually within the visible borders of the tumors using ITK-SNAP version 3.8.0 software in the axial T2WI, DWI, and portal vein phase sequences. Radiomics features were subjected to least absolute shrinkage and selection operator regression to select the associated features of TLSs and construct the radiomics model. Univariate and multivariate analyses were used to identify the clinical radiological variables associated with TLSs. The performances were evaluated by the area under the receiver operator characteristic curve (AUC). STATISTICAL TESTS: Logistic regression analysis, ROC and AUC, Hosmer-Lemeshow test, Kaplan-Meier method with the log-rank test, calibration curves, and decision curve analysis. P < 0.05 was considered statistically significant. RESULTS: The AUCs of arterial phase diffuse hyperenhancement were 0.59 (95% confidence interval [CI], 0.50-0.67), 0.52 (95% CI, 0.43-0.61), and 0.66 (95% CI, 0.52-0.80) in the T, V1, and V2 cohorts. The AUCs of Rad-score were 0.85 (95% CI, 0.77-0.92), 0.81 (95% CI, 0.67-0.94), and 0.84 (95% CI, 0.71-0.96) in the T, V1, and V2 cohorts, respectively. In cohort T, low-risk group showed significantly better median recurrence-free survival (RFS) than that of the high-risk group, which was also confirmed in cohort V1 and V2. DATA CONCLUSION: A preoperative MRI radiomics signature is associated with the intratumoral TLSs status of ICC patients and correlate significantly with RFS. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

A CT-based radiomics approach to predict intra-tumoral tertiary lymphoid structures and recurrence of intrahepatic cholangiocarcinoma.

PURPOSE: To predict the tertiary lymphoid structures (TLSs) status and recurrence-free survival (RFS) of intrahepatic cholangiocarcinoma (ICC) patients using preoperative CT radiomics. PATIENTS AND METHODS: A total of 116 ICC patients were included (training: 86; external validation: 30). The enhanced CT images were performed for the radiomics model. The logistic regression analysis was applied for the clinical model. The combined model was based on the clinical and radiomics models. RESULTS: A total of 107 radiomics features were extracted, and after being eliminated and selected, six features were combined to establish a radiomics model for TLSs prediction. Arterial phase diffuse hyperenhancement and AJCC 8th stage were combined to construct a clinical model. The combined (radiomics nomogram) model outperformed both the independent radiomics model and clinical model in the training cohort (AUC, 0.85 vs. 0.82 and 0.75, respectively) and was validated in the external validation cohort (AUC, 0.88 vs. 0.86 and 0.71, respectively). Patients in the rad-score no less than -0.76 (low-risk) group showed significantly better RFS than those in the less than -0.76 (high-risk) group (p < 0.001, C-index = 0.678). Patients in the nomogram score no less than -1.16 (low-risk) group showed significantly better RFS than those of the less than -1.16 (high-risk) group (p < 0.001, C-index = 0.723). CONCLUSIONS: CT radiomics nomogram could serve as a preoperative biomarker of intra-tumoral TLSs status, better than independent radiomics or clinical models; preoperative CT radiomics nomogram achieved accurate stratification for RFS of ICC patients, better than the postoperative pathologic TLSs status. CRITICAL RELEVANCE STATEMENT: The radiomics nomogram showed better performance in predicting TLSs than independent radiomics or clinical models and better prognosis stratification than postoperative pathologic TLSs status in ICC patients, which may facilitate identifying patients benefiting most from surgery and subsequent immunotherapy. KEY POINTS: • The combined (radiomics nomogram) model consisted of the radiomics model and clinical model (arterial phase diffuse hyperenhancement and AJCC 8th stage). • The radiomics nomogram showed better performance in predicting TLSs than independent radiomics or clinical models in ICC patients. • Preoperative CT radiomics nomogram achieved more accurate stratification for RFS of ICC patients than the postoperative pathologic TLSs status.

Synthetic MRI plus FSE-PROPELLER DWI for differentiating malignant from benign head and neck tumors: a preliminary study.

Background: Preoperative classification of head and neck (HN) tumors remains challenging, especially distinguishing early cancerogenic masses from benign lesions. Synthetic MRI offers a new way for quantitative analysis of tumors. The present study investigated the application of synthetic MRI and stimulus and fast spin echo diffusion-weighted imaging with periodically rotated overlapping parallel lines with enhanced reconstruction (FSE-PROPELLER DWI) to differentiate malignant from benign HN tumors. Materials and methods: Forty-eight patients with pathologically confirmed HN tumors were retrospectively recruited between August 2022 and October 2022. The patients were divided into malignant (n = 28) and benign (n = 20) groups. All patients were scanned using synthetic MRI and FSE-PROPELLER DWI. T1, T2, and proton density (PD) values were acquired on the synthetic MRI and ADC values on the FSE-PROPELLER DWI. Results: Benign tumors (ADC: 2.03 ± 0.31 × 10-3 mm2/s, T1: 1741.13 ± 662.64 ms, T2: 157.43 ± 72.23 ms) showed higher ADC, T1, and T2 values compared to malignant tumors (ADC: 1.46 ± 0.37 × 10-3 mm2/s, T1: 1390.06 ± 241.09 ms, T2: 97.64 ± 14.91 ms) (all P<0.05), while no differences were seen for PD values. ROC analysis showed that T2+ADC (cut-off value, > 0.55; AUC, 0.950) had optimal diagnostic performance vs. T1 (cut-off value, ≤ 1675.84 ms; AUC, 0.698), T2 (cut-off value, ≤ 113.24 ms; AUC, 0.855) and PD (cut off value, > 80.67 pu; AUC, 0.568) alone in differentiating malignant from benign lesions (all P<0.05); yet, the difference in AUC between ADC and T2+ADC or T2 did not reach statistical significance. Conclusion: Synthetic MRI and FSE-PROPELLER DWI can quantitatively differentiate malignant from benign HN tumors. T2 value is comparable to ADC value, and T2+ADC values could improve diagnostic efficacy., apparent diffusion coeffificient, head and neck tumors.

Correlation between synthetic MRI relaxometry and apparent diffusion coefficient in breast cancer subtypes with different neoadjuvant therapy response.

BACKGROUND: To evaluate the correlation between synthetic MRI (syMRI) relaxometry and apparent diffusion coefficient (ADC) maps in different breast cancer subtypes and treatment response subgroups. METHODS: Two hundred sixty-three neoadjuvant therapy (NAT)-treated breast cancer patients with baseline MRI were enrolled. Tumor annotations were obtained by drawing regions of interest (ROIs) along the lesion on T1/T2/PD and ADC maps respectively. Histogram features from T1/T2/PD and ADC maps were respectively calculated, and the correlation between each pair of identical features was analyzed. Meanwhile, features between different NAT treatment response groups were compared, and their discriminatory power was evaluated. RESULTS: Among all patients, 20 out of 27 pairs of features weakly correlated (r = - 0.13-0.30). For triple-negative breast cancer (TNBC), features from PD map in the pathological complete response (pCR) group (r = 0.60-0.86) showed higher correlation with ADC than that of the non-pCR group (r = 0.30-0.43), and the mean from the ADC and PD maps in the pCR group strongly correlated (r = 0.86). For HER2-positive, few correlations were found both in the pCR and non-pCR groups. For luminal HER2-negative, T2 map correlated more with ADC than T1 and PD maps. Significant differences were seen in T2 low percentiles and median in the luminal-HER2 negative subtype, yielding moderate AUCs (0.68/0.72/0.71). CONCLUSIONS: The relationship between ADC and PD maps in TNBC may indicate different NAT responses. The no-to-weak correlation between the ADC and syMRI suggests their complementary roles in tumor microenvironment evaluation. CRITICAL RELEVANCE STATEMENT: The relationship between ADC and PD maps in TNBC may indicate different NAT responses, and the no-to-weak correlation between the ADC and syMRI suggests their complementary roles in tumor microenvironment evaluation. KEY POINTS: • The relationship between ADC and PD in TNBC indicates different NAT responses. • The no-to-weak correlations between ADC and syMRI complementarily evaluate tumor microenvironment. • T2 low percentiles and median predict NAT response in luminal-HER2-negative subtype.

Diffusion kurtosis imaging with multiple quantitative parameters for predicting microsatellite instability status of endometrial carcinoma.

PURPOSE: To explore the value of Diffusion kurtosis imaging (DKI) with multiple quantitative parameters in predicting microsatellite instability (MSI) status in endometrial carcinoma (EC). METHODS: Data of 38 patients with EC were retrospectively analyzed, including 12 MSI and 26 microsatellite stability (MSS). All patients underwent preoperative 1.5T MR examination. The quantitative values of the DKI sequence in the tumor parenchyma of the two groups, including mean kurtosis (MK), axial kurtosis (Ka), radial kurtosis (Kr), fractional anisotropy (FA), fractional anisotropy of kurtosis (FAk), mean diffusivity (MD), axial diffusivity (Da), and radial diffusivity (Dr) were measured by two observers, respectively. RESULTS: The MK, Ka, Kr, FA, FAk, MD, Da, and Dr values of the MSI group were 1.074 ± 0.162, 1.253 ± 0.229, 0.886 ± 0.205, 0.207 ± 0.041, 0.397 ± 0.129, 0.890 ± 0.158 µm2/ms, 1.083 ± 0.218 µm2/ms, and 0.793 ± 0.133 µm2/ms, and 0.956 (0.889,1.002), 1.048 ± 0.211, 0.831 ± 0.099, 0.188 ± 0.061, 0.334 (0.241,0.410), 1.043 ± 0.217 µm2/ms, 1.235 ± 0.229 µm2/ms, and 0.946 ± 0.215 µm2/ms in the MSS group. The MK and Ka values of the MSI group were higher than those of the MSS group (P<0.05), while the MD and Dr values were lower than those of the MSS group (P<0.05). The AUC of MK, Ka, MD, and Dr values in predicting MSI status of EC was 0.763, 0.729, 0.731, 0.748, respectively. The sensitivity was 58.3%, 50.0%, 65.4%, 61.5%, and the specificity was 96.2%, 92.3%, 75.0%, 83.3%, respectively. CONCLUSION: DKI can provide multiple quantitative parameters for predicting the MSI status of EC, and assist gynecologist to optimize the treatment plan for the patients.

Evaluation of late gadolinium enhancement cardiac MRI using deep learning reconstruction.

BACKGROUND: Deep learning (DL)-based methods have been used to improve the imaging quality of magnetic resonance imaging (MRI) by denoising. PURPOSE: To assess the effects of DL-based MR reconstruction (DLR) method on late gadolinium enhancement (LGE) image quality. MATERIAL AND METHODS: A total of 85 patients who underwent cardiovascular magnetic resonance (CMR) examination, including LGE imaging using conventional construction and DLR with varying levels of noise reduction (NR) levels, were included. Both magnitude LGE (MLGE) and phase-sensitive LGE (PSLGE) images were reviewed independently by double-blinded observers who used a 5-point Likert scale for multiple measures regarding image quality. Meanwhile, the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness of images were calculated and compared between conventional LGE imaging and DLR LGE imaging. RESULTS: Both MLGE and PSLGE with DLR at 50% and 75% noise reduction levels received significantly higher scores than conventional imaging for overall imaging quality (all P < 0.01). In addition, the SNR, CNR, and edge sharpness of all DLR LGE imaging are higher than conventional imaging (all P < 0.01). The highest subjective score and best image quality is obtained when the DLR noise reduction level is at 75%. CONCLUSION: DLR reduced image noise while improving image contrast and sharpness in the cardiovascular LGE imaging.

MRI-Based Radiomics Nomogram for Preoperatively Differentiating Intrahepatic Mass-Forming Cholangiocarcinoma From Resectable Colorectal Liver Metastases.

RATIONALE AND OBJECTIVES: To establish a radiomics nomogram based on multiparameter magnetic resonance (MR) images for preoperatively differentiating intrahepatic mass-forming cholangiocarcinoma (IMCC) from colorectal cancer liver metastasis (CRLM). MATERIALS AND METHODS: A total of 133 patients in training cohort (64 IMCC and 69 CRLM), 57 patients in internal validation cohort (29 IMCC and 28 CRLM), and 51 patients (23 IMCC and 28 CRLM) in external validation cohort were included. Radiomics features were extracted from the multiparameter MR images and selected by the least absolute shrinkage and selection operator algorithm to establish the radiomics model. Clinical variables and magnetic resonance imaging (MRI) findings were selected by univariate and multivariate analyses to construct a clinical model. The radiomics nomogram was combined with radiomics model and clinical model. RESULTS: Six features were selected to construct the radiomics model. The radiomics signature showed better discrimination than the clinical model in the training cohort (Area Under the Curve (AUC), 0.92; 95% confidence interval (CI), 0.87-0.96 vs. AUC, 0.74; 95% CI, 0.66-0.83) and the external validation cohort (AUC, 0.90; 95% CI, 0.82-0.98 vs. AUC, 0.81; 95% CI, 0.69-0.93). The radiomics nomogram showed the best discrimination performance with favorable calibration in the training cohort (AUC, 0.94; 95% CI, 0.90-0.97) and the external validation cohort (AUC, 0.92; 95% CI, 0.84-1.00). CONCLUSION: The radiomics nomogram combining radiomics signatures based on multiparameter MRI with clinical factors (serum carcinoembryonic antigen level and tumor diameter) may provide a reliable and noninvasive tool to discriminate IMCC from CRLM, which could help guide treatment strategies and prognosis preoperatively prediction.

Longitudinal assessment of cardiac parameters through MRI in breast cancer patients treated with anti-HER2 therapy.

BACKGROUND: We evaluated the early changes in left ventricular (LV) volumetric, functional, and tissue characteristics in human epidermal growth factor receptor 2 (HER2)-positive breast cancer patients treated with trastuzumab and/or pertuzumab at cardiac magnetic resonance imaging (MRI). METHODS: HER2-positive breast cancer patients undergoing planned anti-HER2 therapy and nonanthracycline-based chemotherapy were enrolled and subdivided into dual anti-HER2 (trastuzumab plus pertuzumab) group and trastuzumab group. Cardiac MRI was performed before treatment and three months after starting, covering ventricular volumes, cardiac function, systolic myocardial strain, myocardial oedema, and T1 and T2 relaxation times. Cardiac dysfunction was primarily defined as a > 10% reduction in LV ejection fraction (LVEF) to < 55% and/or a > 15% global longitudinal strain (GLS) change at the follow-up MRI examination. RESULTS: Twenty-four HER2-positive patients were evaluated (16 in the dual anti-HER2 group, 8 in the trastuzumab group). Six patients developed cardiac dysfunction at follow-up, five of them in the dual anti-HER2 group. One patient developed symptomatic heart failure, and five patients developed asymptomatic cardiac dysfunction. Patients displayed significantly decreased systolic function and increased T1 and T2 relaxation time at follow-up (p ≤ 0.031). Systolic dysfunction remained significant in the dual anti-HER2 group. The decrease in GLS in the trastuzumab group was not significant (p = 0.169). T1 and T2 relaxation times tended to increase, but this was not significant at subgroup analysis. CONCLUSIONS: Cardiac MRI scans showed frequent signs of subclinical cardiotoxicity after short-term anti-HER2 therapy and nonanthracycline-based chemotherapy; the effect was slightly stronger in patients treated with dual therapy. KEY POINTS: • A frequent subclinical cardiotoxicity was detected by cardiac magnetic resonance imaging after short-term anti-human epidermal growth factor receptor 2 (HER2) therapy. • The change in myocardial strain was more marked in patients treated with dual (trastuzumab plus pertuzumab) than with trastuzumab only anti-HER2 therapy. • Cardiotoxicity surveillance through MRI is an interesting option particularly in patients treated with dual anti-HER2 therapy.

Histogram analysis of quantitative parameters from synthetic MRI: correlations with prognostic factors in nasopharyngeal carcinoma.

OBJECTIVES: To evaluate the correlation between histogram parameters derived from synthetic magnetic resonance imaging (SyMRI) and prognostically relevant factors in nasopharyngeal carcinoma (NPC). METHODS: Fifty-nine consecutive NPC patients were prospectively enrolled. Quantitative parameters (T1, T2, and proton density (PD)) were obtained by outlining the three-dimensional volume of interest (VOI) of all lesions. Then, histogram analysis of these quantitative parameters was performed and the correlations with prognostically relevant factors were assessed. By choosing appropriate cutoff, we divided the sample into two groups. Independent-samples t test/Mann-Whitney U test was used and ROC curve analysis was further processed. RESULTS: Histogram parameters of the T1, T2, and PD maps were positively correlated with the Ki-67 expression levels, and PD_mean was the most representative parameter (AUC: 0.861). The PD map exhibited good performance in differentiating epidermal growth factor receptor (EGFR) expression levels (AUC: 0.706~0.732) and histological type (AUC: 0.650~0.660). T2_minimum was highest correlated with Epstein-Barr virus (EBV) DNA levels (r = - 0.419), and PD_75th percentile exhibited the highest performance in distinguishing positive and negative EBV DNA groups (AUC: 0.721). T1_minimum was statistically correlated with EA-IgA expression (r = - 0.313). Additionally, several histogram parameters were negatively correlated with tumor stage (T stage: r = - 0.259 ~ - 0.301; N stage: r = - 0.348 ~ - 0.456; clinical stage: r = - 0.419). CONCLUSIONS: Histogram parameters of SyMRI could reflect tissue intrinsic characteristics and showed potential value in assessing the Ki-67 and EGFR expression levels, histological type, EBV DNA level, EA-IgA, and tumor stage. KEY POINTS: • SyMRI combined with histogram analysis may help clinicians to assess different prognostic factor statuses in nasopharyngeal carcinoma. • The PD map exhibited good discriminating performance in the Ki-67 and EGFR expression levels. • Histogram parameters of SyMRI were negatively correlated with EBV-related blood biomarkers and TNM stage.

Pretreatment synthetic magnetic resonance imaging predicts disease progression in nonmetastatic nasopharyngeal carcinoma after intensity modulation radiation therapy.

BACKGROUND: To investigate the potential of synthetic MRI (SyMRI) in the prognostic assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC), and the predictive value when combined with diffusion-weighted imaging (DWI) as well as clinical factors. METHODS: Fifty-three NPC patients who underwent SyMRI were prospectively included. 10th Percentile, Mean, Kurtosis, and Skewness of T1, T2, and PD maps and ADC value were obtained from the primary tumor. Cox regression analysis was used for analyzing the association between SyMRI and DWI parameters and progression-free survival (PFS), and then age, sex, staging, and treatment as confounding factors were also included. C-index was obtained by bootstrap. Moreover, significant parameters were used to construct models in predicting 3-year disease progression. ROC curves and leave-one-out cross-validation were used to evaluate the performance and stability. RESULTS: Disease progression occurred in 16 (30.2%) patients at a follow-up of 39.6 (3.5, 48.2) months. T1_Kurtosis, T1_Skewness, T2_10th, PD_Mean, and ADC were correlated with PFS, and T1_Kurtosis (HR: 1.093) and ADC (HR: 1.009) were independent predictors of PFS. The C-index of SyMRI and SyMRI + DWI + Clinic models was 0.687 and 0.779. Moreover, the SyMRI + DWI + Clinic model predicted 3-year disease progression better than DWI or Clinic model (p ≤ 0.008). Interestingly, there was no significant difference between the SyMRI model (AUC: 0.748) and SyMRI + DWI + Clinic model (AUC: 0.846, p = 0.092). CONCLUSION: SyMRI combined with histogram analysis could predict disease progression in NPC patients, and SyMRI + DWI + Clinic model further improved the predictive performance.

Development and evaluation clinical-radiomics analysis based on T1-weighted imaging for diagnosing neonatal acute bilirubin encephalopathy.

Purpose: To investigate the value of clinical-radiomics analysis based on T1-weighted imaging (T1WI) for predicting acute bilirubin encephalopathy (ABE) in neonates. Methods: In this retrospective study, sixty-one neonates with clinically confirmed ABE and 50 healthy control neonates were recruited between October 2014 and March 2019. Two radiologists' visual diagnoses for all subjects were independently based on T1WI. Eleven clinical and 216 radiomics features were obtained and analyzed. Seventy percent of samples were randomly selected as the training group and were used to establish a clinical-radiomics model to predict ABE; the remaining samples were used to validate the performance of the models. The discrimination performance was assessed by receiver operating characteristic (ROC) curve analysis. Results: Seventy-eight neonates were selected for training (median age, 9 days; interquartile range, 7-20 days; 49 males) and 33 neonates for validation (median age, 10 days; interquartile range, 6-13 days; 24 males). Two clinical features and ten radiomics features were finally selected to construct the clinical-radiomics model. In the training group, the area under the ROC curve (AUC) was 0.90 (sensitivity: 0.814; specificity: 0.914); in the validation group, the AUC was 0.93 (sensitivity: 0.944; specificity: 0.800). The AUCs of two radiologists' and the radiologists' final visual diagnosis results based on T1WI were 0.57, 0.63, and 0.66, respectively. The discriminative performance of the clinical-radiomics model in the training and validation groups was increased compared to the radiologists' visual diagnosis (P < 0.001). Conclusions: A combined clinical-radiomics model based on T1WI has the potential to predict ABE. The application of the nomogram could potentially provide a visualized and precise clinical support tool.

Sub-differentiation of PI-RADS 3 lesions in TZ by advanced diffusion-weighted imaging to aid the biopsy decision process.

Background: Performing biopsy for intermediate lesions with PI-RADS 3 has always been controversial. Moreover, it is difficult to differentiate prostate cancer (PCa) and benign prostatic hyperplasia (BPH) nodules in PI-RADS 3 lesions by conventional scans, especially for transition zone (TZ) lesions. The purpose of this study is sub-differentiation of transition zone (TZ) PI-RADS 3 lesions using intravoxel incoherent motion (IVIM), stretched exponential model, and diffusion kurtosis imaging (DKI) to aid the biopsy decision process. Methods: A total of 198 TZ PI-RADS 3 lesions were included. 149 lesions were BPH, while 49 lesions were PCa, including 37 non-clinical significant PCa (non-csPCa) lesions and 12 clinical significant PCa (csPCa) lesions. Binary logistic regression analysis was used to examine which parameters could predict PCa in TZ PI-RADS 3 lesions. The ROC curve was used to test diagnostic efficiency in distinguishing PCa from TZ PI-RADS 3 lesions, while one-way ANOVA analysis was used to examine which parameters were statistically significant among BPH, non-csPCa and csPCa. Results: The logistic model was statistically significant (χ2 = 181.410, p<0.001) and could correctly classify 89.39% of the subjects. Parameters of fractional anisotropy (FA) (p=0.004), mean diffusion (MD) (p=0.005), mean kurtosis (MK) (p=0.015), diffusion coefficient (D) (p=0.001), and distribute diffusion coefficient (DDC) (p=0.038) were statistically significant in the model. ROC analysis showed that AUC was 0.9197 (CI 95%: 0.8736-0.9659). Sensitivity, specificity, positive predictive value and negative predictive value were 92.1%, 80.4%, 93.9% and 75.5%, respectively. FA and MK of csPCa were higher than those of non-csPCa (all p<0.05), while MD, ADC, D, and DDC of csPCa were lower than those of non-csPCa (all p<0.05). Conclusion: FA, MD, MK, D, and DDC can predict PCa in TZ PI-RADS 3 lesions and inform the decision-making process of whether or not to perform a biopsy. Moreover, FA, MD, MK, D, DDC, and ADC may have ability to identify csPCa and non-csPCa in TZ PI-RADS 3 lesions.

Histogram analysis of synthetic magnetic resonance imaging: Correlations with histopathological factors in head and neck squamous cell carcinoma.

PURPOSE: To analyse the association between histogram parameters derived from synthetic MRI (SyMRI) and different histopathological factors in head and neck squamous cell carcinoma (HNSCC). METHOD: Sixty-one patients with histologically proven primary HNSCC were prospectively enrolled. The correlations between histogram parameters of SyMRI (T1, T2 and proton density (PD) maps) and histopathological factors were analysed using Spearman analysis. The Mann-Whitney U test or Student's t test was utilized to differentiate histological grades and human papillomavirus (HPV) status. The ROC curves and leave-one-out cross-validation (LOOCV) were used to evaluate the differentiation performance. Bootstrapping was applied to avoid overfitting. RESULTS: Several histogram parameters were associated with histological grade: T1 map (r = 0.291) and PD map (r = 0.294 - 0.382/-0.343), and PD_75th Percentile showed the highest differentiation performance (AUC: 0.721 (ROC) and 0.719 (LOOCV)). Moderately negative correlations were found between p16 status and the histogram parameters: T1 map (r = -0.587 - -0.390), T2 map (r = -0.649 - -0.357) and PD map (r = -0.537 - -0.338). In differentiating HPV infection, Entropy was the most discriminative parameter in each map and T2_Entropy showed the highest diagnostic performance (AUC: 0.851 [ROC] and 0.851 [LOOCV]). Additionally, several histogram parameters were correlated with Ki-67 (r = -0.379/-0.397), epidermal growth factor receptor (EGFR) (r = 0.318/0.322) status and p53 (r = 0.452 - 0.665/-0.607) status. CONCLUSIONS: Histogram parameters derived from SyMRI may serve as a potential biomarker for discriminating relevant histopathological features, including histological differentiation grade, HPV infection, Ki-67, EGFR and p53 statuses.

The utility of texture analysis based on quantitative synthetic magnetic resonance imaging in nasopharyngeal carcinoma: a preliminary study.

BACKGROUND: Magnetic resonance imaging (MRI) is commonly used for the diagnosis of nasopharyngeal carcinoma (NPC) and occipital clivus (OC) invasion, but a proportion of lesions may be missed using non-enhanced MRI. The purpose of this study is to investigate the diagnostic performance of synthetic magnetic resonance imaging (SyMRI) in differentiating NPC from nasopharyngeal hyperplasia (NPH), as well as evaluating OC invasion. METHODS: Fifty-nine patients with NPC and 48 volunteers who underwent SyMRI examination were prospectively enrolled. Eighteen first-order features were extracted from VOIs (primary tumours, benign mucosa, and OC). Statistical comparisons were conducted between groups using the independent-samples t-test and the Mann-Whitney U test to select significant parameters. Multiple diagnostic models were then constructed using multivariate logistic analysis. The diagnostic performance of the models was calculated by receiver operating characteristics (ROC) curve analysis and compared using the DeLong test. Bootstrap and 5-folds cross-validation were applied to avoid overfitting. RESULTS: The T1, T2 and PD map-derived models had excellent diagnostic performance in the discrimination between NPC and NPH in volunteers, with area under the curves (AUCs) of 0.975, 0.972 and 0.986, respectively. Besides, SyMRI models also showed excellent performance in distinguishing OC invasion from non-invasion (AUC: 0.913-0.997). Notably, the T1 map-derived model showed the highest diagnostic performance with an AUC, sensitivity, specificity, and accuracy of 0.997, 96.9%, 97.9% and 97.5%, respectively. By using 5-folds cross-validation, the bias-corrected AUCs were 0.965-0.984 in discriminating NPC from NPH and 0.889-0.975 in discriminating OC invasion from OC non-invasion. CONCLUSIONS: SyMRI combined with first-order parameters showed excellent performance in differentiating NPC from NPH, as well as discriminating OC invasion from non-invasion.

Predicting pathological complete response of neoadjuvant radiotherapy and targeted therapy for soft tissue sarcoma by whole-tumor texture analysis of multisequence MRI imaging.

OBJECTIVES: To construct effective prediction models for neoadjuvant radiotherapy (RT) and targeted therapy based on whole-tumor texture analysis of multisequence MRI for soft tissue sarcoma (STS) patients. METHODS: Thirty patients with STS of the extremities or trunk from a prospective phase II trial were enrolled for this analysis. All patients underwent pre- and post-neoadjuvant RT MRI examinations from which whole-tumor texture features were extracted, including T1-weighted with fat saturation and contrast enhancement (T1FSGd), T2-weighted with fat saturation (T2FS), and diffusion-weighted imaging (DWI) sequences and their corresponding apparent diffusion coefficient (ADC) maps. According to the postoperative pathological results, the patients were divided into pathological complete response (pCR) and non-pCR (N-pCR) groups. pCR was defined as less than 5% of residual tumor cells by postoperative pathology. Delta features were defined as the percentage change in a texture feature from pre- to post-neoadjuvant RT MRI. After data reduction and feature selection, logistic regression was used to build prediction models. ROC analysis was performed to assess the diagnostic performance. RESULTS: Five of 30 patients (16.7%) achieved pCR. The Delta_Model (AUC 0.92) had a better predictive ability than the Pre_Model (AUC 0.78) and Post_Model (AUC 0.76) and was better than AJCC staging (AUC 0.52) and RECIST 1.1 criteria (AUC 0.52). The Combined_Model (pre, post, and delta features) had the best predictive performance (AUC 0.95). CONCLUSION: Whole-tumor texture analysis of multisequence MRI can well predict pCR status after neoadjuvant RT and targeted therapy in STS patients, with better performance than RECIST 1.1 and AJCC staging. KEY POINTS: • MRI multisequence texture analysis could predict the efficacy of neoadjuvant RT and targeted therapy for STS patients. • Texture features showed incremental value beyond routine clinical factors. • The Combined_Model with features at multiple time points showed the best performance.

MRI-based radiomics for pretreatment prediction of response to concurrent chemoradiotherapy in locally advanced cervical squamous cell cancer.

PURPOSE: To investigate the value of magnetic resonance imaging (MRI)-based radiomics in predicting the treatment response to concurrent chemoradiotherapy (CCRT) in patients with locally advanced cervical squamous cell cancer (LACSC). METHODS: In total, 198 patients (training: n = 138; testing: n = 60) with LACSC treated with CCRT between January 2014 and December 2019 were retrospectively enrolled in this study. Responses were evaluated by MRI and clinical data performed at one month after completion of CCRT according to RECIST standards, and patients were divided into the residual group and nonresidual group. Overall, 200 radiomics features were extracted from T2-weighted imaging and apparent diffusion coefficient maps. The radiomics score (Rad-score) was constructed with a feature selection strategy. Logistic regression analysis was used for multivariate analysis of radiomics features and clinical variables. The performance of all models was assessed using receiver operating characteristic curves. RESULTS: Among the clinical variables, tumor grade and FIGO stage were independent risk factors, and the areas under the curve (AUCs) of the clinical model were 0.741 and 0.749 in the training and testing groups. The Rad-score, consisting of 4 radiomics features selected from 200 radiomics features, showed good predictive performance with an AUC of 0.819 in the training group and 0.776 in the testing group, which were higher than the clinical model, but the difference was not statistically significant. The combined model constructed with tumor grade, FIGO stage, and Rad-score achieved the best performance, with an AUC of 0.857 in the training group and 0.842 in the testing group, which were significantly higher than the clinical model. CONCLUSION: MRI-based radiomics features could be used as a noninvasive biomarker to improve the ability to predict the treatment response to CCRT in patients with LACSC.

Cardiac magnetic resonance radiomics for disease classification.

OBJECTIVES: This study investigated the discriminability of quantitative radiomics features extracted from cardiac magnetic resonance (CMR) images for hypertrophic cardiomyopathy (HCM), dilated cardiomyopathy (DCM), and healthy (NOR) patients. METHODS: The data of two hundred and eighty-three patients with HCM (n = 48) or DCM (n = 52) and NOR (n = 123) were extracted from two publicly available datasets. Ten feature selection methods were first performed on twenty-one different sets of radiomics features extracted from the left ventricle, right ventricle, and myocardium segmented from CMR images in the end-diastolic frame, end-systolic frame, and a combination of both; then, nine classical machine learning methods were trained with the selected radiomics features to distinguish HCM, DCM, and NOR. Ninety classification models were constructed based on combinations of the ten feature selection methods and nine classifiers. The classification models were evaluated, and the optimal model was selected. The diagnostic performance of the selected model was also compared to that of state-of-the-art methods. RESULTS: The random forest minimum redundancy maximum relevance model with features based on LeastAxisLength, Maximum2DDiameterSlice, Median, MinorAxisLength, Sphericity, VoxelVolume, Kurtosis, Flatness, and Skewness was the highest performing model, achieving 91.2% classification accuracy. The cross-validated areas under the curve on the test dataset were 0.938, 0.966, and 0.936 for NOR, DCM, and HCM, respectively. Furthermore, compared with those of the state-of-the-art methods, the sensitivity and accuracy of this model were greatly improved. CONCLUSIONS: A predictive model was proposed based on CMR radiomics features for classifying HCM, DCM, and NOR patients. The model had good discriminability. KEY POINTS: • The first-order features and the features extracted from the LOG-filtered images have potential in distinguishing HCM patients from DCM patients. • The features extracted from the RV play little role in distinguishing DCM from HCM. • The VoxelVolume of the myocardium in the ED frame is important in the recognition of DCM.

Association Between Perivascular Adipose Tissue Density and Atherosclerosis in the Descending Thoracic Aorta.

Radiodensity measured by computed tomography (CT) in Hounsfield Units (HU) is emerging as a clinical tool for detecting perivascular adipose tissue (PVAT) inflammation. In the present study, we hypothesized that PVAT radiodensity might predict the risk of descending thoracic aorta atherosclerosis. A total of 73 subjects who underwent CT angiography to investigate aortic disease were retrospectively analyzed. PVAT radiodensity, aortic complex plaque (ACP), mean plaque-burden score (MPBS), and plaque density were measured, and the association between them was analyzed. Perivascular adipose tissue radiodensity (HU) in patients with different aortic plaques grades (grade 1, 2, 3, and 4) were -93.71 ± 2.50, -93.63 ± 3.93, -90.24 ± 4.49, and -89.90 ± 5.18, respectively, and the difference was significant (P = .010). In the regression analysis, PVAT radiodensity was an independent predictor of ACP, with an OR of 1.263. In the linear analysis, PVAT radiodensity was an independent predictor of MPBS, with a ß-coefficient of .073. In the univariate analysis, only the PVAT radiodensity was significantly associated with plaque density, with a ß-coefficient of -1.666. In conclusion, PVAT density was independently related to descending thoracic aorta atherosclerosis.