Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling.

OBJECTIVES: To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling. METHODS: A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10-3 mm2/s were obtained and compared by the McNemar test. RESULTS: The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883-0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015). CONCLUSION: Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models. KEY POINTS: • When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4-9.7%, at the price of slightly degraded sensitivity by 1.5-1.8%, and overall had improved accuracy by 2.6-2.9%. • When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC. • When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

Radiomics based on fluoro-deoxyglucose positron emission tomography predicts liver fibrosis in biopsy-proven MAFLD: a pilot study.

Rationale: Since non-invasive tests for prediction of liver fibrosis have a poor diagnostic performance for detecting low levels of fibrosis, it is important to explore the diagnostic capabilities of other non-invasive tests to diagnose low levels of fibrosis. We aimed to evaluate the performance of radiomics based on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) in predicting any liver fibrosis in individuals with biopsy-proven metabolic dysfunction-associated fatty liver disease (MAFLD). Methods: A total of 22 adults with biopsy-confirmed MAFLD, who underwent 18F-FDG PET/CT, were enrolled in this study. Sixty radiomics features were extracted from whole liver region of interest in 18F-FDG PET images. Subsequently, the minimum redundancy maximum relevance (mRMR) method was performed and a subset of two features mostly related to the output classes and low redundancy between them were selected according to an event per variable of 5. Logistic regression, Support Vector Machine, Naive Bayes, 5-Nearest Neighbor and linear discriminant analysis models were built based on selected features. The predictive performances were assessed by the receiver operator characteristic (ROC) curve analysis. Results: The mean (SD) age of the subjects was 38.5 (10.4) years and 17 subjects were men. 12 subjects had histological evidence of any liver fibrosis. The coarseness of neighborhood grey-level difference matrix (NGLDM) and long-run emphasis (LRE) of grey-level run length matrix (GLRLM) were selected to predict fibrosis. The logistic regression model performed best with an AUROC of 0.817 [95% confidence intervals, 0.595-0.947] for prediction of liver fibrosis. Conclusion: These preliminary data suggest that 18F-FDG PET radiomics may have clinical utility in assessing early liver fibrosis in MAFLD.

Initial experience of generalized intravoxel incoherent motion imaging and diffusion tensor imaging (GIVIM-DTI) in healthy subjects.

PURPOSE: To evaluate the feasibility of combined generalized intravoxel incoherent imaging and diffusion tensor imaging (GIVIM-DTI) to access the renal microstructure and microcirculation with respiratory triggering. MATERIALS AND METHODS: A total of 28 young healthy volunteers with no history of renal disease were recruited into our study. GIVIM-DTI images were acquired with respiratory triggering at 3 Tesla. The following diffusion and pseudodiffusion parameters were obtained: pure tissue diffusion ( Ds), fractional anisotropy (FA), mean diffusivity (MD), mean pseudodiffusion ( D¯), perfusion volume fraction ( fp), dispersion of pseudodiffusion ( σ), and an estimate of the microcirculation flow velocity ( fp⋅D¯). The renal left-right difference was analyzed using a paired t-test. The corticomedullary difference was assessed using the one-way analysis of variance test. The reliability of individual parameters was evaluated with the coefficient of variation (CV). RESULTS: Among all parameters, only the cortical fp showed a bilateral difference (P = 0.045). The cortical fp and σ were significantly higher (P < 0.001 for both) than those in the medulla, but D¯ was significantly lower (P < 0.001) in the cortex, and the fp⋅D¯ values showed no significant corticomedullary difference (P = 0.068). The diffusion parameters Ds and MD were significantly higher (P < 0.001 for both) in the cortex than in the medulla. The cortical FA was significantly lower (P < 0.001) than the corresponding medullary value. Good consistency (CV < 20%) was obtained in the values of Ds, FA, and MD, moderate consistency (CV < 50%) in fp, and poor consistency (CV > 50%) was found in D¯, σ and fp⋅D¯. CONCLUSION: GIVIM-DTI shows promise for advancing the characterization of the renal microstructure and microcirculation. J. Magn. Reson. Imaging 2016;44:732-738.

Evaluation of Association Between Menstrual Cycle Timing and Quantitative Background Parenchymal Enhancement on Breast MRI in Premenopausal Women.

OBJECTIVES: To evaluate the influence of menstrual cycle timing on quantitative background parenchymal enhancement and to assess an optimal timing of breast MRI in premenopausal women. METHODS: A total of 197 premenopausal women were enrolled, 120 of which were in the malignant group and 77 in the benign group. Two radiologists depicted the regions of interest (ROI) of the three consecutive biggest slices of glandular tissue in the unaffected side and calculated the ratio (=[SIpost - SIpre]/SIpre) in ROI from the precontrast and early phase to assess BPE quantitatively. Association of BPE with menstrual cycle timing was compared in three categories. The relationships between BPE and age /body mass index (BMI) were also explored. RESULTS: We found that the BPE ratio presented lower in patients with the follicular phase (day1-14) compared to the luteal phase (day15-30) in the benign group (P = .036). Also, the BPE ratio presented significantly lower in the proliferative phase (day5-14) than the menstrual phase (day1-4) and the secretory phase(day15-30) in the benign group (P = .006). While the BPE ratio was not significantly different among the respective weeks (1-4) of the menstrual cycle in the benign group (P > .05). In the malignant group, the BPE ratio did not significantly differ between/among any menstrual cycle phase or week (all P > .05). CONCLUSION: It seems more suitable for Asian women whose lesions need to follow up or are suspected of malignant to undergo breast MRI within the 1st to 14th day of the menstrual cycle, especially on the 5th to 14th day.

Magnetic Resonance Imaging Features Associated with a High and Low Expression of Tumor-Infiltrating Lymphocytes: A Stratified Analysis According to Molecular Subtypes.

A total of 457 patients, including 241 HR+/HER2- patients, 134 HER2+ patients, and 82 TN patients, were studied. The percentage of TILs in the stroma adjacent to the tumor cells was assessed using a 10% cutoff. The low TIL percentages were 82% in the HR+ patients, 63% in the HER2+ patients, and 56% in the TN patients (p < 0.001). MRI features such as morphology as mass or non-mass enhancement (NME), shape, margin, internal enhancement, presence of peritumoral edema, and the DCE kinetic pattern were assessed. Tumor sizes were smaller in the HR+/HER2- group (p < 0.001); HER2+ was more likely to present as NME (p = 0.031); homogeneous enhancement was mostly seen in HR+ (p < 0.001); and the peritumoral edema was present in 45% HR+, 71% HER2+, and 80% TN (p < 0.001). In each subtype, the MR features between the high- vs. low-TIL groups were compared. In HR+/HER2-, peritumoral edema was more likely to be present in those with high TILs (70%) than in those with low TILs (40%, p < 0.001). In TN, those with high TILs were more likely to present a regular shape (33%) than those with low TILs (13%, p = 0.029) and more likely to present the circumscribed margin (19%) than those with low TILs (2%, p = 0.009).

Multi-modality radiomics nomogram based on DCE-MRI and ultrasound images for benign and malignant breast lesion classification.

Objective: To develop a multi-modality radiomics nomogram based on DCE-MRI, B-mode ultrasound (BMUS) and strain elastography (SE) images for classifying benign and malignant breast lesions. Material and Methods: In this retrospective study, 345 breast lesions from 305 patients who underwent DCE-MRI, BMUS and SE examinations were randomly divided into training (n = 241) and testing (n = 104) datasets. Radiomics features were extracted from manually contoured images. The inter-class correlation coefficient (ICC), Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection and radiomics signature building. Multivariable logistic regression was used to develop a radiomics nomogram incorporating radiomics signature and clinical factors. The performance of the radiomics nomogram was evaluated by its discrimination, calibration, and clinical usefulness and was compared with BI-RADS classification evaluated by a senior breast radiologist. Results: The All-Combination radiomics signature derived from the combination of DCE-MRI, BMUS and SE images showed better diagnostic performance than signatures derived from single modality alone, with area under the curves (AUCs) of 0.953 and 0.941 in training and testing datasets, respectively. The multi-modality radiomics nomogram incorporating the All-Combination radiomics signature and age showed excellent discrimination with the highest AUCs of 0.964 and 0.951 in two datasets, respectively, which outperformed all single modality radiomics signatures and BI-RADS classification. Furthermore, the specificity of radiomics nomogram was significantly higher than BI-RADS classification (both p < 0.04) with the same sensitivity in both datasets. Conclusion: The proposed multi-modality radiomics nomogram based on DCE-MRI and ultrasound images has the potential to serve as a non-invasive tool for classifying benign and malignant breast lesions and reduce unnecessary biopsy.

Radiomics Model for Evaluating the Level of Tumor-Infiltrating Lymphocytes in Breast Cancer Based on Dynamic Contrast-Enhanced MRI.

BACKGROUND: To help identify potential breast cancer (BC) candidates for immunotherapies, we aimed to develop and validate a radiology-based biomarker (radiomic score) to predict the level of tumor-infiltrating lymphocytes (TILs) in patients with BC. PATIENTS AND METHODS: This retrospective study enrolled 172 patients with histopathology-confirmed BC assigned to the training (n = 121) or testing (n = 51) cohorts. Radiomic features were extracted and selected using Analysis-Kit software. The correlation between TIL levels and clinical features and radiomic features was evaluated. The clinical features model, radiomic signature model, and combined prediction model were constructed and compared. Predictive performance was assessed by receiver operating characteristic analysis and clinical utility by implementing a nomogram. RESULTS: Seven radiomic features were selected as the best discriminators to construct the radiomic signature model, the performance of which was good in both the training and validation data sets, with an area under the curve (AUC) of 0.742 (95% confidence interval [CI], 0.642-0.843) and 0.718 (95% CI, 0.558-0.878), respectively. Estrogen receptor status and tumor diameter were confirmed to be significant features for building the clinical feature model, which had an AUC of 0.739 (95% CI, 0.632-0.846) and 0.824 (95% CI, 0.692-0.957), respectively. The combined prediction model had an AUC of 0.800 (95% CI, 0.709-0.892) and 0.842 (95% CI, 0.730-0.954), respectively. CONCLUSION: The radiomic signature could be an important predictor of the TIL level in BC, which, when validated, could be useful in identifying BC patients who can benefit from immunotherapies. The nomogram may help clinicians make decisions.

Diagnosis of Breast Cancer Using Radiomics Models Built Based on Dynamic Contrast Enhanced MRI Combined With Mammography.

OBJECTIVE: To build radiomics models using features extracted from DCE-MRI and mammography for diagnosis of breast cancer. MATERIALS AND METHODS: 266 patients receiving MRI and mammography, who had well-enhanced lesions on MRI and histologically confirmed diagnosis were analyzed. Training dataset had 146 malignant and 56 benign, and testing dataset had 48 malignant and 18 benign lesions. Fuzzy-C-means clustering algorithm was used to segment the enhanced lesion on subtraction MRI maps. Two radiologists manually outlined the corresponding lesion on mammography by consensus, with the guidance of MRI maximum intensity projection. Features were extracted using PyRadiomics from three DCE-MRI parametric maps, and from the lesion and a 2-cm bandshell margin on mammography. The support vector machine (SVM) was applied for feature selection and model building, using 5 datasets: DCE-MRI, mammography lesion-ROI, mammography margin-ROI, mammography lesion+margin, and all combined. RESULTS: In the training dataset evaluated using 10-fold cross-validation, the diagnostic accuracy of the individual model was 83.2% for DCE-MRI, 75.7% for mammography lesion, 64.4% for mammography margin, and 77.2% for lesion+margin. When all features were combined, the accuracy was improved to 89.6%. By adding mammography features to MRI, the specificity was significantly improved from 69.6% (39/56) to 82.1% (46/56), p<0.01. When the developed models were applied to the independent testing dataset, the accuracy was 78.8% for DCE-MRI and 83.3% for combined MRI+Mammography. CONCLUSION: The radiomics model built from the combined MRI and mammography has the potential to provide a machine learning-based diagnostic tool and decrease the false positive diagnosis of contrast-enhanced benign lesions on MRI.

BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning.

BACKGROUND: A wide variety of benign and malignant processes can manifest as non-mass enhancement (NME) in breast MRI. Compared to mass lesions, there are no distinct features that can be used for differential diagnosis. The purpose is to use the BI-RADS descriptors and models developed using radiomics and deep learning to distinguish benign from malignant NME lesions. MATERIALS AND METHODS: A total of 150 patients with 104 malignant and 46 benign NME were analyzed. Three radiologists performed reading for morphological distribution and internal enhancement using the 5th BI-RADS lexicon. For each case, the 3D tumor mask was generated using Fuzzy-C-Means segmentation. Three DCE parametric maps related to wash-in, maximum, and wash-out were generated, and PyRadiomics was applied to extract features. The radiomics model was built using five machine learning algorithms. ResNet50 was implemented using three parametric maps as input. Approximately 70% of earlier cases were used for training, and 30% of later cases were held out for testing. RESULTS: The diagnostic BI-RADS in the original MRI report showed that 104/104 malignant and 36/46 benign lesions had a BI-RADS score of 4A-5. For category reading, the kappa coefficient was 0.83 for morphological distribution (excellent) and 0.52 for internal enhancement (moderate). Segmental and Regional distribution were the most prominent for the malignant group, and focal distribution for the benign group. Eight radiomics features were selected by support vector machine (SVM). Among the five machine learning algorithms, SVM yielded the highest accuracy of 80.4% in training and 77.5% in testing datasets. ResNet50 had a better diagnostic performance, 91.5% in training and 83.3% in testing datasets. CONCLUSION: Diagnosis of NME was challenging, and the BI-RADS scores and descriptors showed a substantial overlap. Radiomics and deep learning may provide a useful CAD tool to aid in diagnosis.

The performance of intravoxel-incoherent motion diffusion-weighted imaging derived hypoxia for the risk stratification of prostate cancer in peripheral zone.

PURPOSE: To assess the association between intravoxel-incoherent motion diffusion-weighted imaging (IVIM) derived hypoxia and the aggressiveness of prostate cancer (PCa) and to explore its contribution to the risk stratification of PCa. METHODS: Seventy-five peripheral zone (PZ) PCa patients, who underwent multiparametric MRI (mpMRI), were included in this study. Systematic ultrasound guided biopsy was used as reference. IVIM was acquired with 5 b values (b = 0∼750 s/mm2). Apparent diffusion coefficient (ADC), pure tissue diffusion (Ds), volume fraction of pseudo-diffusion (fp), hypoxic fraction (HFDWI), hypoxia score (HSDWI) and relative oxygen saturation(rOSDWI), were calculated and histogram analysis was applied. Groups comparison was performed between low-intermediate-grade group (LG, the International Society of Urological Pathology (ISUP) Gleason Grade (GG) ≤2) and high-grade (HG, ISUP GG ≥ 3) group. The correlation between diffusion parameters and ISUP GG was assessed. Cross-validated Support Vector Machine (SVM) Classification was performed and compared with univariate ROC analysis to explore the risk stratification of PZ PCa. RESULTS: Mean, median, and the 10th percentile of Ds differed significantly between groups (p < 0.05). Several parameters significantly correlated with ISUP grade, and the 10th percentile of Ds showed the strongest correlation (ρ= - 0.284). The prediction model containing IVIM derived hypoxia yielded an area under the receiver operating characteristics curve (AUC) ranging 0.749-0.786 for cross-validation. The AUCs of the SVM modeling were higher than that of any single parameter. CONCLUSION: IVIM derived hypoxia demonstrated significant correlation with the aggressiveness of PCa. It's supplemental to the MRI assessment of PCa with a promising stratification of risk stratification of PZ PCa.