Prospective Evaluation of Repeatability and Robustness of Radiomic Descriptors in Healthy Brain Tissue Regions In Vivo Across Systematic Variations in T2-Weighted Magnetic Resonance Imaging Acquisition Parameters.

BACKGROUND: Radiomic descriptors from magnetic resonance imaging (MRI) are promising for disease diagnosis and characterization but may be sensitive to differences in imaging parameters. OBJECTIVE: To evaluate the repeatability and robustness of radiomic descriptors within healthy brain tissue regions on prospectively acquired MRI scans; in a test-retest setting, under controlled systematic variations of MRI acquisition parameters, and after postprocessing. STUDY TYPE: Prospective. SUBJECTS: Fifteen healthy participants. FIELD STRENGTH/SEQUENCE: A 3.0 T, axial T2 -weighted 2D turbo spin-echo pulse sequence, 181 scans acquired (2 test/retest reference scans and 12 with systematic variations in contrast weighting, resolution, and acceleration per participant; removing scans with artifacts). ASSESSMENT: One hundred and forty-six radiomic descriptors were extracted from a contiguous 2D region of white matter in each scan, before and after postprocessing. STATISTICAL TESTS: Repeatability was assessed in a test/retest setting and between manual and automated annotations for the reference scan. Robustness was evaluated between the reference scan and each group of variant scans (contrast weighting, resolution, and acceleration). Both repeatability and robustness were quantified as the proportion of radiomic descriptors that fell into distinct ranges of the concordance correlation coefficient (CCC): excellent (CCC > 0.85), good (0.7 ≤ CCC ≤ 0.85), moderate (0.5 ≤ CCC < 0.7), and poor (CCC < 0.5); for unprocessed and postprocessed scans separately. RESULTS: Good to excellent repeatability was observed for 52% of radiomic descriptors between test/retest scans and 48% of descriptors between automated vs. manual annotations, respectively. Contrast weighting (TR/TE) changes were associated with the largest proportion of highly robust radiomic descriptors (21%, after processing). Image resolution changes resulted in the largest proportion of poorly robust radiomic descriptors (97%, before postprocessing). Postprocessing of images with only resolution/acceleration differences resulted in 73% of radiomic descriptors showing poor robustness. DATA CONCLUSIONS: Many radiomic descriptors appear to be nonrobust across variations in MR contrast weighting, resolution, and acceleration, as well in test-retest settings, depending on feature formulation and postprocessing. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Radiomic Features of Primary Rectal Cancers on Baseline T2 -Weighted MRI Are Associated With Pathologic Complete Response to Neoadjuvant Chemoradiation: A Multisite Study.

BACKGROUND: Twenty-five percent of rectal adenocarcinoma patients achieve pathologic complete response (pCR) to neoadjuvant chemoradiation and could avoid proctectomy. However, pretreatment clinical or imaging markers are lacking in predicting response to chemoradiation. Radiomic texture features from MRI have recently been associated with therapeutic response in other cancers. PURPOSE: To construct a radiomics texture model based on pretreatment MRI for identifying patients who will achieve pCR to neoadjuvant chemoradiation in rectal cancer, including validation across multiple scanners and sites. STUDY TYPE: Retrospective. SUBJECTS: In all, 104 rectal cancer patients staged with MRI prior to long-course chemoradiation followed by proctectomy; curated from three institutions. FIELD STRENGTH/SEQUENCE: 1.5T-3.0T, axial higher resolution T2 -weighted turbo spin echo sequence. ASSESSMENT: Pathologic response was graded on postsurgical specimens. In total, 764 radiomic features were extracted from single-slice sections of rectal tumors on processed pretreatment T2 -weighted MRI. STATISTICAL TESTS: Three feature selection schemes were compared for identifying radiomic texture descriptors associated with pCR via a discovery cohort (one site, N = 60, cross-validation). The top-selected radiomic texture features were used to train and validate a random forest classifier model for pretreatment identification of pCR (two external sites, N = 44). Model performance was evaluated via area under the curve (AUC), accuracy, sensitivity, and specificity. RESULTS: Laws kernel responses and gradient organization features were most associated with pCR (P ≤ 0.01); as well as being commonly identified across all feature selection schemes. The radiomics model yielded a discovery AUC of 0.699 ± 0.076 and a hold-out validation AUC of 0.712 with 70.5% accuracy (70.0% sensitivity, 70.6% specificity) in identifying pCR. Radiomic texture features were resilient to variations in magnetic field strength as well as being consistent between two different expert annotations. Univariate analysis revealed no significant associations of baseline clinicopathologic or MRI findings with pCR (P = 0.07-0.96). DATA CONCLUSION: Radiomic texture features from pretreatment MRIs may enable early identification of potential pCR to neoadjuvant chemoradiation, as well as generalize across sites. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Comparing radiomic classifiers and classifier ensembles for detection of peripheral zone prostate tumors on T2-weighted MRI: a multi-site study.

BACKGROUND: For most computer-aided diagnosis (CAD) problems involving prostate cancer detection via medical imaging data, the choice of classifier has been largely ad hoc, or been motivated by classifier comparison studies that have involved large synthetic datasets. More significantly, it is currently unknown how classifier choices and trends generalize across multiple institutions, due to heterogeneous acquisition and intensity characteristics (especially when considering MR imaging data). In this work, we empirically evaluate and compare a number of different classifiers and classifier ensembles in a multi-site setting, for voxel-wise detection of prostate cancer (PCa) using radiomic texture features derived from high-resolution in vivo T2-weighted (T2w) MRI. METHODS: Twelve different supervised classifier schemes: Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVMs), naïve Bayes, Decision Trees (DTs), and their ensemble variants (bagging, boosting), were compared in terms of classification accuracy as well as execution time. Our study utilized 85 prostate cancer T2w MRI datasets acquired from across 3 different institutions (1 for discovery, 2 for independent validation), from patients who later underwent radical prostatectomy. Surrogate ground truth for disease extent on MRI was established by expert annotation of pre-operative MRI through spatial correlation with corresponding ex vivo whole-mount histology sections. Classifier accuracy in detecting PCa extent on MRI on a per-voxel basis was evaluated via area under the ROC curve. RESULTS: The boosted DT classifier yielded the highest cross-validated AUC (= 0.744) for detecting PCa in the discovery cohort. However, in independent validation, the boosted QDA classifier was identified as the most accurate and robust for voxel-wise detection of PCa extent (AUCs of 0.735, 0.683, 0.768 across the 3 sites). The next most accurate and robust classifier was the single QDA classifier, which also enjoyed the advantage of significantly lower computation times compared to any of the other methods. CONCLUSIONS: Our results therefore suggest that simpler classifiers (such as QDA and its ensemble variants) may be more robust, accurate, and efficient for prostate cancer CAD problems, especially in the context of multi-site validation.

Dimensionality reduction-based fusion approaches for imaging and non-imaging biomedical data: concepts, workflow, and use-cases.

BACKGROUND: With a wide array of multi-modal, multi-protocol, and multi-scale biomedical data being routinely acquired for disease characterization, there is a pressing need for quantitative tools to combine these varied channels of information. The goal of these integrated predictors is to combine these varied sources of information, while improving on the predictive ability of any individual modality. A number of application-specific data fusion methods have been previously proposed in the literature which have attempted to reconcile the differences in dimensionalities and length scales across different modalities. Our objective in this paper was to help identify metholodological choices that need to be made in order to build a data fusion technique, as it is not always clear which strategy is optimal for a particular problem. As a comprehensive review of all possible data fusion methods was outside the scope of this paper, we have focused on fusion approaches that employ dimensionality reduction (DR). METHODS: In this work, we quantitatively evaluate 4 non-overlapping existing instantiations of DR-based data fusion, within 3 different biomedical applications comprising over 100 studies. These instantiations utilized different knowledge representation and knowledge fusion methods, allowing us to examine the interplay of these modules in the context of data fusion. The use cases considered in this work involve the integration of (a) radiomics features from T2w MRI with peak area features from MR spectroscopy for identification of prostate cancer in vivo, (b) histomorphometric features (quantitative features extracted from histopathology) with protein mass spectrometry features for predicting 5 year biochemical recurrence in prostate cancer patients, and (c) volumetric measurements on T1w MRI with protein expression features to discriminate between patients with and without Alzheimers' Disease. RESULTS AND CONCLUSIONS: Our preliminary results in these specific use cases indicated that the use of kernel representations in conjunction with DR-based fusion may be most effective, as a weighted multi-kernel-based DR approach resulted in the highest area under the ROC curve of over 0.8. By contrast non-optimized DR-based representation and fusion methods yielded the worst predictive performance across all 3 applications. Our results suggest that when the individual modalities demonstrate relatively poor discriminability, many of the data fusion methods may not yield accurate, discriminatory representations either. In summary, to outperform the predictive ability of individual modalities, methodological choices for data fusion must explicitly account for the sparsity of and noise in the feature space.

Novel PCA-VIP scheme for ranking MRI protocols and identifying computer-extracted MRI measurements associated with central gland and peripheral zone prostate tumors.

PURPOSE: To identify computer-extracted features for central gland and peripheral zone prostate cancer localization on multiparametric magnetic resonance imaging (MRI). MATERIALS AND METHODS: Preoperative T2-weighted (T2w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) MRI were acquired from 23 men with confirmed prostate cancer. Following radical prostatectomy, the cancer extent was delineated by a pathologist on ex vivo histology and mapped to MRI by nonlinear registration of histology and corresponding MRI slices. In all, 244 computer-extracted features were extracted from MRI, and principal component analysis (PCA) was employed to reduce the data dimensionality so that a generalizable classifier could be constructed. A novel variable importance on projection (VIP) measure for PCA (PCA-VIP) was leveraged to identify computer-extracted MRI features that discriminate between cancer and normal prostate, and these features were used to construct classifiers for cancer localization. RESULTS: Classifiers using features selected by PCA-VIP yielded an area under the curve (AUC) of 0.79 and 0.85 for peripheral zone and central gland tumors, respectively. For tumor localization in the central gland, T2w, DCE, and DWI MRI features contributed 71.6%, 18.1%, and 10.2%, respectively; for peripheral zone tumors T2w, DCE, and DWI MRI contributed 29.6%, 21.7%, and 48.7%, respectively. CONCLUSION: PCA-VIP identified relatively stable subsets of MRI features that performed well in localizing prostate cancer on MRI.

Physics-Informed Discretization for Reproducible and Robust Radiomic Feature Extraction Using Quantitative MRI.

OBJECTIVE: Given the limited repeatability and reproducibility of radiomic features derived from weighted magnetic resonance imaging (MRI), there may be significant advantages to using radiomics in conjunction with quantitative MRI. This study introduces a novel physics-informed discretization (PID) method for reproducible radiomic feature extraction and evaluates its performance using quantitative MRI sequences including magnetic resonance fingerprinting (MRF) and apparent diffusion coefficient (ADC) mapping. MATERIALS AND METHODS: A multiscanner, scan-rescan dataset comprising whole-brain 3D quantitative (MRF T1, MRF T2, and ADC) and weighted MRI (T1w MPRAGE, T2w SPACE, and T2w FLAIR) from 5 healthy subjects was prospectively acquired. Subjects underwent 2 repeated acquisitions on 3 distinct 3 T scanners each, for a total of 6 scans per subject (30 total scans). First-order statistical (n = 23) and second-order texture (n = 74) radiomic features were extracted from 56 brain tissue regions of interest using the proposed PID method (for quantitative MRI) and conventional fixed bin number (FBN) discretization (for quantitative MRI and weighted MRI). Interscanner radiomic feature reproducibility was measured using the intraclass correlation coefficient (ICC), and the effect of image sequence (eg, MRF T1 vs T1w MPRAGE), as well as image discretization method (ie, PID vs FBN), on radiomic feature reproducibility was assessed using repeated measures analysis of variance. The robustness of PID and FBN discretization to segmentation error was evaluated by simulating segmentation differences in brainstem regions of interest. Radiomic features with ICCs greater than 0.75 following simulated segmentation were determined to be robust to segmentation. RESULTS: First-order features demonstrated higher reproducibility in quantitative MRI than weighted MRI sequences, with 30% (n = 7/23) features being more reproducible in MRF T1 and MRF T2 than weighted MRI. Gray level co-occurrence matrix (GLCM) texture features extracted from MRF T1 and MRF T2 were significantly more reproducible using PID compared with FBN discretization; for all quantitative MRI sequences, PID yielded the highest number of texture features with excellent reproducibility (ICC > 0.9). Comparing texture reproducibility of quantitative and weighted MRI, a greater proportion of MRF T1 (n = 225/370, 61%) and MRF T2 (n = 150/370, 41%) texture features had excellent reproducibility (ICC > 0.9) compared with T1w MPRAGE (n = 148/370, 40%), ADC (n = 115/370, 32%), T2w SPACE (n = 98/370, 27%), and FLAIR (n = 102/370, 28%). Physics-informed discretization was also more robust than FBN discretization to segmentation error, as 46% (n = 103/222, 46%) of texture features extracted from quantitative MRI using PID were robust to simulated 6 mm segmentation shift compared with 19% (n = 42/222, 19%) of weighted MRI texture features extracted using FBN discretization. CONCLUSIONS: The proposed PID method yields radiomic features extracted from quantitative MRI sequences that are more reproducible and robust than radiomic features extracted from weighted MRI using conventional (FBN) discretization approaches. Quantitative MRI sequences also demonstrated greater scan-rescan robustness and first-order feature reproducibility than weighted MRI.

Quantifying 18F-Fluorodeoxyglucose Uptake in Perianal Fistulas on PET/CT: A Retrospective Analysis.

RATIONALE AND OBJECTIVES: The use of 18F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG-PET/CT) in assessing inflammatory diseases has shown significant promise. Uptake patterns in perianal fistulas, which may be an incidental finding on PET/CT, have not been purposefully studied. Our aim was to compare FDG uptake of perianal fistulas to that of the liver and anal canal in patients who underwent PET/CT for hematologic/oncologic diagnosis or staging. MATERIALS AND METHODS: We retrospectively identified patients who underwent FDG-PET/CT imaging between January 2011 and May 2023, where the report described a perianal fistula or abscess. PET/CTs of patients included in the study were retrospectively analyzed to record the maximum standardized uptake value (SUVmax) of the fistula, abscess, anal canal, rectum, and liver. Fistula-to-liver and Fistula-to-anus SUVmax ratios were calculated. We statistically compared FDG activity among the fistula, liver, and anal canal. We also assessed FDG activity in patients with vs. without anorectal cancer, as well as across different St. James fistula grades. RESULTS: The study included 24 patients with identifiable fistulas. Fistula SUVmax (mean=10.8 ± 5.28) was significantly higher than both the liver (mean=3.09 ± 0.584, p < 0.0001) and the anal canal (mean=5.98 ± 2.63, p = 0.0005). Abscess fistula SUVmax was 15.8 ± 4.91. St. James grade 1 fistulas had significantly lower SUVmax compared to grades 2 and 4 (p = 0.0224 and p = 0.0295, respectively). No significant differences existed in SUVmax ratios between anorectal and non-anorectal cancer groups. CONCLUSION: Perianal fistulas have increased FDG avidity with fistula SUVmax values that are significantly higher than the anal canal.

Quantification of Visceral Fat at the L5 Vertebral Body Level in Patients with Crohn's Disease Using T2-Weighted MRI.

The umbilical or L3 vertebral body level is often used for body fat quantification using computed tomography. To explore the feasibility of using clinically acquired pelvic magnetic resonance imaging (MRI) for visceral fat measurement, we examined the correlation of visceral fat parameters at the umbilical and L5 vertebral body levels. We retrospectively analyzed T2-weighted half-Fourier acquisition single-shot turbo spin echo (HASTE) MR axial images from Crohn's disease patients who underwent MRI enterography of the abdomen and pelvis over a three-year period. We determined the area/volume of subcutaneous and visceral fat from the umbilical and L5 levels and calculated the visceral fat ratio (VFR = visceral fat/subcutaneous fat) and visceral fat index (VFI = visceral fat/total fat). Statistical analyses involved correlation analysis between both levels, inter-rater analysis between two investigators, and inter-platform analysis between two image-analysis platforms. Correlational analysis of 32 patients yielded significant associations for VFI (r = 0.85; p < 0.0001) and VFR (r = 0.74; p < 0.0001). Intraclass coefficients for VFI and VFR were 0.846 and 0.875 (good agreement) between investigators and 0.831 and 0.728 (good and moderate agreement) between platforms. Our study suggests that the L5 level on clinically acquired pelvic MRIs may serve as a reference point for visceral fat quantification.

Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors.

BACKGROUND: Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy. PURPOSE: Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL-based brain tumor segmentation accuracy toward developing more generalizable models for multi-institutional data. METHODS: We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non-ET on MRI; with performance quantified via a 5-fold cross-validated Dice coefficient. MRI scans were evaluated through the open-source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as "better" quality (BQ) or "worse" quality (WQ), via relative thresholding. Segmentation performance was re-evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts. RESULTS: For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal-to-noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models. CONCLUSIONS: Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet-based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.

Evaluating the Change in 18F-Fluorodeoxyglucose Uptake in Perianal Fistulas on PET/CT over Time: A Serial Retrospective Analysis.

RATIONALE AND OBJECTIVES: Perianal fistulas on18F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG-PET/CT) can be an incidental site of FDG uptake in patients undergoing PET for other indications. There are no longitudinal studies describing FDG uptake patterns in perianal fistulas. Therefore, we aimed to analyze changes in FDG uptake over time in patients with incidental perianal fistulas. PATIENTS AND METHODS: Patients who underwent at least two FDG-PET/CTs between January 2011 and May 2023, with incidental perianal fistula, were retrospectively identified. We analyzed all sequential PET/CTs to determine the presence of a perianal fistula and recorded the fistula's maximum standardized uptake value (SUVmax). Statistical analysis compared fistula FDG-avidity in the initial versus final PET/CT examinations and assessed the correlation between initial fistula SUVmax and percent change over time. RESULTS: The study included 15 fistulas in 14 patients, with an average of 5 PET/CT examinations per patient. The average interval between the first and last PET/CT was 24 months (range: 6-64). The average initial fistula SUVmax (11.28 ± 3.81) was significantly higher than the final fistula SUVmax (7.22 ± 3.99) (p = 0.0067). The fistula SUVmax declined by an average of 32.01 ± 35.33% with no significant correlation between initial fistula SUVmax and percent change over time (r = -0.213, p = 0.443, 95% CI -0.66-0.35). CONCLUSION: FDG uptake in perianal fistulas shows temporal fluctuations but follows a decreasing SUVmax trend, possibly indicating a relationship with inflammatory activity. Further studies with larger cohorts paired with perianal fistula pelvic MR imaging are needed to validate these observations and their utility in guiding further management.

CohortFinder: an open-source tool for data-driven partitioning of digital pathology and imaging cohorts to yield robust machine-learning models.

Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder (http://cohortfinder.com), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream digital pathology and medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.

Radiomics to Detect Inflammation and Fibrosis on Magnetic Resonance Enterography in Stricturing Crohn's Disease.

BACKGROUND & AIMS: Non-invasive cross-sectional imaging via magnetic resonance enterography (MRE) offers excellent accuracy for the diagnosis of stricturing complications in Crohn's disease (CD) but is limited in determining the degrees of fibrosis and inflammation within a stricture. We developed and validated a radiomics-based machine-learning model for separately characterizing the degree of histopathologic inflammation and fibrosis in CD strictures and compared it to centrally read visual radiologist scoring of MRE. METHODS: This single center, cross-sectional study, included 51 CD patients (n=34 for discovery; n=17 for validation) with terminal ileal strictures confirmed on diagnostic MRE within 15 weeks of resection. Histopathological specimens were scored for inflammation and fibrosis and spatially linked with corresponding pre-surgical MRE sequences. Annotated stricture regions on MRE were scored visually by radiologists as well as underwent 3D radiomics-based machine learning analysis; both evaluated against histopathology. RESULTS: Two distinct sets of radiomic features capturing textural heterogeneity within strictures were linked with each of severe inflammation or severe fibrosis across both discovery (area under the curve (AUC)=0.69, 0.83) and validation (AUCs=0.67,0.78) cohorts. Radiologist visual scoring had an AUC=0.67 for identifying severe inflammation and AUC=0.35 for severe fibrosis. Use of combined radiomics and radiologist scoring robustly augmented identification of severe inflammation (AUC=0.79) and modestly improved assessment of severe fibrosis (AUC=0.79 for severe fibrosis) over individual approaches. CONCLUSIONS: Radiomic features of CD strictures on MRE can accurately identify severe histopathologic inflammation and severe histopathologic fibrosis, as well as augment performance of radiologist visual scoring in stricture characterization.

Geldof Expert Consensus Classification of Perianal Fistulizing Crohn's Disease: A Real-World Application in a Serial Fistula MRI Cohort.

Background and Aims: Perianal fistulizing Crohn's disease (CD-PAF) is an aggressive phenotype of Crohn's disease (CD) defined by frequent relapses and disabling symptoms. A novel consensus classification system was recently outlined by Geldof et al. that seeks to unify disease severity with patient-centered goals but has not yet been validated. We aimed to apply this to a real-world cohort and identify factors that predict transition between classes over time. Methods: We identified all patients with CD-PAF and at least one baseline and one follow-up pelvic (pMRI). Geldof Classification, disease characteristics, and imaging indices were collected retrospectively at time periods corresponding with respective MRIs. Results: We identified 100 patients with CD-PAF of which 96 were assigned Geldof Classes 1 - 2c at baseline. Most patients (78.1%) started in Class 2b, but changes in classification were observed in 52.1% of all patients. Male sex (72.0%, 46.6%, 40.0%, p = 0.03) and prior perianal surgery (52.0% vs 44.6% vs 40.0%, p = 0.02) were more frequently observed in those with improved. Baseline pMRI indices were not associated with changes in classification, however, greater improvements in mVAI, MODIFI-CD, and PEMPAC were seen among those who improved. Linear mixed effect modeling identified only male sex (-0.31, 95% CI -0.60 to -0.02) with improvement in class. Conclusion: Geldof classification highlights the dynamic nature of CD-PAF over time, however, our ability to predict transitions between classes remains limited and requires prospective assessment. Improvement in MRI index scores over time was associated with a transition to lower Geldof classification.

Characterization of renal masses with MRI-based radiomics: assessment of inter-package and inter-observer reproducibility in a prospective pilot study.

OBJECTIVES: To evaluate radiomics features' reproducibility using inter-package/inter-observer measurement analysis in renal masses (RMs) based on MRI and to employ machine learning (ML) models for RM characterization. METHODS: 32 Patients (23M/9F; age 61.8 ± 10.6 years) with RMs (25 renal cell carcinomas (RCC)/7 benign masses; mean size, 3.43 ± 1.73 cm) undergoing resection were prospectively recruited. All patients underwent 1.5 T MRI with T2-weighted (T2-WI), diffusion-weighted (DWI)/apparent diffusion coefficient (ADC), and pre-/post-contrast-enhanced T1-weighted imaging (T1-WI). RMs were manually segmented using volume of interest (VOI) on T2-WI, DWI/ADC, and T1-WI pre-/post-contrast imaging (1-min, 3-min post-injection) by two independent observers using two radiomics software packages for inter-package and inter-observer assessments of shape/histogram/texture features common to both packages (104 features; n = 26 patients). Intra-class correlation coefficients (ICCs) were calculated to assess inter-observer and inter-package reproducibility of radiomics measurements [good (ICC ≥ 0.8)/moderate (ICC = 0.5-0.8)/poor (ICC < 0.5)]. ML models were employed using reproducible features (between observers and packages, ICC > 0.8) to distinguish RCC from benign RM. RESULTS: Inter-package comparisons demonstrated that radiomics features from T1-WI-post-contrast had the highest proportion of good/moderate ICCs (54.8-58.6% for T1-WI-1 min), while most features extracted from T2-WI, T1-WI-pre-contrast, and ADC exhibited poor ICCs. Inter-observer comparisons found that radiomics measurements from T1-WI pre/post-contrast and T2-WI had the greatest proportion of features with good/moderate ICCs (95.3-99.1% T1-WI-post-contrast 1-min), while ADC measurements yielded mostly poor ICCs. ML models generated an AUC of 0.71 [95% confidence interval = 0.67-0.75] for diagnosis of RCC vs. benign RM. CONCLUSION: Radiomics features extracted from T1-WI-post-contrast demonstrated greater inter-package and inter-observer reproducibility compared to ADC, with fair accuracy for distinguishing RCC from benign RM. CLINICAL RELEVANCE: Knowledge of reproducibility of MRI radiomics features obtained on renal masses will aid in future study design and may enhance the diagnostic utility of radiomics models for renal mass characterization.

TOpCLASS Expert Consensus Classification of Perianal Fistulizing Crohn's Disease: A Real-World Application in a Serial Fistula MRI Cohort.

BACKGROUND AND AIMS: Perianal fistulizing Crohn's disease (PFCD) is an aggressive phenotype of Crohn's disease defined by frequent relapses and disabling symptoms. A novel consensus classification system was recently outlined by the TOpCLASS consortium that seeks to unify disease severity with patient-centered goals but has not yet been validated. We aimed to apply this to a real-world cohort and identify factors that predict transition between classes over time. METHODS: We identified all patients with PFCD and at least one baseline and one follow-up pelvic (pMRI). TOpCLASS classification, disease characteristics, and imaging indices were collected retrospectively at time periods corresponding with respective MRIs. RESULTS: We identified 100 patients with PFCD of which 96 were assigned TOpCLASS Classes 1 - 2c at baseline. Most patients (78.1%) started in Class 2b, but changes in classification were observed in 52.1% of all patients. Male sex (72.0%, 46.6%, 40.0%, p = 0.03) and prior perianal surgery (52.0% vs 44.6% vs 40.0%, p = 0.02) were more frequently observed in those with improved class. Baseline pMRI indices were not associated with changes in classification, however, greater improvements in mVAI, MODIFI-CD, and PEMPAC were seen among those who improved. Linear mixed effect modeling identified only male sex (-0.31, 95% CI -0.60 to -0.02) with improvement in class. CONCLUSION: The TOpCLASS classification highlights the dynamic nature of PFCD over time, however, our ability to predict transitions between classes remains limited and requires prospective assessment. Improvement in MRI index scores over time was associated with a transition to lower TOpCLASS classification.

Clonal Parabacteroides from Gut Microfistulous Tracts as Transmissible Cytotoxic Succinate-Commensal Model of Crohn's Disease Complications.

Crohn's disease (CD) has been traditionally viewed as a chronic inflammatory disease that cause gut wall thickening and complications, including fistulas, by mechanisms not understood. By focusing on Parabacteroides distasonis (presumed modern succinate-producing commensal probiotic), recovered from intestinal microfistulous tracts (cavernous fistulous micropathologies CavFT proposed as intermediate between 'mucosal fissures' and 'fistulas') in two patients that required surgery to remove CD-damaged ilea, we demonstrate that such isolates exert pathogenic/pathobiont roles in mouse models of CD. Our isolates are clonally-related; potentially emerging as transmissible in the community and mice; proinflammatory and adapted to the ileum of germ-free mice prone to CD-like ileitis (SAMP1/YitFc) but not healthy mice (C57BL/6J), and cytotoxic/ATP-depleting to HoxB8-immortalized bone marrow derived myeloid cells from SAMP1/YitFc mice when concurrently exposed to succinate and extracts from CavFT-derived E. coli , but not to cells from healthy mice. With unique genomic features supporting recent genetic exchange with Bacteroides fragilis -BGF539, evidence of international presence in primarily human metagenome databases, these CavFT Pdis isolates could represent to a new opportunistic Parabacteroides species, or subspecies (' cavitamuralis' ) adapted to microfistulous niches in CD.

Integrating Radiomics With Clinicoradiological Scoring Can Predict High-Risk Patients Who Need Surgery in Crohn's Disease: A Pilot Study.

BACKGROUND: Early identification of Crohn's disease (CD) patients at risk for complications could enable targeted surgical referral, but routine magnetic resonance enterography (MRE) has not been definitively correlated with need for surgery. Our objective was to identify computer-extracted image (radiomic) features from MRE associated with risk of surgery in CD and combine them with clinical and radiological assessments to predict time to intervention. METHODS: This was a retrospective single-center pilot study of CD patients who had an MRE within 3 months prior to initiating medical therapy. Radiomic features were extracted from annotated terminal ileum regions on MRE and combined with clinical variables and radiological assessment (via Simplified Magnetic Resonance Index of Activity scoring for wall thickening, edema, fat stranding, ulcers) in a random forest classifier. The primary endpoint was high- and low-risk groups based on need for surgery within 1 year of MRE. The secondary endpoint was time to surgery after treatment. RESULTS: Eight radiomic features capturing localized texture heterogeneity within the terminal ileum were significantly associated with risk of surgery within 1 year of treatment (P < .05); yielding a discovery cohort area under the receiver-operating characteristic curve of 0.67 (n = 50) and validation cohort area under the receiver-operating characteristic curve of 0.74 (n = 23). Kaplan-Meier analysis of radiomic features together with clinical variables and Simplified Magnetic Resonance Index of Activity scores yielded the best hazard ratio of 4.13 (P = (7.6 × 10-6) and concordance index of 0.71 in predicting time to surgery after MRE. CONCLUSIONS: Radiomic features on MRE may be associated with risk of surgery in CD, and in combination with clinicoradiological scoring can yield an accurate prognostic model for time to surgery.

Region-specific deep learning models for accurate segmentation of rectal structures on post-chemoradiation T2w MRI: a multi-institutional, multi-reader study.

Introduction: For locally advanced rectal cancers, in vivo radiological evaluation of tumor extent and regression after neoadjuvant therapy involves implicit visual identification of rectal structures on magnetic resonance imaging (MRI). Additionally, newer image-based, computational approaches (e.g., radiomics) require more detailed and precise annotations of regions such as the outer rectal wall, lumen, and perirectal fat. Manual annotations of these regions, however, are highly laborious and time-consuming as well as subject to inter-reader variability due to tissue boundaries being obscured by treatment-related changes (e.g., fibrosis, edema). Methods: This study presents the application of U-Net deep learning models that have been uniquely developed with region-specific context to automatically segment each of the outer rectal wall, lumen, and perirectal fat regions on post-treatment, T2-weighted MRI scans. Results: In multi-institutional evaluation, region-specific U-Nets (wall Dice = 0.920, lumen Dice = 0.895) were found to perform comparably to multiple readers (wall inter-reader Dice = 0.946, lumen inter-reader Dice = 0.873). Additionally, when compared to a multi-class U-Net, region-specific U-Nets yielded an average 20% improvement in Dice scores for segmenting each of the wall, lumen, and fat; even when tested on T2-weighted MRI scans that exhibited poorer image quality, or from a different plane, or were accrued from an external institution. Discussion: Developing deep learning segmentation models with region-specific context may thus enable highly accurate, detailed annotations for multiple rectal structures on post-chemoradiation T2-weighted MRI scans, which is critical for improving evaluation of tumor extent in vivo and building accurate image-based analytic tools for rectal cancers.

Central gland and peripheral zone prostate tumors have significantly different quantitative imaging signatures on 3 Tesla endorectal, in vivo T2-weighted MR imagery.

PURPOSE: To identify and evaluate textural quantitative imaging signatures (QISes) for tumors occurring within the central gland (CG) and peripheral zone (PZ) of the prostate, respectively, as seen on in vivo 3 Tesla (T) endorectal T2-weighted (T2w) MRI. MATERIALS AND METHODS: This study used 22 preoperative prostate MRI data sets (16 PZ, 6 CG) acquired from men with confirmed prostate cancer (CaP) and scheduled for radical prostatectomy (RP). The prostate region-of-interest (ROI) was automatically delineated on T2w MRI, following which it was corrected for intensity-based acquisition artifacts. An expert pathologist manually delineated the dominant tumor regions on ex vivo sectioned and stained RP specimens as well as identified each of the studies as either a CG or PZ CaP. A nonlinear registration scheme was used to spatially align and then map CaP extent from the ex vivo RP sections onto the corresponding MRI slices. A total of 110 texture features were then extracted on a per-voxel basis from all T2w MRI data sets. An information theoretic feature selection procedure was then applied to identify QISes comprising T2w MRI textural features specific to CG and PZ CaP, respectively. The QISes for CG and PZ CaP were evaluated by means of Quadratic Discriminant Analysis (QDA) on a per-voxel basis against the ground truth for CaP on T2w MRI, mapped from corresponding histology. RESULTS: The QDA classifier yielded an area under the Receiver Operating characteristic curve of 0.86 for the CG CaP studies, and 0.73 for the PZ CaP studies over 25 runs of randomized three-fold cross-validation. By comparison, the accuracy of the QDA classifier was significantly lower when (a) using all 110 texture features (with no feature selection applied), as well as (b) a randomly selected combination of texture features. CONCLUSION: CG and PZ prostate cancers have significantly differing textural quantitative imaging signatures on T2w endorectal in vivo MRI.