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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Crohn's disease related strictures in cross-sectional imaging: More than meets the eye?

Strictures in Crohn's disease (CD) are a hallmark of long-standing intestinal damage, brought about by inflammatory and non-inflammatory pathways. Understanding the complex pathophysiology related to inflammatory infiltrates, extracellular matrix deposition, as well as muscular hyperplasia is crucial to produce high-quality scoring indices for assessing CD strictures. In addition, cross-sectional imaging modalities are the primary tool for diagnosis and follow-up of strictures, especially with the initiation of anti-fibrotic therapy clinical trials. This in turn requires such modalities to both diagnose strictures with high accuracy, as well as be able to delineate the impact of each histomorphologic component on the individual stricture. We discuss the current knowledge on cross-sectional imaging modalities used for stricturing CD, with an emphasis on histomorphologic correlates, novel imaging parameters which may improve segregation between inflammatory, muscular, and fibrotic stricture components, as well as a future outlook on the role of artificial intelligence in this field of gastroenterology.

RADIomic Spatial TexturAl Descriptor (RADISTAT): Quantifying Spatial Organization of Imaging Heterogeneity Associated With Tumor Response to Treatment.

Localized disease heterogeneity on imaging extracted via radiomics approaches have recently been associated with disease prognosis and treatment response. Traditionally, radiomics analyses leverage texture operators to derive voxel- or region-wise feature values towards quantifying subtle variations in image appearance within a region-of-interest (ROI). With the goal of mining additional voxel-wise texture patterns from radiomic "expression maps", we introduce a new RADIomic Spatial TexturAl descripTor (RADISTAT). This was driven by the hypothesis that quantifying spatial organization of texture patterns within an ROI could allow for better capturing interactions between different tissue classes present in a given region; thus enabling more accurate characterization of disease or response phenotypes. RADISTAT involves: (a) robustly identifying sub-compartments of low, intermediate, and high radiomic expression (i.e. heterogeneity) in a feature map and (b) quantifying spatial organization of sub-compartments via graph interactions. RADISTAT was evaluated in two clinically challenging problems: (1) discriminating nodal/distant metastasis from metastasis-free rectal cancer patients on post-chemoradiation T2w MRI, and (2) distinguishing tumor progression from pseudo-progression in glioblastoma multiforme using post-chemoradiation T1w MRI. Across over 800 experiments, RADISTAT yielded a consistent discriminatory signature for tumor progression (GBM) and disease metastasis (RCa); where its sub-compartments were associated with pathologic tissue types (fibrosis or tumor, determined via fusion of MRI and pathology). In a multi-institutional setting for both clinical problems, RADISTAT resulted in higher classifier performance (11% improvement in AUC, on average) compared to radiomic descriptors. Furthermore, combining RADISTAT with radiomic descriptors resulted in significantly improved performance compared to using radiomic descriptors alone.

Challenges in ensuring the generalizability of image quantitation methods for MRI.

Image quantitation methods including quantitative MRI, multiparametric MRI, and radiomics offer great promise for clinical use. However, many of these methods have limited clinical adoption, in part due to issues of generalizability, that is, the ability to translate methods and models across institutions. Researchers can assess generalizability through measurement of repeatability and reproducibility, thus quantifying different aspects of measurement variance. In this article, we review the challenges to ensuring repeatability and reproducibility of image quantitation methods as well as present strategies to minimize their variance to enable wider clinical implementation. We present possible solutions for achieving clinically acceptable performance of image quantitation methods and briefly discuss the impact of minimizing variance and achieving generalizability towards clinical implementation and adoption.

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.

Adipokine Resistin Levels at Time of Pediatric Crohn Disease Diagnosis Predict Escalation to Biologic Therapy.

BACKGROUND: Hypertrophy of visceral adipose tissue (VAT) is a hallmark of Crohn disease (CD). The VAT produces a wide range of adipokines, biologically active factors that contribute to metabolic disorders in addition to CD pathogenesis. The study aim was to concomitantly evaluate serum adipokine profiles and VAT volumes as predictors of disease outcomes and treatment course in newly diagnosed pediatric patients with CD. METHODS: Pediatric patients ages 6 to 20 years were enrolled, and their clinical data and anthropometric measurements were obtained. Adipokine levels were measured at 0, 6, and 12 months after CD diagnosis and baseline in control patients (CP). The VAT volumes were measured by magnetic resonance imaging or computed tomography imaging within 3 months of diagnosis. RESULTS: One hundred four patients undergoing colonoscopy were prospectively enrolled: 36 diagnosed with CD and 68 CP. The serum adipokine resistin and plasminogen activator inhibitor (PAI)-1 levels were significantly higher in patients with CD at diagnosis than in CP. The VAT volume was similar between CD and CP. Baseline resistin levels at the time of diagnosis in patients with CD who were escalated to biologics was significantly higher than in those not treated using biologic therapy by 12 months (29.8 ng/mL vs 13.8 ng/mL; P = 0.004). A resistin level of ≥29.8 ng/mL at the time of diagnosis predicted escalation to biologic therapy in the first year after diagnosis with a specificity of 95% (sensitivity = 53%; area under the curve = 0.82; P = 0.015 for model with log-scale). There was a significantly greater reduction in resistin (P = 0.002) and PAI-1 (P = 0.010) at the 12-month follow-up in patients on biologics compared with patients who were not treated using biologics. CONCLUSIONS: Serum resistin levels at diagnosis of pediatric CD predict the escalation to biologic therapy at 12 months, independent of VAT volumes. Resistin and PAI-1 levels significantly improved in patients with CD after treatment using biologics compared with those not on biologics. These results suggest the utility of resistin as a predictive biomarker in pediatric CD.

Identifying Cross-Scale Associations between Radiomic and Pathomic Signatures of Non-Small Cell Lung Cancer Subtypes: Preliminary Results.

(1) Background: Despite the complementarity between radiology and histopathology, both from a diagnostic and a prognostic perspective, quantitative analyses of these modalities are usually performed in disconnected silos. This work presents initial results for differentiating two major non-small cell lung cancer (NSCLC) subtypes by exploring cross-scale associations between Computed Tomography (CT) images and corresponding digitized pathology images. (2) Methods: The analysis comprised three phases, (i) a multi-resolution cell density quantification to identify discriminant pathomic patterns for differentiating adenocarcinoma (ADC) and squamous cell carcinoma (SCC), (ii) radiomic characterization of CT images by using Haralick descriptors to quantify tumor textural heterogeneity as represented by gray-level co-occurrences to discriminate the two pathological subtypes, and (iii) quantitative correlation analysis between the multi-modal features to identify potential associations between them. This analysis was carried out using two publicly available digitized pathology databases (117 cases from TCGA and 54 cases from CPTAC) and a public radiological collection of CT images (101 cases from NSCLC-R). (3) Results: The top-ranked cell density pathomic features from the histopathology analysis were correlation, contrast, homogeneity, sum of entropy and difference of variance; which yielded a cross-validated AUC of 0.72 ± 0.02 on the training set (CPTAC) and hold-out validation AUC of 0.77 on the testing set (TCGA). Top-ranked co-occurrence radiomic features within NSCLC-R were contrast, correlation and sum of entropy which yielded a cross-validated AUC of 0.72 ± 0.01. Preliminary but significant cross-scale associations were identified between cell density statistics and CT intensity values using matched specimens available in the TCGA cohort, which were used to significantly improve the overall discriminatory performance of radiomic features in differentiating NSCLC subtypes (AUC = 0.78 ± 0.01). (4) Conclusions: Initial results suggest that cross-scale associations may exist between digital pathology and CT imaging which can be used to identify relevant radiomic and histopathology features to accurately distinguish lung adenocarcinomas from squamous cell carcinomas.