The histopathological evaluation of biopsies by human experts is a gold standard in clinical disease diagnosis. While recent artificial intelligence-based (AI) approaches have reached human expert-level performance, they often display shortcomings caused by variations in sample preparation, limiting clinical applicability. This study investigates the impact of data variation on AI-based histopathological grading and explores algorithmic approaches that confer prediction robustness. To evaluate the impact of data variation in histopathology, we collected a multicentric, retrospective, observational prostate cancer (PCa) trial consisting of six cohorts in 3 countries with 25,591 patients, 83,864 images. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in section thickness, staining protocol, and scanner. This unique training dataset enabled the development of an AI-based PCa grading framework by training on patient outcome, not subjective grading. It was made robust through several algorithmic adaptations, including domain adversarial training and credibility-guided color adaptation. We named the final grading framework PCAI. We compare PCAI to a BASE model and human experts on three external test cohorts, comprising 2,255 patients and 9,437 images. Variations in sample processing, particularly section thickness and staining time, significantly reduced the performance of AI-based PCa grading by up to 8.6 percentage points in the event-ordered concordance index (EOC-Index) thus highlighting serious risks for AI-based histopathological grading. Algorithmic improvements for model robustness, credibility, and training on high-variance data as well as outcome-based severity prediction give rise to robust models with grading performance surpassing experienced pathologists. We demonstrate how our algorithmic enhancements for greater robustness lead to significantly better performance, surpassing expert grading on EOC-Index and 5-year AUROC by up to 21.2 percentage points.

Background:Prostate cancer (PCa) is among the most common cancers in men and its diagnosis requires the histopathological evaluation of biopsies by human experts. While several recent artificial intelligence-based (AI) approaches have reached human expert-level PCa grading, they often display significantly reduced performance on external datasets. This reduced performance can be caused by variations in sample preparation, for instance the staining protocol, section thickness, or scanner used. Another limiting factor of contemporary AI-based PCa grading is the prediction of ISUP grades, which leads to the perpetuation of human annotation errors. Methods:We developed the prostate cancer aggressiveness index (PCAI), an AI-based PCa detection and grading framework that is trained on objective patient outcome, rather than subjective ISUP grades. We designed PCAI as a clinical application, containing algorithmic modules that offer robustness to data variation, medical interpretability, and a measure of prediction confidence. To train and evaluate PCAI, we generated a multicentric, retrospective, observational trial consisting of six cohorts with 25,591 patients, 83,864 images, and 5 years of median follow-up from 5 different centers and 3 countries. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in sample thickness, staining protocol, and scanner, allowing for the systematic evaluation and optimization of model robustness to data variation. The performance of PCAI was assessed on three external test cohorts from two countries, comprising 2,255 patients and 9,437 images. Findings:Using our high-variance datasets, we show how differences in sample processing, particularly slide thickness and staining time, significantly reduce the performance of AI-based PCa grading by up to 6.2 percentage points in the concordance index (C-index). We show how a select set of algorithmic improvements, including domain adversarial training, conferred robustness to data variation, interpretability, and a measure of credibility to PCAI. These changes lead to significant prediction improvement across two biopsy cohorts and one TMA cohort, systematically exceeding expert ISUP grading in C-index and AUROC by up to 22 percentage points. Interpretation:Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.

BACKGROUND AND OBJECTIVES:This study identified a clinically significant subset of patients with glioma with tumor outside of contrast enhancement present at autopsy and subsequently developed a method for detecting nonenhancing tumor using radio-pathomic mapping. We tested the hypothesis that autopsy-based radio-pathomic tumor probability maps would be able to noninvasively identify areas of infiltrative tumor beyond traditional imaging signatures. METHODS:A total of 159 tissue samples from 65 subjects were aligned to MRI acquired nearest to death for this retrospective study. Demographic and survival characteristics for patients with and without tumor beyond the contrast-enhancing margin were computed. An ensemble algorithm was used to predict pixelwise tumor presence from pathological annotations using segmented cellularity (Cell), extracellular fluid, and cytoplasm density as input (6 train/3 test subjects). A second level of ensemble algorithms was used to predict voxelwise Cell, extracellular fluid, and cytoplasm on the full data set (43 train/22 test subjects) using 5-by-5 voxel tiles from T1, T1 + C, fluid-attenuated inversion recovery, and apparent diffusion coefficient as input. The models were then combined to generate noninvasive whole brain maps of tumor probability. RESULTS:Tumor outside of contrast was identified in 41.5% of patients, who showed worse survival outcomes (hazard ratio = 3.90, P < .001). Tumor probability maps reliably tracked nonenhancing tumor on a range of local and external unseen data, identifying tumor outside of contrast in 69% of presurgical cases that also showed reduced survival outcomes (hazard ratio = 1.67, P = .027). CONCLUSION:This study developed a multistage model for mapping gliomas using autopsy tissue samples as ground truth, which was able to identify regions of tumor beyond traditional imaging signatures.

ABSTRACTBackgroundMembranous nephropathy (MN) is caused by autoantibody binding to podocyte foot process antigens such as THSD7A and PLA2R1. The mechanisms of the glomerular antigen/autoantibody deposition and clearance are unknown.MethodsWe explore the origin and significance of glomerular accumulations in (1) diagnostic and follow-up biospecimens from THSD7A+and PLA2R1+-MN patients compared to nephrotic non-MN patients, and (2) in experimental models of THSD7A+-MN.ResultsWe discovered podocyte exophers as correlates of histological antigen/autoantibody aggregates found in the glomerular urinary space of MN patients. Exopher vesicle formation represents a novel form of toxic protein aggregate removal inCaenorhabditis elegansneurons. In MN patients, podocytes released exophers to the urine. Enrichment of exophers from MN patient urines established them as a glomerular exit route for antigens and bound autoantibody. Exophers also carried disease-associated proteins such as complement and provided a molecular imprint of podocyte injury pathways. In experimental THSD7A+-MN, exophers were formed from podocyte processes and cell body. Their formation involved the translocation of antigen/autoantibody from the subepithelial to the urinary side of podocyte plasma membranes. Urinary exopher-release correlated with lower albuminuria and lower glomerular antigen/autoantibody burden. In MN patients the prospective monitoring of urinary exopher abundance and of exopher-bound autoantibodies was additive in the assessment of immunologic MN activity.ConclusionsExopher-formation and release is a novel pathomechanism in MN to remove antigen/autoantibody aggregates from the podocyte. Tracking exopher-release will add a non-invasive diagnostic tool with prognostic potential to clinical diagnostics and follow-up of MN patients.

This study used prostate histology and multi-parametric magnetic resonance imaging (MP-MRI) to evaluate diffusion differences in Gleason pattern 4 gland morphology. After surgery, tissue was sliced using slicing jigs, annotated by a board-certified pathologist, and digitally contoured to differentiate lumen and epithelium. Slides were co-registered to the T2-weighted MRI scan. Two linear mixed models were fitted to the MP-MRI data to consider the different hierarchical structures. Model (1) considers patient as random effect, and Model (2) adds a nested effect for slide. We found that cribriform glands were more diffusion restricted than fused glands in Gleason Grade 4 tumors.

Prostate cancer is among the most common cancers in men with around 1.4 million new cases each year world-wide. A vital part in the diagnosis of prostate cancer is the evaluation of its severity using biopsies and histopathology. Recent progress in artificial intelligence-based image analysis has led to a flurry of algorithms for the automated analysis of prostate cancer histopathological data focusing on the detection of cancerous areas, the grading of cancer severity, and patient outcome. Some of these approaches have reached human expert-level performance and digital models trained directly on patient outcomes might surpass human performance in the future. Although these results hold great promise for the future usage of digital pathology in clinical settings, several bottlenecks remain to be addressed. Especially the robustness, reliability and trustworthiness of predictions must be guaranteed across a wide range of variation in protocols and instrumentation. While human experts are relatively robust to technical and biological variation in biopsies, artificial intelligence-based systems tend to struggle with differences in staining intensity, color, scanner type, and image resolution, impeding the clinical usage of digital models. In this work we highlight salient problems and minimal requirements of computational pathology for future use in clinical settings, while focusing on prostate cancer as a use case. In particular, we highlight data and model problems and solutions that include data variability, dataset size, and data annotations, as well as model robustness to data heterogeneity, model prediction confidence, and the explainability of model decisions. While model and data requirements for successful computational pathology in clinics will be highlighted, legal, ethical, and deployment requirements will not be addressed in this review. In summary, we provide a short overview of the field, salient problems, and potential solutions to harvest the full potential of digital pathology for prostate cancer in clinical practice.

Prostate cancer is the most commonly diagnosed cancer in men, accounting for 27% of the new male cancer diagnoses in 2022. If organ-confined, removal of the prostate through radical prostatectomy is considered curative; however, distant metastases may occur, resulting in a poor patient prognosis. This study sought to determine whether quantitative pathomic features of prostate cancer differ in patients who biochemically experience biological recurrence after surgery. Whole-mount prostate histology from 78 patients was analyzed for this study. In total, 614 slides were hematoxylin and eosin stained and digitized to produce whole slide images (WSI). Regions of differing Gleason patterns were digitally annotated by a genitourinary fellowship-trained pathologist, and high-resolution tiles were extracted from each annotated region of interest for further analysis. Individual glands within the prostate were identified using automated image processing algorithms, and histomorphometric features were calculated on a per-tile basis and across WSI and averaged by patients. Tiles were organized into cancer and benign tissues. Logistic regression models were fit to assess the predictive value of the calculated pathomic features across tile groups and WSI; additionally, models using clinical information were used for comparisons. Logistic regression classified each pathomic feature model at accuracies >80% with areas under the curve of 0.82, 0.76, 0.75, and 0.72 for all tiles, cancer only, noncancer only, and across WSI. This was comparable with standard clinical information, Gleason Grade Groups, and CAPRA score, which achieved similar accuracies but areas under the curve of 0.80, 0.77, and 0.70, respectively. This study demonstrates that the use of quantitative pathomic features calculated from digital histology of prostate cancer may provide clinicians with additional information beyond the traditional qualitative pathologist assessment. Further research is warranted to determine possible inclusion in treatment guidance.

Expansion microscopy physically enlarges biological specimens to achieve nanoscale resolution using diffraction-limited microscopy systems1. However, optimal performance is usually reached using laser-based systems (for example, confocal microscopy), restricting its broad applicability in clinical pathology, as most centres have access only to light-emitting diode (LED)-based widefield systems. As a possible alternative, a computational method for image resolution enhancement, namely, super-resolution radial fluctuations (SRRF)2,3, has recently been developed. However, this method has not been explored in pathology specimens to date, because on its own, it does not achieve sufficient resolution for routine clinical use. Here, we report expansion-enhanced super-resolution radial fluctuations (ExSRRF), a simple, robust, scalable and accessible workflow that provides a resolution of up to 25 nm using LED-based widefield microscopy. ExSRRF enables molecular profiling of subcellular structures from archival formalin-fixed paraffin-embedded tissues in complex clinical and experimental specimens, including ischaemic, degenerative, neoplastic, genetic and immune-mediated disorders. Furthermore, as examples of its potential application to experimental and clinical pathology, we show that ExSRRF can be used to identify and quantify classical features of endoplasmic reticulum stress in the murine ischaemic kidney and diagnostic ultrastructural features in human kidney biopsies.

This study used autopsy tissue samples to develop multi-stage radio-pathomic models of tumor probability in glioma patients. Three models were trained to predict cell density, extracellular fluid density, and cytoplasm density segmented from autopsy samples using T1, T1C, FLAIR, and ADC intensity. A fourth model was then trained to predict tumor probability from pathological annotations using the cellularity, extracellular fluid, and cytoplasm segmentations as input. The combined models were then able to non-invasively estimate tumor probability using MRI. These maps identified regions of tumor beyond the contrast-enhancing region and discriminated between areas of tumor and vasogenic edema within FLAIR hyperintensity.

One in eight men will be affected by prostate cancer (PCa) in their lives. While the current clinical standard prognostic marker for PCa is the Gleason score, it is subject to inter-reviewer variability. This study compares two machine learning methods for discriminating between cancerous regions on digitized histology from 47 PCa patients. Whole-slide images were annotated by a GU fellowship-trained pathologist for each Gleason pattern. High-resolution tiles were extracted from annotated and unlabeled tissue. Patients were separated into a training set of 31 patients (Cohort A, n = 9345 tiles) and a testing cohort of 16 patients (Cohort B, n = 4375 tiles). Tiles from Cohort A were used to train a ResNet model, and glands from these tiles were segmented to calculate pathomic features to train a bagged ensemble model to discriminate tumors as (1) cancer and noncancer, (2) high- and low-grade cancer from noncancer, and (3) all Gleason patterns. The outputs of these models were compared to ground-truth pathologist annotations. The ensemble and ResNet models had overall accuracies of 89% and 88%, respectively, at predicting cancer from noncancer. The ResNet model was additionally able to differentiate Gleason patterns on data from Cohort B while the ensemble model was not. Our results suggest that quantitative pathomic features calculated from PCa histology can distinguish regions of cancer; however, texture features captured by deep learning frameworks better differentiate unique Gleason patterns.

The latent space of a generative adversarial network (GAN) may model pathologically-significant semantics with unsupervised learning. To explore this phenomenon, we trained and tested a StyleGAN2 on a high quality prostate histology dataset covering the prostate cancer (PCa) diagnostic spectrum. Our pathologist annotated synthetic images to identify learned PCa regions in the GAN latent space. New points were drawn from these regions, synthesized into images, and given to a pathologist for annotation. 77% of the new points received the same annotation, and 98% of the latent points received the same or adjacent diagnostic stage annotation. This confirms the GAN network can accurately disentangle and model PCa features without exposure to labels in the training process.

Background This study identified a clinically significant subset of glioma patients with tumor outside of contrast-enhancement present at autopsy, and subsequently developed a method for detecting non-enhancing tumor using radio-pathomic mapping. We tested the hypothesis that autopsy-based radio-pathomic tumor probability maps would be able to non-invasively identify areas of infiltrative tumor beyond traditional imaging signatures.Methods A total of 159 tissue samples from 65 subjects were aligned to MRI acquired nearest to death for this study. Demographic and survival characteristics for patients with and without tumor beyond the contrast-enhancing margin were computed. An ensemble algorithm was used to predict pixelwise tumor presence from pathological annotations using segmented cellularity (Cell), extracellular fluid (ECF), and cytoplasm (Cyt) density as input (6 train/3 test subjects). A second level of ensemble algorithms were used to predict voxel-wise Cell, ECF, and Cyt on the full dataset (43 train/22 test subjects) using 5-by-5 voxel tiles from T1, T1+C, FLAIR, and ADC as input. The models were then combined to generate non-invasive whole brain maps of tumor probability.Results Tumor outside of contrast was identified in 41.5 percent of patients, who showed worse survival outcomes (HR=3.90, p < 0.001). Tumor probability maps reliably tracked non-enhancing tumor in the test set, external data collected pre-surgery, and longitudinal data to identify treatment-related changes and anticipate recurrence.Conclusions This study developed a multi-1 stage model for mapping gliomas using autopsy tissue samples as ground truth, which was able to identify regions of tumor beyond traditional imaging signatures.### Competing Interest StatementPSL and JMC receive funding from Novacure Inc. unrelated to the scope of this study### Funding StatementPSL: American Brain Tumor Association Grant DG160004, Froedtert Foundation, Strain for the Brain 5K Run, Milwaukee, WI, NIH/NCI R01CA218144, R01CA218144-02S1, R21CA231892, and R01CA249882. BME: NIH/NCI R01CA270027, NIH/NCI P50CA211015, DoD CA20029### Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:IRB of Medical College of Wisconsin gave ethical approval for this workI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesThe MRI and histology data sets used in this study are not currently publicly available due to data usage agreement restrictions. De-identified data is available upon reasonable request.

A radio-pathomic model for cellularity trained with tissue samples acquired at postmortem examination is able to identify regions of hypercellular tumor beyond traditional imaging signatures. BACKGROUND AND PURPOSE: Currently, contrast-enhancing margins on T1WI are used to guide treatment of gliomas, yet tumor invasion beyond the contrast-enhancing region is a known confounding factor. Therefore, this study used postmortem tissue samples aligned with clinically acquired MRIs to quantify the relationship between intensity values and cellularity as well as to develop a radio-pathomic model to predict cellularity using MR imaging data. MATERIALS AND METHODS: This single-institution study used 93 samples collected at postmortem examination from 44 patients with brain cancer. Tissue samples were processed, stained with H&E, and digitized for nuclei segmentation and cell density calculation. Pre- and postgadolinium contrast T1WI, T2 FLAIR, and ADC images were collected from each patient’s final acquisition before death. In-house software was used to align tissue samples to the FLAIR image via manually defined control points. Mixed-effects models were used to assess the relationship between single-image intensity and cellularity for each image. An ensemble learner was trained to predict cellularity using 5 × 5 voxel tiles from each image, with a two-thirds to one-third train-test split for validation. RESULTS: Single-image analyses found subtle associations between image intensity and cellularity, with a less pronounced relationship in patients with glioblastoma. The radio-pathomic model accurately predicted cellularity in the test set (root mean squared error = 1015 cells/mm2) and identified regions of hypercellularity beyond the contrast-enhancing region. CONCLUSIONS: A radio-pathomic model for cellularity trained with tissue samples acquired at postmortem examination is able to identify regions of hypercellular tumor beyond traditional imaging signatures.

The presence and extent of cribriform patterned Gleason 4 (G4) glands are associated with poor prognosis following radical prostatectomy. This study used whole-mount prostate histology and multiparametric magnetic resonance imaging (MP-MRI) to evaluate diffusion differences in G4 gland morphology. Fourty-eight patients underwent MP-MRI prior to prostatectomy, of whom 22 patients had regions of both G4 cribriform glands and G4 fused glands (G4CG and G4FG, respectively). After surgery, the prostate was sliced using custom, patient-specific 3D-printed slicing jigs modeled according to the T2-weighted MR image, processed, and embedded in paraffin. Whole-mount hematoxylin and eosin-stained slides were annotated by our urologic pathologist and digitally contoured to differentiate the lumen, epithelium, and stroma. Digitized slides were co-registered to the T2-weighted MRI scan. Linear mixed models were fitted to the MP-MRI data to consider the different hierarchical structures at the patient and slide level. We found that Gleason 4 cribriform glands were more diffusion-restricted than fused glands.

Background One in eight men will be affected by prostate cancer (PCa) in their lives. While the current clinical standard prognostic marker for PCa is the Gleason score, it is subject to interreviewer variability. This study compares two machine learning methods for discriminating between high- and low-grade PCa on histology from 47 PCa patients. Methods Digitized slides were annotated by a GU fellowship-trained pathologist. High-resolution tiles were extracted from annotated and unlabeled tissue. Glands were segmented and pathomic features were calculated and averaged across each patient. Patients were separated into a training set of 31 patients (Cohort A, n=9345 tiles) and a testing cohort of 16 patients (Cohort B, n=4375 tiles). Tiles from Cohort A were used to train a compact classification ensemble model and a ResNet model to discriminate tumor and were compared to pathologist annotations. Results The ensemble and ResNet models had overall accuracies of 89% and 88%, respectively. The ResNet model was additionally able to differentiate Gleason patterns on data from Cohort B while the ensemble model was not. Conclusions Our results suggest that quantitative pathomic features calculated from PCa histology can distinguish regions of cancer; how-ever, texture features captured by deep learning frameworks better differentiate unique Gleason patterns.

Abstract PURPOSE Glioblastoma is one of the most common and deadly adult brain tumors. Current standard treatment is surgical resection followed by radiation and concomitant chemotherapy (chemoRT). Glioblastoma progression is monitored using MRI, primarily relying on post-contrast T1-weighted imaging (T1C). Unfortunately, tumor invasion is known to extend beyond traditional contrast enhancement. T1-subtraction (T1S) maps have been introduced as a better tumor volume estimate. In this study we compare T1S map derived tumor annotations to a radiologist for identifying histologically confirmed tumor in patients with differing treatment histories at autopsy. METHODS Ten patients with autopsy confirmed glioblastoma and MRI within 1 month of death were recruited for this study. Seven patients received chemoRT combined (chemoRT+) and three patients received no treatment beyond surgery (chemoRT-). Patient’s brains were sliced axially in the same orientation as their final MRI using a patient-specific slicing jig. Large tissue samples were taken, processed, embedded in paraffin, stained for hematoxylin and eosin, and digitized at 40x resolution. Digital images were annotated for infiltrative tumor, pseudopalisading necrosis, and necrosis without palisading cells. T1S and radiologist annotations were created for each patient using their final MRI (mean 18 days prior to death). The annotated histology images were aligned and resampled into MRI space using custom software and the overlap of pathologically confirmed tumor and MRI derived annotations was compared. RESULTS T1S maps alone were significantly better at identifying areas of histologically confirmed tumor in chemoRT+ patients compared to chemoRT- patients (p=0.043). T1S derived annotations overlapped with 52% of histologically confirmed tumor in the chemoRT- patients and 78% in the chemoRT+. The radiologist drawn tumor masks were more accurate in chemoRT+ patients, identifying 61% confirmed tumor (trending, p=0.097, chemoRT+=61%). CONCLUSION These results demonstrate the difficulty of identifying pathologically confirmed tumor outside contrast enhancement in glioblastoma patients, even in the untreated state.

Tumor heterogeneity in glioblastoma complicates delineation of active tumor using standard MR imaging. Pseudo-progression following treatment with chemotherapy and radiation (chemoRT) further complicates how tumors appear. T1-weighted subtraction maps (T1S) have been used to better identify subtly enhancing regions containing infiltrative tumor. This study examines the differences in tumor appearance between patients treated with chemoRT compared to a cohort opting out at autopsy, to understand how chemoRT changes contrast enhancement on MRI. Ten patients diagnosed with glioblastoma were recruited for whole brain donation for this study. Three patients received no treatment (chemoRT-), and seven received a combination of chemoRT and additional treatments (chemoRT+), including but not limited to bevacizumab (Bev) and tumor treating fields (TTF). Large tissue samples were taken at autopsy from whole brain samples sliced axially to align with the last clinical MRI using patient-specific 3D-printed slicing jigs. All tissue samples were hematoxylin and eosin (HE) stained and digitized at 40X resolution (27 total samples). The whole slide images (WSI) were annotated to outline regions containing necrosis without pseudopalisading cells, tumor with pseudopalisading necrosis, and infiltrative tumor. T1S were created for each patient by subtracting intensity normalized T1-weighted images from T1 post-contrast images (T1C). The annotated WSIs were aligned and resampled into MRI space using a custom software. A mixed effect model was used to compare the T1S intensity between chemoRT +/- cohorts within each pathological annotation, incorporating a random effect for subject. Mean T1S intensity was greater in untreated subjects when compared to chemoRT-subjects within each pathological annotation, including necrosis without pseudopalisading cells, tumor with pseudopalisading necrosis, and infiltrative tumor (p< 0.001). We show that chemoRT reduces the contrast enhancement in all aspects of pathologically validated tumor compartments, including infiltrative tumor. Future research is needed to examine if other patterns are evident in additional MR sequences.

BACKGROUND Over one-half of all cancer patients receive radiation therapy (RT). However, radiation exposure to the heart can cause cardiotoxicity. Nevertheless, there is a paucity of data on RT-induced cardiac damage, with limited understanding of safe regional RT doses, early detection, prevention, and management. A common initial feature of cardiotoxicity is asymptomatic dysfunction, which, if left untreated, may progress to heart failure. The current paradigm for cardiotoxidty detection and management relies primarily upon assessment of ejection fraction. However, cardiac injury can occur without a dear change in ejection fraction. OBJECTIVES We sought to identify cardiac magnetic resonance (CMR) imaging markers of early RT-induced cardiac dysfunction. METHODS We investigated the effect of RT on global and regional cardiac function and myocardial T1/T2 values at 2 time points post-RT using CMR in a rat model of localized cardiac RT. Rats who received image-guided whole-heart radiation of 24 Gy were compared with sham-treated rats. RESULTS The rats maintained normal global cardiac function post-RT. However, a deterioration in strain was particularly notable at 10 weeks post-RT, and changes in circumferential strain were larger than changes in radial or longitudinal strain. Compared with sham treatment, circumferential strain changes occurred at the basal, mid-ventricular, and apical levels (p < 0.05 for all at both 8 weeks and 10 weeks post-RT), most of the radial strain changes occurred at the midventricular (p = 0.044 at 8 weeks post-RT) and basal (p = 0.018 at 10 weeks post-RT) levels, and most of the longitudinal strain changes occurred at the apical (p 0.002 at 8 weeks post-RT) and basal (p 0.035 at 10 weeks post-RT) levels. Regionally, lateral myocardial segments showed the greatest worsening in strain measurements, and histological changes supported these findings. Despite worsened myocardial strain post-RT, myocardial tissue displacement measures were maintained, or even increased. T1/T2 measurements showed small nonsignificant changes post-RT compared with values in nonirradiated rats. CONCLUSIONS Our findings suggest MRI regional myocardial strain is a sensitive imaging biomarker for detecting RT-induced subdinical cardiac dysfunction before compromise of global cardiac function. (C) 2021 The Authors. Published by Elsevier on behalf of the American College of Cardiology Foundation.