Journal of Pathology Informatics

Convolutional neural networks (CNNs) have shown strong capabilities for image analysis. However, deploying these models in medical settings is complicated by their limited transparency. Over recent years, many approaches have been developed to overcome the so-called "black box" problem of deep neural networks. Here, we show how such explainable AI (XAI) approaches can be applied to not only improve transparency but also training data quality and model performance, with classification of lung damage in histopathology images as use case. First, we conducted a thorough exploratory data analysis and visually compared the compressed multi-dimensional representations of the histology images from the last CNN layers with labels given by pathologists to reveal flaws in the training data. Second, we used Gradient-based Class Activation Mapping (Grad-CAM) as well as SHapley Additive exPlanations (SHAP) values to identify image regions that significantly contributed to the model decisions. To overcome identified shortcomings, we then finetuned additional top layers of the CNNs and introduced model architectures with attention which improved model performance. In summary, we developed a practical workflow that uses interpretability analyses to examine model perception, assess label consistency, and guide model refinement on the example of lung histopathology scoring, demonstrating how XAI approaches can increase both transparency and model performance. The code for this paper is shared at https://github.com/Aitslab/Histology_XAI.git.

Background: General-purpose large language models (LLMs) are increasingly evaluated in diagnostic pathology, but prior studies have largely emphasized diagnostic accuracy rather than how models fail. We evaluated four LLMs for diagnostic performance, pathology-relevant errors and hallucinations, their burden, and potential clinical impact across multi-organ pathology cases. Design: In this retrospective multicenter study, 153 pathology cases from two institutions spanning 20 organs were evaluated using ChatGPT-5.3 (LLM1), Gemini 3 (LLM2), Grok 4.20 (LLM3), and Claude Opus 4.6 (LLM4). Each LLM received multi-magnification histologic images with clinical context and generated a microscopic description and diagnosis. No data splitting, training, or fine-tuning was performed. Twenty-one pathologists assessed 612 outputs for diagnostic correctness, error and hallucination type and burden, clinical impact (0-4), and overall performance (1-5). Results: Strict diagnostic accuracy was 48.9% overall (60.1% including partially correct diagnoses) and ranged from 36.6% to 58.2% across LLMs. Errors occurred in 82.0% of outputs and hallucinations in 76.6%; 90.2% contained at least one error or hallucination. Misinterpretation was the most frequent error (72.1%), while fabricated histologic features were the dominant hallucination type (74.5%). LLM2 had significantly lower misinterpretation rates than the other three LLMs, while LLM3 had significantly higher fabricated-feature hallucination rates than LLM1 and LLM2. Errors were more frequent in incorrect than correct diagnoses (97.5% vs 66.2%), as were hallucinations (95.1% vs 59.9%; both p < 0.001). Every strictly incorrect diagnosis contained an error and/or hallucination, while 79.9% of strictly correct diagnoses also contained at least one. In multivariable analysis, LLM3 was independently associated with higher odds of an incorrect diagnosis. Diagnostic correctness was the strongest determinant of high clinical impact; each one-point increase in hallucination burden increased the odds by 63% (adjusted OR, 1.63). Conclusion: Diagnostic accuracy alone substantially underestimates the safety limitations of general-purpose LLMs in histopathology. Errors and hallucinations were common even when the final diagnosis was correct, and their burden was independently associated with clinical impact. Evaluation frameworks should therefore assess both diagnostic correctness and the reliability and potential consequences of accompanying generated content.

Cervical cancer is largely preventable when ab- normal cells are detected early. However, manual Pap-smear screening remains labor-intensive because a specimen may con- tain thousands of cells, borderline abnormalities are subtle, and expert cytology review is not equally accessible. Although artificial intelligence can reduce this workload, conventional classifiers often return a label without directly exposing the evidence used and may exploit staining or image-acquisition shortcuts. To address these limitations, we present CERVEX, a pathology-foundation-model framework with an additive class- evidence readout. Each class score is computed as the spatial mean of its class-specific evidence map plus a learned bias; therefore, the heatmap and numerical score are generated by the same forward calculation. CERVEX also produces a numerical research report containing class probabilities, evidence strength, ranked candidate regions, and segmentation-derived morphology, including N:C ratio and nuclear geometry. Under repeated slide- grouped evaluation on RIVA, with labelled target-cohort cells included during training, CERVEX distinguished abnormal from normal cells with AUROC 0.911 (SD 0.009), sensitivity 0.869, and specificity 0.796. Furthermore, fixed-grid analysis without cell coordinates distinguished low- from high-grade disease across 101 graded abnormal slides with AUROC 0.823 [0.728, 0.911]. On SIPaKMeD, nucleus and complete-cell segmentation reached Dice 0.932 and 0.942, while nuclear area fraction and N:C ratio reached measurement correlations of 0.977 and 0.962, respectively. Moreover, CERVEX produced class-specific spatial evidence while a separate held-out CRIC comparison did not resolve an accuracy difference from the conventional classifier, demonstrating computation-linked explainability with only 1.9% measured runtime overhead. Ultimately, CERVEX enables auto- mated analysis of cervical cytology microscope fields by linking cell classification, computation-linked spatial evidence, and in- terpretable numerical morphology indices in one pipeline. This supports transparent candidate-region review and establishes a practical foundation for future whole-slide screening and prospective clinical validation.

Foundation models (FMs) have rapidly become dominant in artificial intelligence and are increasingly being adopted in computational pathology. Numerous pathology-specific FMs have been developed and evaluated for a variety of downstream tasks, most commonly using frozen image embeddings with linear probes. While a pathology FM, at least implicitly suggests broad reusability across tasks, the transferability of these models to neurodegenerative disease-related tasks remains largely unexplored. In this study, we evaluated fourteen frozen feature extractors, including general-vision and pathology FMs, across four pathology image classification datasets spanning two specialized neurodegenerative disease immuno-histochemistry (IHC) tasks (Tau neurofibrillary tangle (NFT) and amyloid-{beta} plaque classification) and two cancer-related hematoxylin and eosin (H&E) tasks (the breast tissue BACH dataset and the multi-tissue TIL dataset). The cancer-related H&E datasets represent tasks more closely aligned with the predominant pretraining domain of many current pathology FMs, whereas the neurodegenerative IHC datasets represent a more specialized domain with limited representation in existing FM pretraining cohorts. Frozen embedding linear probes were compared against a conventional supervised ResNet-50 convolutional neural network (CNN) trained directly on image tiles using identical train, validation, and test splits. Across both neurodegenerative IHC datasets, the supervised CNN substantially outperformed all frozen FM linear probes. In contrast, pathology FMs achieved performance comparable to, and in some cases exceeding, the supervised CNN across the two cancer-related H&E datasets, with UNI2-h achieving the highest performance on BACH and several pathology FMs performing on par with the CNN on the larger TIL dataset. Furthermore, a supervised CNN trained using only 1% of the Tau NFT training data (1,938 tiles) still exceeded the performance of the best frozen FM linear probe trained on the complete dataset. Together, these results suggest the transferability of frozen pathology FMs may depend strongly on how well the downstream task is represented by their pretraining domain. These findings demonstrate frozen pathology FMs transfer effectively to the cancer-related H&E tasks evaluated here but may be less effective for specialized neurodegenerative IHC tasks less well represented in current FM pretraining cohorts. Expanding pathology FM pretraining datasets to include a broader range of disease domains and staining modalities may therefore improve transferability to specialized pathology applications. Our findings also highlight the continued importance of conventional supervised learning and motivate future work investigating nonlinear probes and end-to-end FM fine-tuning.

Background: Deep-learning systems for Gleason grading are developed almost entirely on high-end clinical scanners and on cohorts from a small number of Western institutions, yet deployment increasingly involves other devices and other populations. These two distribution shifts, device and population, are rarely tested together on the same physical slides. The PAR dataset, from Erbil, Iraq, digitizes each biopsy on three scanners and provides three distinct pathologist grades, so it permits both tests at once on a Middle Eastern cohort. A concurrent study by the dataset originators validated a task-specific model and two foundation models on PAR; we complement it by testing an inde-pendently developed detect-then-grade pipeline and by separating scanner effects on detection from scanner effects on grading. Methods: We applied one fixed model de-veloped on North American and European material to all 1017 whole-slide images (339 slides from 185 patients, three scanners; 49.6% clinically significant cancer) with no scanner-specific or population-specific tuning. We measured cancer detection (area under the ROC curve of the predicted cancer-tissue fraction), all-slide ISUP agreement of the deployed detect-then-grade pipeline (quadratic-weighted kappa, QWK), and grading agreement on pathologist-confirmed cancers, at the slide level and, because a case carries up to two slides, at the patient level. The reference reader was S.A.; thresholds and operating points were cross-validated leave-one-out; scanners were compared by paired within-biopsy bootstrap and confidence intervals confirmed by patient-cluster bootstrap. Results: Detection was statistically equivalent across scanners (AUC 0.987 to 0.991; paired differences at most 0.003) and transferred to this non-Western cohort with no per-population tuning. At a 95% sensitivity operating point the deployed pipeline reached cross-validated all-slide QWK of 0.86, 0.81, and 0.86 (Grundium, Hamamatsu, Leica), matching the inter-pathologist ceiling of 0.81, against 0.23 to 0.62 for the ungated model. Grading of confirmed cancers was scanner dependent: the compact Grundium (0.63) did not differ from the clinical Leica (0.67; paired difference 0.04, 95% CI -0.03 to 0.11), while both exceeded Hamamatsu (0.44). Results held at the patient level, with grading somewhat lower for two scanners; the two slides of a case disagreed in grade in 43% of cases, and patient clustering did not widen the intervals. Conclusions: Can-cer-tissue fraction is a triage signal robust across scanner and transferable to an un-derrepresented population for detection, while grading is the scanner-sensitive step. Prostate grading models should be deployed as a detect-then-grade pipeline, with grading validated per device and confirmed on the local population.

Cervical cytology screening relies on the visual assessment of nuclear and cellular morphology across thousands of cells per slide, a labor-intensive task that could benefit from quantitative computational support. Here we present CytoLens, a modular deep learning system that detects and counts nuclei, delineates nuclei and whole cells, measures the nuclear-to-cell area ratio (N:C), classifies cells from multifocal images and scores candidate abnormality. We trained and tested each module on a public dataset matched to its task, without pooling datasets. CytoLens detected nuclei with an F1 score of 0.931 (95% confidence interval (CI), 0.914-0.946) and counted 75 of 100 fields to within one nucleus. Point-prompted segmentation achieved mean Dice coefficients of 0.901 for nuclei and 0.847 for whole cells and, without retraining, transferred to a second dataset in which measured N:C increased with lesion grade in parallel with expert outlines. Multifocal hierarchical classification reached a mean accuracy of 0.947 across four Bethesda-aligned categories, and abnormality scores ranked annotated abnormal candidates with an area under the receiver operating characteristic curve (AUROC) of 0.865. These results support the evaluation of CytoLens on patient-linked clinical specimens.

Purpose Restaging transurethral resection of bladder tumor (reTURBT) is the standard-of-care for some patients with high-risk non-muscle invasive bladder cancer (NMIBC). However, it may lead to complications and biomarkers to avoid unnecessary reTURBT are needed. Materials and Methods Patients with high-risk NMIBC undergoing reTURBT were prospectively enrolled. Whole-exome sequencing along with low-pass whole-genome sequencing were performed on index TURBT samples to generate mutational profiles and copy number variation. Up to 50 personalized mutations and a fixed panel of 500 hotspot mutations were used for detecting variants from urine samples collected prior to reTURBT. Using a prespecified algorithm, tumor fraction (TF) and copy number burden (CNB) score were used to measure minimal residual disease and correlated with reTURBT pathology. Results Overall, 72/76 urine samples collected from patients with high-risk NMIBC prior to reTURBT passed quality check. From the indext TURBT specimens, a median of 39 personalized variants from the index TURBT were used for disease tracking. Overall, median TF was 0.206 vs. 0.001 in patients with and without residual tumor, respectively (p<0.001). Similarly, CNB score was elevated (7.34 vs. 4.02, p<0.001). utDNA achieved sensitivity of 97.8% and specificity of 69.2%, with area under the curve (AUC) of 0.932 in predicting disease found on reTURBT. Analyses of the index and reTURBT tissue and urine mutational profiles provided evidence for underdiagnosis of subclinical disease at the time of reTURBT. Conclusion Paired personalized and panel utDNA can be used to accurately detect residual disease in patients with high-risk NMIBC with potentially wide-ranging clinical applications.

IntroductionWhile placental perfusion and pathology jointly affect pregnancy outcomes, cotyledon-specific perfusion across gestation and its correlation with local injury is not yet well understood. Ferumoxytol dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) offers a promising way to noninvasively identify cotyledons across gestation and quantify longitudinal cotyledon-specific perfusion changes. Additionally, intraplacental injection of bioactive fibrin sealant allows us to model thrombotic placental injury and further assess cotyledon-level relationships between perfusion and significant injury. MethodsPregnant rhesus macaques (N=13) received intrauterine saline or fibrin sealant injections at gestational day (GD) [~]101 and underwent ferumoxytol DCE-MRI at GDs [~]100, 115, and 145. Placental perfusion domains derived from contrast arrival time were segmented at each imaging time point and matched to cotyledons identified following tissue collection by cesarean section, with cotyledon perfusion quantified longitudinally and correlated with cotyledon-specific quantitative histopathology. ResultsAll pregnancies were successfully carried to term. Fibrin sealant injections induced significantly higher levels of placental pathology compared to saline controls. MRI-derived perfusion domains were largely consistent across gestation and showed predominantly one-to-one correspondence with term cotyledons, with successful perfusion-pathology pairing achieved in 153 cotyledons. Longitudinal cotyledon perfusion changes showed significant positive correlations with villous agglutination injuries. ConclusionsFeasibility of noninvasively tracking placental cotyledon perfusion using ferumoxytol DCE-MRI was demonstrated, and the efficacy of the rhesus macaque thrombotic injury model was confirmed. The positive perfusion-pathology correlations suggested intrinsic placental regulatory mechanisms and functional plasticity. This new framework is promising for future translational studies and validation of ex vivo cotyledon perfusion models. HighlightsO_LILongitudinal tracking of placental perfusion domains with ferumoxytol MRI C_LIO_LISuccessful matching of cotyledons and MRI-derived perfusion domains C_LIO_LIConfirmed thrombotic injury-model induced cotyledon pathology C_LIO_LIMaternal perfusion compensation in presence of villous pathology C_LI

Reliable clinical deployment of automated liver segmentation requires mechanisms for detecting failures in rare and previously unseen scenarios. Achieving this goal requires an appropriately calibrated threshold that converts an out-of-distribution (OOD) score into a failure prediction. However, threshold calibration typically relies on expert-labeled failures, creating a substantial annotation burden when failures are rare. Building upon our prior work, which uses Pairwise Surface DSC scores as indicators of segmentation quality, we propose a label-free framework for calibrating OOD score thresholds. First, we fitted a log-t distribution to Pairwise Surface DSC scores from a validation set of 400 internal scans to approximate an in-distribution score distribution. New segmentations were assigned significance scores based on their extremity under this fitted distribution and categorized into Low, Medium, and High Risk review groups using statistically principled cutoffs of 0.25 and 0.05. The fitted log-t distribution provided a strong fit to the observed scores and remained robust to moderate contamination by OOD cases. On an independent test set of 500 internal and external scans, the combined Medium and High Risk categories achieved 100% sensitivity and 79% specificity, whereas the High Risk category alone achieved 78% sensitivity and 96% specificity. These results indicate that clinically meaningful failure detection can be derived from unlabeled data. Our code is available at https://github.com/marshalln7/Label_Free_OOD_Threshold_Selection.

Background Histological diagnosis of early-stage mycosis fungoides (MF) is hindered by profound overlap with benign inflammatory dermatoses (BIDs), leading to diagnostic delays and extensive ancillary testing. We developed MIMIC (Multiple Instance-learning for Identification of Mycosis fungoides In Cutaneous biopsies), a weakly supervised deep learning model designed as a triage tool at initial H&E whole slide image (WSI) review to distinguish classic patch and plaque stage MF from BIDs. We externally validated the model and evaluated its clinical utility. Methods In this retrospective multicentre study, we trained a base model using weakly supervised attention based multiple instance learning on 3,339 WSIs from two Dutch centres. Crucially, all MF training labels were derived from a deeply phenotyped national cohort featuring strict multidisciplinary expert panel consensus diagnoses (the clinical gold standard). Transportability was evaluated on 371 WSIs from four independent European centres. A blinded reader study on 171 WSIs compared morphology only performance of MIMIC with 11 (dermato-)pathologists. We then retrained an updated model on all retrospective multicentre data and assessed clinical utility in a strictly held out, consecutive Utrecht cohort (2022-2023; 486 accessions, 863 WSIs). Primary analysis focused on classic MF versus BIDs (453 accessions). Decision curve analysis, using Platt scaled probabilities to correct for spectrum bias, evaluated net benefit at a prespecified, safety oriented threshold of 0.04. Findings The base model showed good multicentre transportability (mean centre specific AUROC 0.91; pooled AUROC 0.84). In the reader study, MIMIC achieved an AUROC of 0.87, exceeding the mean pathologist AUROC (0.79) and the best individual reader (0.83). In the consecutive MF versus BID cohort, the updated model achieved an AUROC of 0.87 (95% CI 0.81-0.92). At the 0.04 threshold, sensitivity was 97.8% (44/45 MF cases) and specificity 50.2%, reducing unnecessary ancillary workups by 39.9 per 100 screening cases versus a test all strategy. Interpretation By identifying nearly half of BIDs as low risk while preserving near complete sensitivity for classic early stage MF in a European digital pathology workflow, this unimodal H&E approach offers a scalable digital solution to reduce defensive ancillary testing and accelerate the diagnostic journey for patients with MF. Further validation is needed in non European centres and in populations with darker skin phototypes.

BackgroundTraditional immunohistochemistry (IHC) with chromogen detection has limited multiplex capacity, detecting at most 4 protein markers per tissue section simultaneously, thereby restricting comprehensive spatial analysis of valuable human biopsies. We developed and validated a robust serial IHC (sIHC) staining method to detect multiple antigens on a single kidney biopsy slide, maximizing data yield for diagnosing and studying complex kidney diseases. MethodsFormalin-fixed, paraffin-embedded kidney biopsy sections were subjected to repeated IHC/imaging cycles with antibody removal using an optimized sodium dodecyl sulfate-glycerol buffer stripping protocol. Images were then co-registered, and analysis was performed using a variety of methodologies, including color deconvolution, cell segmentation, and spatial clustering. ResultsThis optimized sIHC method successfully detected up to 20 antigens on a single slide. Combining image analysis and artificial intelligence software, for example with HALO (Indica Labs), the assay assembles high-dimensional images and enables quantitative histology and single-cell spatial analysis. Using this advanced method, we were able to identify rare cell populations, such as double-negative T cells, that are challenging to detect conventionally. ConclusionWe have developed a validated, high-capacity sIHC protocol that uses standard IHC procedures with commercially available, clinically validated off-the-shelf antibodies. This method is a valuable, cost-effective tool for obtaining extensive, high-dimensional single-cell-resolved spatial data from limited pathology samples, such as a human kidney biopsy.

Current state of the art computational pathology foundation models attain satisfying accuracy most general pathology tasks including detection of pancreatic ductal adenocarcinoma (PDAC) but fail to provide sufficient explainability, operating as "black boxes". Some interpretability effort has been made, with models providing attention maps that project back on the slide the models high attended areas that pushed for the given prediction result, without further naming or reasoning explanation which can limit pathologists trust toward the prediction. We developed C3PRO, a cell-centric framework attempting to provide deeper understanding and explainability, by using embeddings extracted using a pathology foundation model, from cell centered tiles containing both the cell and its close neighborhood, which were then clustered into recurrent morphological phenotypes. A spatial graph was additionally constructed on top of the back-projected vocabulary to account for recurrent motifs. The evaluation of the model performance involved a cohort of 809 patients (825 diagnostic biopsies) using nested cross validation. C3PRO was benchmarked against four different multiple instance learning frameworks and achieved on-par performance for diagnostic (0.958 AUC), survival (0.617) and resectability (0.696) prediction, while providing additional insights compared to the strongest baseline models. Each clustered phenotype was probed and extracted as a representative tile mosaic and annotated by two expert pathologists, constituting a phenotype vocabulary available for statistical analysis. These phenotypes were scored by pathologists with physical brightfield microscopy and replicated the independent statistical significance impact on overall survival prediction from diagnostic biopsies.

Hematologic diagnostics and especially cytomorphologic assessment are time-intensive and require high levels of expertise. Vision Language Models (VLM) show promise in medical image analysis in radiology and histopathology, while an evaluation on detecting acute myeloid leukemia (AML) is lacking. Our goal was to evaluate three Vision Language Models regarding their diagnostic accuracy and safety in clinical decision support in detecting AML from digitized bone marrow smears (BMS). Whole slide images were obtained from bone marrow smears of 50 AML patients and 50 bone marrow donors. Ten representative fields of view per sample were extracted manually. Three VLMs were used, two of which are considered generalist models (Qwen3.5-397B-A17B-FP8, GLM-4.6V-FP8), while the other one is a medically adapted model (Medgemma-27b-it). All models performed zero-shot analysis using two prompting strategies: First, a context-rich prompt requesting reporting of WHO/FAB diagnostic criteria in a structured manner, and secondly a minimal prompt without specific hematologic context. Overall diagnostic accuracy was poor for all models as they exhibited the overwhelming tendency to classify most samples as leukemic: With context-rich prompts, GLM4.6 identified 90% of leukemic samples while also labeling 92% of bone marrow donors as AML. The medical specialist model MedGemma-27b showed similar failure, misclassifying 86% of healthy donors and correctly detecting AML in only 66% of cases. Qwen3.5 performed best under detailed prompting, achieving a specificity of 0.26 and accuracy of 0.51. Accuracy of all models improved with context-free prompts (accuracies range 0.47-0.79), yet they still lacked the ability to correctly distinguish between leukemia and healthy bone marrow. Qwen3.5 was the only model to maintain meaningful specificity (0.64) and correctly identified 94% of AML, yielding an overall accuracy of 0.79. Morphologic feature-level agreement with human expert reports was poor across all models, indicating poor recognition of cell-level morphologies. This failure is likely driven by the fact that pathology imaging archives are vastly scraped during model training while hematological samples are not as widely available and therefore, hematology is an out-of-bounds use-case for these models, rendering them currently unsuitable for clinical decision support in hematology.

Pathologic diagnoses of hematopoietic diseases require immunohistochemistry (IHC) stains selected by pathologists upon preview of H&E-stained slides. This multi-step workflow can delay diagnostic turnaround time by days. Hence, we developed the Hematopathology Automatic Triaging System (HATS), which automates IHC panel ordering directly from H&E whole-slide images using pretrained pathology foundation model representations combined with attention-based multiple-instance learning. After the most comprehensive evaluation of pathology foundation models for hematologic malignancy classification to date, encompassing seven publicly available models, we trained HATS on 4,996 whole-slide images from 1,607 patients spanning the ten most common lymphoma diagnostic categories. HATS achieves 84% case-level subtype classification accuracy (0.962 ROC-AUC), translating to 92% IHC panel ordering accuracy. In a blinded reader study, HATS outperforms practicing pathologists at predicting lymphoma subtypes from morphology alone (85% vs 65%). In an independent real-world validation of 230 clinical cases, after directing 7 cases with scant tissue for manual review, HATS-ordered IHC panels were sufficient for diagnosis in 72.6% of cases. By automating the triaging step while preserving full pathologist oversight, HATS offers a safe and practical entry point for clinical AI adoption in pathology.

Importance There is growing interest to avoid radical cystectomy (RC) in patients with muscle-invasive bladder cancer (MIBC) who receive neoadjuvant chemotherapy and achieve pathological complete response (ypCR). To achieve this goal, molecular biomarkers will likely need to be used to enhance clinical staging given the limitations of evaluation by cystoscopy, cytology, and cross-sectional imaging. There are no studies evaluating whether safe RC avoidance (SaRCA) would be cost effective and what impacts it would have on quality of life (QoL) and survival. Objective This study models the potential economic, QoL, and survival costs/benefits of a ypCR biomarker as it relates to SaRCA using a decision analysis and Markov Model (MM). Methods/Materials A decision tree and MM was created to compare the expected costs of initial treatment, QoL, and survival under one strategy where all patients undergo RC after neoadjuvant treatment versus an alternative strategy where all patients would be subjected to the biomarker test with biomarker-positive patients (those with presumed residual disease) undergoing RC, while biomarker-negative patients (presumed complete responders) would undergo surveillance for up to 20 years. ypCR rates to neoadjuvant therapy, survival with and without RC, quality adjusted life years (QALY), and costs were abstracted from the literature. Test cost, sensitivity, and specificity were also abstracted from the literature for multiple clinical or liquid biopsy approaches. Results Broadly, SaRCA approaches are cost effective with the exception of systematic endoscopic evaluation (SEE). All testing approaches result in higher QALY and overall life expectancy compared to no testing. The cost of the test is offset by decreased usage of RC to realize a cost savings. These domains are further improved when cisplatin-based chemotherapy is replaced with emerging neoadjuvant therapies. Conclusions and relevance Modeling supports the development of accurate biomarker tests which can distinguish residual disease states to enable SaRCA. Such a biomarker could be used to avoid an expensive and risky operation, and unexpectedly would provide a survival benefit by reducing the number of perioperative mortalities in patients achieving ypCR. Development of an accurate biomarker-based test is likely to reduce cost and increase QoL and survival. An accurate biomarker test would have utility for patients, payers, hospitals, and physicians.

Objectives To assess the effectiveness of our proposed urinary segmentation method based upon image processing, and to contrast its performance against various approaches. Subjects and Methods Non-contrast-enhanced computed tomography (NCCT) scans of instances with stone disease were collected. An experienced urologist and a senior radiology resident generated ground truths by manually drawing the regions of interest (ROIs) of stone samples. The proposed method took loosely defined ROIs as input and included three steps: (1) finding mean_HU_rim, the mean Hounsfield unit (HU) of the stone rim, on each NCCT slice by an edge detection operator; (2) considering pixels with HU higher than the minimum value of all the mean_HU_rim; and (3) removing noise. The entire data was divided into a developing set of 406 samples to evaluate the performance of the proposed method as well as to fine-tune a nnUNetv2 model and a comparison test set of 125 samples to compare the performance and inference time of various segmentation methods. In addition, the reproducibility of our method was tested on the 30 samples randomly selected from the entire data. Results A total of 531 stone samples from 287 instances were included. Our method showed a high level of agreement with the ground truth in the developing set, with the median (interquartile range) Dice coefficient of 0.86 (0.81 - 0.89). The reproducibility of our method was remarkably high with the median (interquartile range) Dice coefficient of 1.0 (0.991 - 1.0). On the comparison test set, our semi-automatic segmentation outperformed the fixed thresholding and deep-learning-based methods. Lastly, the inference time of the proposed method was less than a second. Conclusion The proposed semi-automatic approach provided a consistently reliable, simple, and robust method to segment urinary stones.

Objective: To perform internal and external validation of a gradient-boosted decision tree (GBDT) fusion model that integrates zygote morphokinetic parameters with conventional embryo assessment features for blastocyst prediction, and to compare its discriminative performance against senior embryologists. Methods: This retrospective cohort study included 631 normally fertilized zygotes from 218 treatment cycles. A GBDT fusion model integrating 84 zygote morphokinetic parameters and 8 conventional assessment features was evaluated internally (5-fold cross-validation) and externally on a public dataset of 523 embryos with blastocyst outcomes. Model performance was assessed using area under the ROC curve (AUC), area under the precision-recall curve (AUPRC), F1 score, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Discrimination was compared with embryologist consensus using the DeLong test; agreement was assessed with Cohen's kappa. Results: The model achieved an internal AUC of 0.78 (95% CI 0.74-0.82), AUPRC 0.72, F1 0.73, sensitivity 0.74, specificity 0.77, PPV 0.72, and NPV 0.79. External validation on the public dataset demonstrated acceptable generalizability (AUC 0.76, 95% CI 0.71-0.81). The model significantly outperformed embryologist consensus (AUC 0.70, P<0.001) with moderate agreement (kappa=0.56). Decision curve analysis confirmed clinical net benefit at threshold probabilities of 0.15-0.55. Conclusions: The GBDT fusion model integrating zygote morphokinetics with conventional assessment demonstrates good discrimination and external generalizability for blastocyst prediction, providing an interpretable decision-support tool for embryo selection in IVF practice.

Background: Artificial intelligence (AI) models for mammography can achieve high diagnostic performance when training and test data originate from similar populations and imaging environments, but performance often deteriorates under cross- cohort domain shift. Differences in acquisition systems, image characteristics, preprocessing, population composition, and disease prevalence can introduce distributional variation that is poorly captured by conventional within- dataset validation. Recent studies have further shown that Foundation Model representations can retain substantial dataset-specific information. However, it remains unclear how image representation influences diagnostic transfer to completely unseen cohorts and whether domain-adversarial learning provides comparable benefits across different representation types. Methods: We systematically evaluated cross-cohort mammography classification using seven independent datasets spanning diverse geographic, institutional, scanner, and imaging environments. Three image representations were compared: handcrafted radiomic features, EfficientNet-B0-derived features, and embeddings from the medical vision-language model MedSigLIP-448. Each was evaluated under three preprocessing conditions: unprocessed images, Otsu-based breast-region extraction, and Otsu extraction combined with Contrast Limited Adaptive Histogram Equalization (CLAHE). Patient-level classification was performed using a mean-pooled multilayer perceptron (MLP) baseline and an attention-based Domain-Adversarial Neural Network (DANN). Generalization was evaluated using a multi-source Leave-One-Domain-Out (LODO) framework in which six datasets were used for model development and the seventh was completely withheld as an unseen test cohort, iteratively across all seven datasets. Performance was primarily assessed by area under the receiver operating characteristic curve (AUC-ROC). Results: Cross-cohort performance depended strongly on image representation and model architecture. MedSigLIP consistently provided the highest performance on unseen cohorts. With MedSigLIP features, mean LODO AUC-ROC increased from 0.598 with MLP to 0.685 with DANN for unprocessed images, from 0.607 to 0.678 after Otsu preprocessing, and from 0.603 to 0.659 after CLAHE+Otsu preprocessing. When DANN-MLP differences were evaluated across held-out datasets and preprocessing conditions, a significant gain was observed for MedSigLIP after correction for multiple comparisons, whereas corresponding gains were not significant for Radiomics or EfficientNet-B0. A mixed-effects analysis similarly showed a positive MedSigLIP X DANN interaction, although this narrowly missed conventional statistical significance. Unprocessed images produced the highest numerical mean performance for MedSigLIP-DANN, but preprocessing itself had no significant overall effect. Notably, linear probing showed strong dataset discriminability in MedSigLIP and EfficientNet representations but little linearly recoverable dataset information in Radiomics, indicating that low dataset separability alone did not predict better diagnostic generalization. Conclusion: Cross-cohort mammography generalization depends strongly on the choice of image representation and its interaction with the classification strategy. MedSigLIP provided the most transferable representation in our multi-source unseen-domain evaluation, and the performance gain associated with DANN was concentrated in MedSigLIP rather than consistently observed across representation types. These findings suggest that the effectiveness of domain-adversarial learning is representation-dependent and that neither conventional preprocessing nor low dataset discriminability alone ensures robust transfer to unseen clinical cohorts.

Objectives: Menopausal symptoms are heterogeneous and commonly assessed by questionnaires. We explored serum two-dimensional gel electrophoresis (2-DE) protein spots associated with menopausal symptom burden. Methods: This exploratory cross-sectional study included 27 women aged 45-55 years. A total of 550 matched serum 2-DE spots were quantified. A frequency-adjusted symptom burden score was calculated as the sum of severity x frequency products across 10 symptoms. Spots were screened using Spearman rank correlation with Benjamini-Hochberg false discovery rate (FDR) adjustment, followed by qualitative image review. Spots #285 and #636 were prioritized for vasomotor and psychological domain analyses. Results: The median age was 51.0 years; 13 participants were menstruating and 14 were amenorrheic. The median overall symptom burden score was 45.0 (interquartile range, 6.5-58.5) and was inversely correlated with spots #285 and #636. Spot #285 was inversely correlated with vasomotor symptom score, including inverse correlations in both menstrual-status groups. Spot #636 was inversely correlated with psychological symptom score overall, with a stronger descriptive correlation among menstruating participants. Neither candidate remained significant after FDR adjustment. Conclusions: Spots #285 and #636 are hypothesis-generating candidates requiring molecular identification, analytical validation, multiplicity-aware confirmation, and independent replication.

Purpose: To quantify the sampling error of conventional 2D regions of interest (ROIs) compared with whole-organ 3D volumetric CT attenuation for opportunistic hepatic steatosis screening, and to evaluate its dependency on intraparenchymal spatial heterogeneity. Materials and Methods: In this retrospective computational study (CLAIM-compliant), 971 abdominal CT scans were analyzed across a multicenter derivation cohort (TotalSegmentator v2, n = 841) and an external validation cohort (Medical Segmentation Decathlon Task03, n = 130). Automated 3D liver segmentation was performed using nnU-Net, followed by an 8-mm spherical 3D erosion to eliminate peripheral partial volume effects and major hilar vessels. Three clinical sampling paradigms (1, 3, and 5 axial 2D ROIs of 15 mm diameter) were modeled through 500 stochastic Monte Carlo iterations per scan (485,500 total simulations). Absolute sampling error (|Delta HU| = |HU_ROI - HU_3D|) and diagnostic misclassification rates at the standard <= 40 HU steatosis threshold were computed. Results: In the derivation cohort, the conventional 3-ROI approach yielded a mean absolute error of 6.61 +/- 7.83 HU (median: 2.92 HU), significantly underperforming compared to the 5-ROI strategy (5.21 +/- 6.00 HU; Wilcoxon paired test, p < 0.001) but improving on the single-ROI approach (11.32 +/- 14.16 HU; p < 0.001). Sampling error correlated strongly with parenchymal spatial heterogeneity (Pearson r = 0.850, 95% CI: [0.830-0.868], p < 0.001). In borderline attenuation zones (35-45 HU), diagnostic misclassification reached 45.2% in heterogeneous livers. Findings were corroborated on external validation, confirming the reproducible decay of sampling error (|Delta HU| = 7.38 HU for 1 ROI vs. 5.14 HU for 3 ROI, p < 0.001). Conclusion: Manual 2D ROI sampling exhibits an intrinsic metrological uncertainty exceeding clinically relevant thresholds (5 HU) in heterogeneous livers, misclassifying nearly half of borderline cases. Opportunistic screening requires fully automated 3D volumetric extraction embedded into clinical PACS workflows.