Shakiba Sharifi

Digital pathology has transformed anatomic pathology by enabling whole-slide imaging, remote review, reproducible annotation, image analysis, and the development of artificial intelligence-based decision-support tools. In forensic pathology, however, the transition from glass slides to digital forensic histopathology remains in its early stages, despite recent evidence supporting the feasibility and diagnostic reliability of whole-slide imaging in medico-legal practice. The subsequent crucial step involves not merely digitizing forensic slides but also developing curated, multicentric, legally governed, and controlled-access datasets comprising forensic histopathological images. Such datasets are essential for education, interobserver harmonization, external quality assessment, and the development of reproducible quantitative tools suitable for forensic applications. This perspective paper argues that forensic pathology should regard datasets as scientific infrastructure rather than as passive image collections. An artificial intelligence-ready forensic histopathology dataset should include whole-slide images, standardized annotations, technical acquisition parameters, histological processing information, forensic metadata, quality-control records, reference standards, uncertainty labels, and explicit governance rules. Although important lessons can be drawn from anatomic pathology datasets, forensic pathology presents specific challenges, including low case numbers, post-mortem artifacts, heterogeneous sampling, variable fixation and preservation conditions, judicial and privacy concerns, and differences in national regulation of post-mortem data. We therefore propose a literature-informed conceptual framework for the development of forensic histopathology datasets, intended for forensic pathologists, researchers, institutional stakeholders, and AI tools developers. The framework is intended to support the development of shared resources for education, research, and AI development and validation, thereby providing a foundation for trustworthy and scientifically defensible computational applications in forensic pathology.

Cardiovascular disease is a leading cause of mortality, with coronary artery disease accounting for over 60% of cases in adults. Accurate quantification of coronary stenosis in forensic autopsies is crucial for determining causality between pathological findings and death, but is hindered by subjective visual assessments and inter-observer variability. This study aimed to develop an AI-driven tool using whole-slide images for objective stenosis measurement in forensic investigations. From 98 anonymized H&E-stained autopsy slides (234 coronary sections), 103 high-quality regions of interest were selected and split into training (n = 82), validation (n = 14), and test (n = 7) datasets. Annotations delineated lumen, internal elastic lamina, and external elastic lamina using QuPath. A SegFormer-B0 transformer model was trained with data augmentation, weighted cross-entropy loss, and AdamW optimization. Post-processing enforced anatomical structural hierarchy and generated hybrid confidence maps. On validation dataset, agreement with ground truth was excellent (MAE 3.22% points; RMSE 4.00; MAPE 6.07%; r = 0.986; ICC = 0.986), with slight underestimation. Bland–Altman bias was − 1.36 pp (95% LoA − 9.01 to 6.28 pp), indicating performance across severities. On the test set, accuracy improved (MAE 1.01 pp; RMSE 1.50; MAPE 2.11%; r = 0.998; ICC = 0.995) and outperformed three pathologists’ visual estimates (MAE 16.11, 8.18, 4.79 pp). Bland–Altman bias for the model was − 0.82 pp with tight limits of agreement (− 3.48 to 1.83 pp). Total inference time was 199.08 s for seven cases (28.44 s/image). WSI-based transformer pipeline enables rapid, auditable, and reproducible coronary stenosis measurement, reducing inter-observer variability and supporting standardized interpretation in forensic investigations. The online version contains supplementary material available at 10.1007/s00414-026-03800-6.

Anomaly detection is fundamental for ensuring quality control and operational efficiency in industrial environments, yet conventional approaches face significant challenges when training data contains mislabeled samples-a common occurrence in real-world scenarios. This paper presents RAD, a robust anomaly detection framework that integrates Normalizing Flows with Model-Agnostic Meta-Learning to address the critical challenge of label noise in industrial settings. Our approach employs a bi-level optimization strategy where meta-learning enables rapid adaptation to varying noise conditions, while uncertainty quantification guides adaptive L2 regularization to maintain model stability. The framework incorporates multiscale feature processing through pretrained feature extractors and leverages the precise likelihood estimation capabilities of Normalizing Flows for robust anomaly scoring. Comprehensive evaluation on MVTec-AD and KSDD2 datasets demonstrates superior performance, achieving I-AUROC scores of 95.4% and 94.6% respectively under clean conditions, while maintaining robust detection capabilities above 86.8% and 92.1% even when 50% of training samples are mislabeled. The results highlight RAD's exceptional resilience to noisy training conditions and its ability to detect subtle anomalies across diverse industrial scenarios, making it a practical solution for real-world anomaly detection applications where perfect data curation is challenging.