Marianna Garavello

Estimating the post‐mortem interval (PMI) remains a major challenge in forensic practice, as conventional thanatological signs are strongly influenced by biological and environmental variables. Immunohistochemistry is a complementary strategy for identifying tissue biomarkers with time‐dependent post‐mortem persistence. In this retrospective study, we assessed the immunohistochemical expression of Caspase‐8, Annexin A1, B‐cell lymphoma 2 (Bcl‐2), and Nuclear Factor kappa B (NF‐κB) in brain, heart, and liver samples from 32 autopsies with known PMI (1.38–23 days). Cases were stratified into four PMI groups: < 2 days, ≥ 2 to < 5 days, ≥ 5 to ≤ 8 days, and > 8 days. Immunoreactivity was scored semi‐quantitatively as weak (1+) or strong (2+). Caspase‐8 showed the highest overall positivity and the longest persistence, remaining detectable up to 22 days in heart, 16 days in brain, and 14 days in liver, with complete positivity across tissues up to 8 days. Annexin A1 displayed last positivity at 6.09 days in brain and 7.63 days in heart and liver, being consistently negative beyond 8 days. Bcl‐2 expression was restricted to myocardium and detected only in very early PMI cases (< 2 days), whereas NF‐κB was consistently negative. These findings support a tissue‐specific, multiparametric model for PMI stratification.

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.