AI Insight
Researchers developed AI models using diffusion-based generative approaches to automatically detect fatal cerebral hemorrhage in postmortem CT scans, trained on 265 healthy subjects and 33 hemorrhage cases from 2011-2025. The unsupervised model achieved good performance (AUROC 0.928), but adding weak image-level supervision from documented causes of death substantially improved detection accuracy (AUROC 0.991). The models work by reconstructing what a healthy brain should look like and flagging differences as potential anomalies, requiring only simple labels rather than detailed annotations.
Why it matters
This approach could streamline forensic postmortem imaging by automatically flagging cases requiring urgent review, addressing the time-intensive nature of manual interpretation. The method's reliance on weak supervision rather than detailed annotations makes it more practical for forensic settings where annotated training data is scarce.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Postmortem computed tomography (PMCT) is increasingly used in forensic medicine, yet image interpretation remains largely manual and time-consuming, and supervised deep learning is constrained by the scarcity of annotated forensic datasets. This study investigated whether diffusion-based generative models can detect fatal cerebral haemorrhage on PMCT through reconstruction-based anomaly detection, using solely image-level labels derived from the documented cause of death. Postmortem brain CT examinations acquired at a single forensic institute between 2011 and 2025 were retrospectively analyzed, comprising 265 healthy subjects and 33 cases of fatal intracranial haemorrhage. After automated brain extraction, slice selection and intensity normalization, two diffusion frameworks were trained: an unsupervised denoising diffusion probabilistic model (AnoDDPM) trained on healthy anatomy alone, and a weakly supervised classifier-guided diffusion model exploiting image-level labels. Anomaly scores were derived from the reconstruction error between each slice and its pseudo-healthy reconstruction, and detection was assessed at the image level using 95% bootstrap confidence intervals. AnoDDPM achieved an AUROC of 0.928 (95% CI 0.812-0.989) and an AUPRC of 0.794 (95% CI 0.429-0.946), whereas the classifier-guided model reached an AUROC of 0.991 (95% CI 0.984-0.997) with an AUPRC of 0.960 (95% CI 0.855-0.994). These results demonstrate excellent feasibility of diffusion-based anomaly detection for forensic PMCT and indicate that weak, image-level supervision substantially improves detection, thereby supporting the future development of automated triage tools for postmortem brain imaging.
Source: 2D anomaly detection of fatal cerebral hemorrhage on postmortem CT