Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning - a feasibility study

• Published in: Forensic science, medicine, and pathology medicine, and pathology, 2017-12, Vol.13 (4), p.426-431
• Main Authors: Ebert, Lars C., Heimer, Jakob, Schweitzer, Wolf, Sieberth, Till, Leipner, Anja, Thali, Michael, Ampanozi, Garyfalia
• Format: Article
• Language: English
• Subjects: Criminology and Criminal Justice; CT imaging; Feasibility Studies; Female; Forensic Medicine; Forensic Pathology - methods; Humans; Image Processing, Computer-Assisted; Male; Medical imaging equipment; Medicine; Medicine & Public Health; Neural Networks (Computer); Original Article; Pathology; Pericardial Effusion - diagnostic imaging; Retrospective Studies; Software; Tomography, X-Ray Computed
• ISSN: 1547-769X; 1556-2891
• DOI: 10.1007/s12024-017-9906-1

Post mortem computed tomography (PMCT) can be used as a triage tool to better identify cases with a possibly non-natural cause of death, especially when high caseloads make it impossible to perform autopsies on all cases. Substantial data can be generated by modern medical scanners, especially in a forensic setting where the entire body is documented at high resolution. A solution for the resulting issues could be the use of deep learning techniques for automatic analysis of radiological images. In this article, we wanted to test the feasibility of such methods for forensic imaging by hypothesizing that deep learning methods can detect and segment a hemopericardium in PMCT. For deep learning image analysis software, we used the ViDi Suite 2.0. We retrospectively selected 28 cases with, and 24 cases without, hemopericardium. Based on these data, we trained two separate deep learning networks. The first one classified images into hemopericardium/not hemopericardium, and the second one segmented the blood content. We randomly selected 50% of the data for training and 50% for validation. This process was repeated 20 times. The best performing classification network classified all cases of hemopericardium from the validation images correctly with only a few false positives. The best performing segmentation network would tend to underestimate the amount of blood in the pericardium, which is the case for most networks. This is the first study that shows that deep learning has potential for automated image analysis of radiological images in forensic medicine.