Header

UZH-Logo

Maintenance Infos

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


Ebert, Lars C; Heimer, Jakob; Schweitzer, Wolf; Sieberth, Till; Leipner, Anja; Thali, Michael J; Ampanozi, Garyfalia (2017). Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning - a feasibility study. Forensic Science, Medicine, and Pathology, 13(4):426-431.

Abstract

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.

Abstract

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.

Statistics

Citations

Altmetrics

Downloads

0 downloads since deposited on 14 Dec 2017
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > Institute of Legal Medicine
Dewey Decimal Classification:340 Law
610 Medicine & health
Uncontrolled Keywords:Deep learning; Forensic imaging; Hemopericardium; Neural networks; PMCT
Language:English
Date:2017
Deposited On:14 Dec 2017 15:28
Last Modified:19 Feb 2018 09:35
Publisher:Springer
ISSN:1547-769X
OA Status:Closed
Publisher DOI:https://doi.org/10.1007/s12024-017-9906-1
PubMed ID:28819715

Download