Sperm hunting on optical microscope slides for forensic analysis with deep convolutional networks – a feasibility study. (January 2022)

• Record Type: Journal Article
• Authors: Golomingi, Raffael; Haas, Cordula; Dobay, Akos; Kottner, Sören; Ebert, Lars
• Is Part Of: Forensic science international. Volume 56(2022)
• Publication Date: 2022-01
• Subjects: Machine learning -- Convolutional neural networks -- Artificial intelligence -- Forensics -- Microscopy -- Sperm detection; Forensic genetics -- Periodicals; Génétique légale -- Périodiques; Forensic genetics; Electronic journals; Periodicals; 614.1
• DOI: 10.1016/j.fsigen.2021.102602
• Languages: English
• ISSNs: 1872-4973

Abstract

Abstract: Microscopic sperm detection is an important task in sexual assault cases. In some instances, the samples contain no or only low amounts of semen. Therefore, the biological material is transferred onto a glass slide and needs to be manually scanned using an optical microscope. This work can be very time consuming, especially when no spermatozoa is present. In such a case, the result needs to be validated. In this article we show how convolutional neural networks can perform this task and how they can reduce the scanning time by locating the sperm cells on images taken under the microscope. For this purpose, we trained a VGG19 network and a VGG19 variation with 1942 images, some containing sperm cells and some not. Highlights: The detection of spermatocytes on optical microscopy images was automated using deep convolutional networks. By using class activation mapping the features relevant for classification are highlighted on each image. The accuracy of sperm detection was 95%, suggesting that the proposed method is feasible for the task.