TY  - JOUR
PY  - 2019//
TI  - Digital whole-slide image analysis for automated diatom test in forensic cases of drowning using a convolutional neural network algorithm
JO  - Forensic science international
A1  - Zhou, Yuanyuan
A1  - Zhang, Ji
A1  - Huang, Jiao
A1  - Deng, Kaifei
A1  - Zhang, Jianhua
A1  - Qin, Zhiqiang
A1  - Wang, Zhenyuan
A1  - Zhang, Xiaofeng
A1  - Tuo, Ya
A1  - Chen, Liqin
A1  - Chen, Yijiu
A1  - Huang, Ping
SP  - e109922
EP  - e109922
VL  - 302
IS  - 
N2  - Diatom examinations have been widely used to perform drowning diagnosis in forensic practice. However, current methods for recognizing diatoms, which use light or electron microscopy, are time-consuming and laborious and often result in false positive or negative decisions. In this study, we demonstrated an artificial intelligence (AI)-based system to automatically identify diatoms in conjunction with a classical chemical digestion approach. By employing transfer learning and data augmentation methods, we trained convolutional neural network (CNN) models on thousands or tens of thousands of tiles from digital whole-slide images of diatom smears. The results showed that the trained model identified the regions containing diatoms in the tiles. In an independent test, where the slide samples were collected in forensic casework, the best CNN model demonstrated a performance competitive with those of 5 forensic pathologists with experience in diatom quantification. This pilot study paves the way for future intelligent diatom examinations; many efficient diatom extraction methods could be incorporated into our automated system.<br><br>Copyright © 2019 Elsevier B.V. All rights reserved.<p />  <p>Language: en</p>
LA  - en
SN  - 0379-0738
UR  - http://dx.doi.org/10.1016/j.forsciint.2019.109922
ID  - ref1
ER  -