Chromosome Siamese Abnormality Detector - Detection of structural chromosomal abnormalities using Siamese architecture
Highly performing automatic detection of structural chromosomal abnormalities using Siamese architecture
The detection of structural chromosomal abnormalities (SCA) is crucial for the diagnosis, prognosis and management of many genetic diseases and cancers. This detection, done by highly qualified medical experts, is tedious and time-consuming. We propose a highly performing and intelligent method to assist cytogeneticists to screen for SCA. Each chromosome is present in two copies that make up a pair of chromosomes. Usually, SCA are present in only one copy of the pair. Convolutional neural networks (CNN) with a Siamese architecture are particularly relevant for evaluating similarities between two images, which is why we intended to use this method to detect abnormalities within copies of chromosomes. As a proof-of-concept, we first focused on a deletion occurring on chromosome 5 (del(5q)) observed in hematological malignancies. Using our dataset, we conducted several experiments without and with data augmentation on seven popular CNN models. Overall, the performances obtained were very relevant for detecting deletions, particularly with the Xception and InceptionResNetV2 models achieving 97.50% and 97.01% of the F1 score, respectively. We additionally demonstrated that these models successfully recognized another SCA, inversion inv(3), which is one of the most difficult SCA to detect. This experiment improved when the training was applied on inversion inv(3) dataset, achieving 98.65% of accuracy and 94.82% of F1 score. The technique that we propose in this paper is the first highly performing method based on Siamese architecture that allows the detection of SCA.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent