DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge

Abstract

Chromosome classification is an important but difficult and tedious task in karyotyping. Previous methods only classify manually segmented single chromosome, which is far from clinical practice. In this work, we propose a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image. We firstly introduce the Additive Angular Margin Loss to enhance the discriminative power of model. To alleviate batch effects, we transform decision boundary of each class case-by-case through a siamese network which make full use of prior knowledges that chromosomes usually appear in pairs. Furthermore, we take the clinically seven group criterion as a prior knowledge and design an additional Group Inner-Adjacency Loss to further reduce inter-class similarities. 3390 metaphase images from clinical laboratory are collected and labelled to evaluate the performance. Results show that the new design brings encouraging performance gains comparing to the state-of-the-art baselines.

This work is supported by a fund from another hospital. Only Li Xiao conceived the idea and supervised Chunlong Luo to complete the work, the data provider did not participate in the research process. Thus, the authorships and institutional information are not correct. After careful consideration, I decide to withdraw this preprint version

References in corpus (4)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
• DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks