CIS-Net: An End-to-end Chromosome Instance Segmentation Method Based on Disturbance Features Deactivation and Strengthened Disparity

Yulin Tan, Xing Wu, Chengliang Wang, Zailin Yang, Longrong Ran, Yao Liu

Abstract: Chromosomes are the carriers of human genetic information. Abnormal numbers of chromosomes can cause a variety of diseases. Karyotype analysis is an important means to assist in the diagnosis of chromosome abnormalities. Current deep learning-based karyotype analysis methods first segment single chromosomes on metaphase images and then classify each single chromosome. There are two problems with these methods. First, large intra-class differences and small interclass differences of chromosomes can easily lead to classification errors. Second, chromosome segmentation and classification are independent of each other, making overall optimization impossible. Therefore, we proposed CIS-Net. Disturbance Features Deactivation Module(DFDM) is first designed to improve the model’s key feature selection capabilities; then Strengthened Disparity Loss(SD Loss) is designed to enhance the ability to distinguish easily confused chromosome classes. Meanwhile, we define chromosome karyotype analysis as a 24-class instance segmentation problem, realizing end-to-end chromosome segmentation and classification on the whole metaphase image. Experiments on the AutoKary2022 dataset demonstrate that CISNet performs well compared to existing models, achieving the best mAP of 90.7%.