Adversarial Multiscale Feature Learning Framework for Overlapping Chromosome Segmentation |
| |
Authors: | Liye Mei Yalan Yu Hui Shen Yueyun Weng Yan Liu Du Wang Sheng Liu Fuling Zhou Cheng Lei |
| |
Institution: | 1.The Institute of Technological Sciences, Wuhan University, Wuhan 430072, China; (L.M.); (Y.W.); (D.W.); (S.L.);2.The Department of Hematology, Zhongnan Hospital of Wuhan University, Wuhan 430071, China; (Y.Y.); (H.S.); (F.Z.);3.The Key Laboratory of Transients in Hydrolic Machinery of Ministry of Education, School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, China;4.The Alipay Tian Qian Security Lab., Beijing 100020, China; |
| |
Abstract: | Chromosome karyotype analysis is of great clinical importance in the diagnosis and treatment of diseases. Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis. However, the strip-shaped chromosomes easily overlap each other when imaged, significantly affecting the accuracy of the subsequent analysis and hindering the development of chromosome analysis instruments. In this paper, we present an adversarial, multiscale feature learning framework to improve the accuracy and adaptability of overlapping chromosome segmentation. We first adopt the nested U-shaped network with dense skip connections as the generator to explore the optimal representation of the chromosome images by exploiting multiscale features. Then we use the conditional generative adversarial network (cGAN) to generate images similar to the original ones; the training stability of the network is enhanced by applying the least-square GAN objective. Finally, we replace the common cross-entropy loss with the advanced Lovász-Softmax loss to improve the model’s optimization and accelerate the model’s convergence. Comparing with the established algorithms, the performance of our framework is proven superior by using public datasets in eight evaluation criteria, showing its great potential in overlapping chromosome segmentation. |
| |
Keywords: | overlapping chromosome segmentation conditional generative adversarial network nested U-shaped network multiscale feature learning Lová sz-Softmax |
|
|