Ph.D. student Qin Yulei's paper "Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks" (by Yulei Qin, Juan Wen, Hao Zheng, Xiaolin Huang, Jie Yang, Lingqian Wu, Ning Song, Yue-Min Zhu, and Guang -Zhong Yang) was accepted by IEEE Transactions on Medical Imaging, a top journal in the field of medical imaging.

       The paper proposes a chromosome classification recognition model called Varifocal-Net, which can simultaneously predict chromosome type and polarity. The method consists of three steps. The first step is to learn the global and local scale features through two networks, and the second step is to combine the learned feature construction categories and polarity classifiers. The final step is to use the allocation strategy to classify the chromosomes in each case based on the predicted probability results. The experimental results show that the proposed method exceeds the best existing algorithms and has the clinical practice value of assisted karyotype analysis.