A Deep Segmentation Network of Multi-Scale Feature Fusion Based on Attention Mechanism for IVOCT Lumen Contour

• Published in: IEEE/ACM transactions on computational biology and bioinformatics Vol. 18; no. 1; pp. 62 - 69
• Main Authors: Huang, Chenxi, Lan, Yisha, Xu, Gaowei, Zhai, Xiaojun, Wu, Jipeng, Lin, Fan, Zeng, Nianyin, Hong, Qingqi, Ng, E. Y. K., Peng, Yonghong, Chen, Fei, Zhang, Guokai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: attention mechanism; Blood Vessels - diagnostic imaging; Cardiovascular disease; Cardiovascular diseases; contour segmentation; Contours; Convolution; Coronary artery disease; Data mining; Databases, Factual; Deep Learning; Diagnostic systems; Electronic mail; Endovascular Procedures - methods; Entropy; Feature extraction; Heart; Heart diseases; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; IVOCT images; Medical imaging; Neural Networks, Computer; Residual network; Tomography, Optical Coherence - methods; Training; Working conditions
• ISSN: 1545-5963; 1557-9964; 1557-9964
• DOI: 10.1109/TCBB.2020.2973971

Recently, coronary heart disease has attracted more and more attention, where segmentation and analysis for vascular lumen contour are helpful for treatment. And intravascular optical coherence tomography (IVOCT) images are used to display lumen shapes in clinic. Thus, an automatic segmentation method for IVOCT lumen contour is necessary to reduce the doctors' workload while ensuring diagnostic accuracy. In this paper, we proposed a deep residual segmentation network of multi-scale feature fusion based on attention mechanism (RSM-Network, Residual Squeezed Multi-Scale Network) to segment the lumen contour in IVOCT images. Firstly, three different data augmentation methods including mirror level turnover, rotation and vertical flip are considered to expand the training set. Then in the proposed RSM-Network, U-Net is contained as the main body, considering its characteristic of accepting input images with any sizes. Meanwhile, the combination of residual network and attention mechanism is applied to improve the ability of global feature extraction and solve the vanishing gradient problem. Moreover, the pyramid feature extraction structure is introduced to enhance the learning ability for multi-scale features. Finally, in order to increase the matching degree between the actual output and expected output, the cross entropy loss function is also used. A series of metrics are presented to evaluate the performance of our proposed network and the experimental results demonstrate that the proposed RSM-Network can learn the contour details better, contributing to strong robustness and accuracy for IVOCT lumen contour segmentation.