Tengfei Tan1, Zhilun Wang1, Hongwei Du2, Jinzhang Xu3, Bensheng Qiu1. 1. University of Science and Technology of China, No.96, JinZhai Road Baohe District, Hefei, 230026, Anhui, People's Republic of China. 2. University of Science and Technology of China, No.96, JinZhai Road Baohe District, Hefei, 230026, Anhui, People's Republic of China. duhw@ustc.edu.cn. 3. School of Electrical Engineering and Automation, Hefei University of Technology, Hefei, 230009, Anhui, People's Republic of China.
Abstract
PURPOSE: The morphological characteristics of retinal vessels are vital for the early diagnosis of pathological diseases such as diabetes and hypertension. However, the low contrast and complex morphology pose a challenge to automatic retinal vessel segmentation. To extract precise semantic features, more convolution and pooling operations are adopted, but some structural information is potentially ignored. METHODS: In the paper, we propose a novel lightweight pyramid network (LPN) fusing multi-scale features with spatial attention mechanism to preserve the structure information of retinal vessels. The pyramid hierarchy model is constructed to generate multi-scale representations, and its semantic features are strengthened with the introduction of the attention mechanism. The combination of multi-scale features contributes to its accurate prediction. RESULTS: The LPN is evaluated on benchmark datasets DRIVE, STARE and CHASE, and the results indicate its state-of-the-art performance (e.g., ACC of 97.09[Formula: see text]/97.49[Formula: see text]/97.48[Formula: see text], AUC of 98.79[Formula: see text]/99.01[Formula: see text]/98.91[Formula: see text] on the DRIVE, STARE and CHASE datasets, respectively). The robustness and generalization ability of the LPN are further proved in cross-training experiment. CONCLUSION: The visualization experiment reveals the semantic gap between various scales of the pyramid and verifies the effectiveness of the attention mechanism, which provide a potential basis for the pyramid hierarchy model in multi-scale vessel segmentation task. Furthermore, the number of model parameters is greatly reduced.
PURPOSE: The morphological characteristics of retinal vessels are vital for the early diagnosis of pathological diseases such as diabetes and hypertension. However, the low contrast and complex morphology pose a challenge to automatic retinal vessel segmentation. To extract precise semantic features, more convolution and pooling operations are adopted, but some structural information is potentially ignored. METHODS: In the paper, we propose a novel lightweight pyramid network (LPN) fusing multi-scale features with spatial attention mechanism to preserve the structure information of retinal vessels. The pyramid hierarchy model is constructed to generate multi-scale representations, and its semantic features are strengthened with the introduction of the attention mechanism. The combination of multi-scale features contributes to its accurate prediction. RESULTS: The LPN is evaluated on benchmark datasets DRIVE, STARE and CHASE, and the results indicate its state-of-the-art performance (e.g., ACC of 97.09[Formula: see text]/97.49[Formula: see text]/97.48[Formula: see text], AUC of 98.79[Formula: see text]/99.01[Formula: see text]/98.91[Formula: see text] on the DRIVE, STARE and CHASE datasets, respectively). The robustness and generalization ability of the LPN are further proved in cross-training experiment. CONCLUSION: The visualization experiment reveals the semantic gap between various scales of the pyramid and verifies the effectiveness of the attention mechanism, which provide a potential basis for the pyramid hierarchy model in multi-scale vessel segmentation task. Furthermore, the number of model parameters is greatly reduced.
Authors: Liang-Chieh Chen; George Papandreou; Iasonas Kokkinos; Kevin Murphy; Alan L Yuille Journal: IEEE Trans Pattern Anal Mach Intell Date: 2017-04-27 Impact factor: 6.226
Authors: Isabel N Figueiredo; Susana Moura; Júlio S Neves; Luís Pinto; Sunil Kumar; Carlos M Oliveira; João D Ramos Journal: Comput Biol Med Date: 2016-09-26 Impact factor: 4.589
Authors: Muhammad Moazam Fraz; Paolo Remagnino; Andreas Hoppe; Bunyarit Uyyanonvara; Alicja R Rudnicka; Christopher G Owen; Sarah A Barman Journal: IEEE Trans Biomed Eng Date: 2012-06-22 Impact factor: 4.538