TY - GEN
T1 - Learning to Address Intra-segment Misclassification in Retinal Imaging
AU - Zhou, Yukun
AU - Xu, Moucheng
AU - Hu, Yipeng
AU - Lin, Hongxiang
AU - Jacob, Joseph
AU - Keane, Pearse A.
AU - Alexander, Daniel C.
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity. Segmenting retinal blood vessels in retinal photographs is one such scenario, in which arteries and veins need to be identified and differentiated from each other and from the background. Intra-segment misclassification, i.e. veins classified as arteries or vice versa, frequently occurs when arteries and veins intersect, whereas in binary retinal vessel segmentation, error rates are much lower. We thus propose a new approach that decomposes multi-class segmentation into multiple binary, followed by a binary-to-multi-class fusion network. The network merges representations of artery, vein, and multi-class feature maps, each of which are supervised by expert vessel annotation in adversarial training. A skip-connection based merging process explicitly maintains class-specific gradients to avoid gradient vanishing in deep layers, to favor the discriminative features. The results show that, our model respectively improves F1-score by 4.4%, 5.1%, and 4.2% compared with three state-of-the-art deep learning based methods on DRIVE-AV, LES-AV, and HRF-AV data sets. Code: https://github.com/rmaphoh/Learning-AVSegmentation
AB - Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity. Segmenting retinal blood vessels in retinal photographs is one such scenario, in which arteries and veins need to be identified and differentiated from each other and from the background. Intra-segment misclassification, i.e. veins classified as arteries or vice versa, frequently occurs when arteries and veins intersect, whereas in binary retinal vessel segmentation, error rates are much lower. We thus propose a new approach that decomposes multi-class segmentation into multiple binary, followed by a binary-to-multi-class fusion network. The network merges representations of artery, vein, and multi-class feature maps, each of which are supervised by expert vessel annotation in adversarial training. A skip-connection based merging process explicitly maintains class-specific gradients to avoid gradient vanishing in deep layers, to favor the discriminative features. The results show that, our model respectively improves F1-score by 4.4%, 5.1%, and 4.2% compared with three state-of-the-art deep learning based methods on DRIVE-AV, LES-AV, and HRF-AV data sets. Code: https://github.com/rmaphoh/Learning-AVSegmentation
KW - Binary-to-multi-class fusion network
KW - Intra-segment misclassification
KW - Multi-class segmentation
KW - Retinal vessel
UR - https://www.scopus.com/pages/publications/85116496014
U2 - 10.1007/978-3-030-87193-2_46
DO - 10.1007/978-3-030-87193-2_46
M3 - 会议稿件
AN - SCOPUS:85116496014
SN - 9783030871925
T3 - Lecture Notes in Computer Science
SP - 482
EP - 492
BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 - 24th International Conference, Proceedings
A2 - de Bruijne, Marleen
A2 - de Bruijne, Marleen
A2 - Cattin, Philippe C.
A2 - Cotin, Stéphane
A2 - Padoy, Nicolas
A2 - Speidel, Stefanie
A2 - Zheng, Yefeng
A2 - Essert, Caroline
PB - Springer Science and Business Media Deutschland GmbH
T2 - 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021
Y2 - 27 September 2021 through 1 October 2021
ER -