Incremental learning for exudate and hemorrhage segmentation on fundus images

Abstract Deep-learning-based segmentation methods have shown great success across many medical image applications. However, the custom training paradigms suffer from a well-known constraint of the requirement of pixel-wise annotations, which is labor-intensive, especially when they are required to learn new classes incrementally. Contemporary incremental learning focuses on dealing with catastrophic forgetting in image classification and object detection. However, this work aims to promote the performance of the current model to learn new classes with the help of the previous model in the context of incremental learning of instance segmentation. It enormously benefits the current model when the labeled data is limited because of the high labor intensity of manual labeling. In this paper, on the Diabetic Retinopathy (DR) lesion segmentation problem, a novel incremental segmentation paradigm is proposed to distill the knowledge of the previous model to improve the current model. Remarkably, we propose various approaches working on the class-based alignment of the probability maps of the current and the previous model, accounting for the difference between the background classes of the two models. The experimental evaluation of DR lesion segmentation shows the effectiveness of the proposed approaches.

[1]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[2]  Hamid Reza Pourreza,et al.  A novel method for retinal exudate segmentation using signal separation algorithm , 2016, Comput. Methods Programs Biomed..

[3]  Pietro Zanuttigh,et al.  Incremental Learning Techniques for Semantic Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[4]  Shuguang Cui,et al.  Learning Mutually Local-Global U-Nets For High-Resolution Retinal Lesion Segmentation In Fundus Images , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[5]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[6]  Elena Prokofyeva,et al.  Epidemiology of Major Eye Diseases Leading to Blindness in Europe: A Literature Review , 2011, Ophthalmic Research.

[7]  Nassir Navab,et al.  Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss , 2019, MICCAI.

[8]  Cordelia Schmid,et al.  End-to-End Incremental Learning , 2018, ECCV.

[9]  U. Rajendra Acharya,et al.  Computer-aided diagnosis of diabetic retinopathy: A review , 2013, Comput. Biol. Medicine.

[10]  Noel E. O'Connor,et al.  Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning , 2019, 2020 International Joint Conference on Neural Networks (IJCNN).

[11]  Rynson W. H. Lau,et al.  Geometry-Aware Distillation for Indoor Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ke Chen,et al.  Structured Knowledge Distillation for Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[15]  Samuel Rota Bulo,et al.  Modeling the Background for Incremental Learning in Semantic Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Changming Sun,et al.  Knowledge Adaptation for Efficient Semantic Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Cordelia Schmid,et al.  Incremental Learning of Object Detectors without Catastrophic Forgetting , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Gert Cauwenberghs,et al.  Incremental and Decremental Support Vector Machine Learning , 2000, NIPS.

[19]  J. Shaw,et al.  IDF Diabetes Atlas: Global estimates for the prevalence of diabetes for 2015 and 2040. , 2011, Diabetes research and clinical practice.

[20]  Yandong Guo,et al.  Incremental Classifier Learning with Generative Adversarial Networks , 2018, ArXiv.

[21]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[22]  Michael H. Goldbaum,et al.  Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels , 2003, IEEE Transactions on Medical Imaging.

[23]  Farida Cheriet,et al.  A Multitask Learning Architecture for Simultaneous Segmentation of Bright and Red Lesions in Fundus Images , 2018, MICCAI.