JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection (2022-03-01T00:00:00.000000Z)

TL;DR

A novel method, named JOINED, for prior guided multi-task learning for joint OD/OC segmentation and fovea detection, which outperforms existing state-of-the-art approaches on the publicly-available GAMMA, PALM, and REFUGE datasets of fundus images.

Abstract

Fundus photography has been routinely used to document the presence and severity of various retinal degenerative diseases such as age-related macula degeneration, glaucoma, and diabetic retinopathy, for which the fovea, optic disc (OD), and optic cup (OC) are important anatomical landmarks. Identification of those anatomical landmarks is of great clinical importance. However, the presence of lesions, drusen, and other abnormalities during retinal degeneration severely complicates automatic landmark detection and segmentation. Most existing works treat the identification of each landmark as a single task and typically do not make use of any clinical prior information. In this paper, we present a novel method, named JOINED, for prior guided multi-task learning for joint OD/OC segmentation and fovea detection. An auxiliary branch for distance prediction, in addition to a segmentation branch and a detection branch, is constructed to effectively utilize the distance information from each image pixel to landmarks of interest. Our proposed JOINED pipeline consists of a coarse stage and a fine stage. At the coarse stage, we obtain the OD/OC coarse segmentation and the heatmap localization of fovea through a joint segmentation and detection module. Afterwards, we crop the regions of interest for subsequent fine processing and use predictions obtained at the coarse stage as additional information for better performance and faster convergence. Experimental results reveal that our proposed JOINED outperforms existing state-of-the-art approaches on the publicly-available GAMMA, PALM, and REFUGE datasets of fundus images. Furthermore, JOINED ranked the 5th on the OD/OC segmentation and fovea detection tasks in the GAMMA challenge hosted by the MICCAI2021 workshop OMIA8.

References32 items

GAMMA Challenge: Glaucoma grAding from Multi-Modality imAges

BSDA-Net: A Boundary Shape and Distance Aware Joint Learning Framework for Segmenting and Classifying OCTA Images

Medical Image Segmentation using Squeeze-and-Expansion Transformers

Prior Guided Fundus Image Quality Enhancement Via Contrastive Learning

Robust Segmentation of Optic Disc and Cup from Fundus Images Using Deep Neural Networks

SESV: Accurate Medical Image Segmentation by Predicting and Correcting Errors

Joint disc and cup segmentation based on recurrent fully convolutional network

A Review on the optic disc and optic cup segmentation and classification approaches over retinal fundus images for detection of glaucoma

Efficient and robust optic disc detection and fovea localization using region proposal network and cascaded network

ResNeSt: Split-Attention Networks

Unsupervised Learning of Landmarks based on Inter-Intra Subject Consistencies

REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset

A Pixel-Wise Distance Regression Approach for Joint Retinal Optical Disc and Fovea Detection

Enhanced Optic Disk and Cup Segmentation with Glaucoma Screening from Fundus Images using Position encoded CNNs

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

Attention U-Net: Learning Where to Look for the Pancreas

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation

Blood vessel inpainting based technique for efficient localization and segmentation of optic disc in digital fundus images

Optic Disc and Optic Cup Segmentation Methodologies for Glaucoma Image Detection: A Survey

U-Net: Convolutional Networks for Biomedical Image Segmentation

Locating the Optic Disc in Retinal Images

Ranking of optic disc variables for detection of glaucomatous optic nerve damage.

FARGO: A Joint Framework for FAZ and RV Segmentation from OCTA Images

FundusPosNet: A deep learning driven heatmap regression model for the joint localization of optic disc and fovea centers in color fundus images

Optic Disc, Cup and Fovea Detection from Retinal Images Using U-Net++ with EfficientNet Encoder

PALM The pathologic myopia (PALM)3 dataset were provided by the ISBI

SEGMENTATION OF OPTIC DISC IN FUNDUS IMAGES