Classification of Findings with Localized Lesions in Fundoscopic Images using a Regionally Guided CNN

11/02/2018
by   Jaemin Son, et al.
6

Fundoscopic images are often investigated by ophthalmologists to spot abnormal lesions to make diagnoses. Recent successes of convolutional neural networks are confined to diagnoses of few diseases without proper localization of lesion. In this paper, we propose an efficient annotation method for localizing lesions and a CNN architecture that can classify an individual finding and localize the lesions at the same time. Also, we introduce a new loss function to guide the network to learn meaningful patterns with the guidance of the regional annotations. In experiments, we demonstrate that our network performed better than the widely used network and the guidance loss helps achieve higher AUROC up to 4.1

READ FULL TEXT

page 2

page 7

research
06/25/2018

3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection

Detecting lesions from computed tomography (CT) scans is an important bu...
research
06/28/2019

Classification of glomerular hypercellularity using convolutional features and support vector machine

Glomeruli are histological structures of the kidney cortex formed by int...
research
11/02/2018

Ischemic Stroke Lesion Segmentation in CT Perfusion Scans using Pyramid Pooling and Focal Loss

We present a fully convolutional neural network for segmenting ischemic ...
research
07/10/2020

Evaluation of Big Data based CNN Models in Classification of Skin Lesions with Melanoma

This chapter presents a methodology for diagnosis of pigmented skin lesi...
research
07/05/2021

Automated age-related macular degeneration area estimation – first results

This work aims to research an automatic method for detecting Age-related...
research
11/29/2017

Detection-aided liver lesion segmentation using deep learning

A fully automatic technique for segmenting the liver and localizing its ...
research
01/26/2020

Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives

Deep learning has proven to be an essential tool for medical image analy...

Please sign up or login with your details

Forgot password? Click here to reset