Mini Lesions Detection on Diabetic Retinopathy Images via Large Scale CNN Features

TL;DR

This paper introduces a novel large-scale feature pyramid network (LFPN) for detecting tiny lesions in diabetic retinopathy fundus images, improving early diagnosis accuracy by addressing the challenges of small lesion size.

Contribution

The paper proposes a large-size feature pyramid network (LFPN) and an effective region proposal strategy specifically designed for mini lesion detection in fundus images, outperforming existing methods.

Findings

LFPN outperforms traditional FPN and Faster RCNN in lesion detection accuracy.

The method effectively detects small lesions, aiding early DR diagnosis.

Enhanced sensitivity in lesion localization improves DR severity assessment.

Abstract

Diabetic retinopathy (DR) is a diabetes complication that affects eyes. DR is a primary cause of blindness in working-age people and it is estimated that 3 to 4 million people with diabetes are blinded by DR every year worldwide. Early diagnosis have been considered an effective way to mitigate such problem. The ultimate goal of our research is to develop novel machine learning techniques to analyze the DR images generated by the fundus camera for automatically DR diagnosis. In this paper, we focus on identifying small lesions on DR fundus images. The results from our analysis, which include the lesion category and their exact locations in the image, can be used to facilitate the determination of DR severity (indicated by DR stages). Different from traditional object detection for natural images, lesion detection for fundus images have unique challenges. Specifically, the size of a lesion instance is usually very small, compared with the original resolution of the fundus images, making them diffcult to be detected. We analyze the lesion-vs-image scale carefully and propose a large-size feature pyramid network (LFPN) to preserve more image details for mini lesion instance detection. Our method includes an effective region proposal strategy to increase the sensitivity. The experimental results show that our proposed method is superior to the original feature pyramid network (FPN) method and Faster RCNN.