Semi-supervised Classification of Chest Radiographs

Pooch, Eduardo; Ballester, Pedro; Barros, Rodrigo C.

doi:10.1007/978-3-030-61166-8_19

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In medical imaging, Hansen et al 16 explore MixMatch in two distinct medical imaging domains as skin lesion diagnosis and lung cancer prediction. Pooch et al 17 evaluate the performance of different methods including pseudo-labeling, Mean Teacher, 18 Unsupervised Data Augmentation (UDA), 19 MixMatch 14 and FixMatch 15 in a chest radiography classification task.…”

Section: Introductionmentioning

confidence: 99%

Deep semi-supervised and self-supervised learning for diabetic retinopathy detection

Arrieta

Perdomo²,

González³

2023

18th International Symposium on Medical Information Processing and Analysis

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is one of the leading causes of blindness in the working-age population of developed countries, caused by a side effect of diabetes that reduces the blood supply to the retina. Deep neural networks have been widely used in automated systems for DR classification on eye fundus images. However, these models need a large number of annotated images. In the medical domain, annotations from experts are costly, tedious, and time-consuming; as a result, a limited number of annotated images are available. This paper presents a semi-supervised method that leverages unlabeled images and labeled ones to train a model that detects diabetic retinopathy. The proposed method uses unsupervised pretraining via self-supervised learning followed by supervised fine-tuning with a small set of labeled images and knowledge distillation to increase the performance in a classification task. This method was evaluated on the EyePACS test and Messidor-2 dataset achieving 0.94 and 0.89 AUC respectively using only 2% of EyePACS train labeled images.

show abstract

Section: Introductionmentioning

confidence: 99%