Building Disease Detection Algorithms with Very Small Numbers of Positive Samples
원문 초록
Although deep learning can provide promising results in medical image analysis, the lack of very large annotated datasets confines its full potential. Furthermore, limited positive samples also create unbalanced datasets which limit the true positive rates of trained models. As unbalanced datasets are mostly unavoidable, it is greatly beneficial if we can extract useful knowledge from negative samples to improve classification accuracy on limited positive samples. To this end, we propose a new strategy for building medical image analysis pipelines that target disease detection. We train a discriminative segmentation model only on normal images to provide a source of knowledge to be transferred to a disease detection classifier. We show that using the feature maps of a trained segmentation network, deviations from normal anatomy can be learned by a two-class classification network on an extremely unbalanced training dataset with as little as one positive for 17 negative samples. We demonstrate that even though the segmentation network is only trained on normal cardiac computed tomography images, the resulting feature maps can be used to detect pericardial effusion and cardiac septal defects with two-class convolutional classification networks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
MedCAM-OsteoCls: Medical Context Aware Multimodal Classification of Knee Osteoarthritis
Chronic Obstructive Pulmonary Disease Severity Classification using lung sound
Bio-Inspired Feature Selection in Brain Disease Detection via an Improved Sparrow Search Algorithm
Crosslink-Net: Double-Branch Encoder Network via Fusing Vertical and Horizontal Convolutions for Medical Image Segmentation
Deep Learning for Musical Form: Recognition and Analysis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.