Abstract
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as IMAGENET and PLACES. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious, laborious, and time consuming, but it also demands costly, specialty-oriented skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method to naturally integrate active learning and transfer learning (fine-tuning) into a single framework, which starts directly with a pre-trained CNN to seek “worthy” samples for annotation and gradually enhances the (fine-tuned) CNN via continual fine-tuning. We have evaluated our method using three distinct medical imaging applications, demonstrating that it can reduce annotation efforts by at least half compared with random selection.
Original language | English (US) |
---|---|
Article number | 101997 |
Journal | Medical image analysis |
Volume | 71 |
DOIs | |
State | Published - Jul 2021 |
Keywords
- Active learning
- Annotation cost reduction
- Computer-aided diagnosis
- Convolutional neural networks
- Medical image analysis
- Transfer learning
ASJC Scopus subject areas
- Radiological and Ultrasound Technology
- Radiology Nuclear Medicine and imaging
- Computer Vision and Pattern Recognition
- Health Informatics
- Computer Graphics and Computer-Aided Design