Discrepancy-Based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images

Bai，Fan1; Xing，Xiaohan2; Shen，Yutian1; Ma，Han1; Meng，Max Q.H.1,3

10.1007/978-3-031-16452-1_3

2022

25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

0302-9743

1611-3349

978-3-031-16451-4

LECT NOTES ARTIF INT

13438 LNCS

24-34

SEP 18-22, 2022

null,Singapore,SINGAPORE

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Weakly supervised methods, such as class activation maps (CAM) based, have been applied to achieve bleeding segmentation with low annotation efforts in Wireless Capsule Endoscopy (WCE) images. However, the CAM labels tend to be extremely noisy, and there is an irreparable gap between CAM labels and ground truths for medical images. This paper proposes a new Discrepancy-basEd Active Learning (DEAL) approach to bridge the gap between CAMs and ground truths with a few annotations. Specifically, to liberate labor, we design a novel discrepancy decoder model and a CAMPUS (CAM, Pseudo-label and groUnd-truth Selection) criterion to replace the noisy CAMs with accurate model predictions and a few human labels. The discrepancy decoder model is trained with a unique scheme to generate standard, coarse and fine predictions. And the CAMPUS criterion is proposed to predict the gaps between CAMs and ground truths based on model divergence and CAM divergence. We evaluate our method on the WCE dataset and results show that our method outperforms the state-of-the-art active learning methods and reaches comparable performance to those trained with full annotated datasets with only 10% of the training data labeled. The source code is available at https://github.com/baifanxxx/DEAL.

Active learning Segmentation WCE images

Others

English

CPCI-S

National Key R&D program of China[2019YFB1312400] ; Hong Kong RGC CRF[C4063-18G] ; Hong Kong RGC GRF[14211420]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:000867418200003

2-s2.0-85139008873

Scopus

1.Department of Electronic Engineering,The Chinese University of Hong Kong,Shatin,Hong Kong
2.Department of Electrical Engineering,City University of Hong Kong,Kowloon,Hong Kong
3.Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,China

Bai，Fan,Xing，Xiaohan,Shen，Yutian,et al. Discrepancy-Based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:24-34.