Exploratory Training for Universal Lesion Detection: Enhancing Lesion Mining Quality Through Temporal Verification

计算机科学 质量(理念) 人工智能 病变 模式识别(心理学) 医学 病理 认识论 哲学
作者
Xiaoyu Bai,Geng Chen,Benteng Ma,Changyang Li,Jingfeng Zhang,Yong Xia
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:: 1-13
标识
DOI:10.1109/jbhi.2024.3417274
摘要

Universal lesion detection (ULD) has great value in clinical practice as it can detect various lesions across multiple organs. Deep learning-based detectors have great potential but require high-quality annotated training data. In practice, due to cost, expertise requirements, and the diverse nature of lesions, incomplete annotations are often encountered. Directly training ULD detectors under this condition can yield suboptimal results. Leading pseudo-label methods rely on a dynamic lesion-mining mechanism operating at the mini-batch level to address the issue of incomplete annotations. However, the quality of mined lesions in this approach is inconsistent across different iterations, potentially limiting performance enhancement. Inspired by the observation that deep models learn concepts with increasing complexity, we propose an innovative exploratory-training-based ULD (ET-ULD) method to assess the reliability of mined lesions over time. Specifically, we employ a teacher-student detection model, the teacher model is used to mine suspicious lesions, which are combined with incomplete annotations to train the student model. On top of that, we design a bounding-box bank to record the mining timestamps. Each image is trained in several rounds, allowing us to get a sequence of timestamps for the mined lesions. If a mined lesion consistently appears in the timestamp sequence, it is likely to be a true lesion, otherwise, it may just be a noise. This serves as a crucial criterion for selecting reliable mined lesions for subsequent retraining. Our experimental results confirm the effectiveness of ET-ULD, showcasing its ability to surpass existing state-of-the-art methods on two distinct lesion image datasets. Notably, on the DeepLesion dataset, ET-ULD achieved a significant enhancement, outperforming the previous leading method by 5.4% in Average Precision (AP), thus demonstrating its superior performance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
lin发布了新的文献求助10
1秒前
无奈秋荷发布了新的文献求助10
1秒前
123完成签到,获得积分10
1秒前
风起人散完成签到,获得积分10
1秒前
无辜念文完成签到,获得积分10
1秒前
咖飞发布了新的文献求助10
2秒前
5秒前
熊猫发布了新的文献求助10
5秒前
淡定的十七完成签到 ,获得积分10
5秒前
xuhang完成签到,获得积分10
6秒前
宁少爷完成签到,获得积分10
7秒前
Fn完成签到 ,获得积分10
8秒前
10秒前
10秒前
学术混子发布了新的文献求助10
10秒前
王婷完成签到,获得积分10
11秒前
沉静青寒完成签到,获得积分10
11秒前
科目三应助lin采纳,获得10
11秒前
11秒前
可爱茹嫣完成签到,获得积分10
11秒前
烂瞓完成签到 ,获得积分10
12秒前
13秒前
无奈秋荷完成签到,获得积分20
13秒前
淡定的十七关注了科研通微信公众号
13秒前
阔达的无剑完成签到,获得积分10
15秒前
CWNU_HAN应助overThat采纳,获得30
15秒前
88发布了新的文献求助10
16秒前
机械腾完成签到,获得积分10
18秒前
学术混子完成签到,获得积分10
18秒前
科研小裴完成签到 ,获得积分10
18秒前
8282868完成签到,获得积分10
20秒前
cmh完成签到 ,获得积分10
21秒前
ZL完成签到 ,获得积分10
22秒前
英勇靖雁完成签到,获得积分20
22秒前
22秒前
hezi完成签到,获得积分10
24秒前
24秒前
哎哟很烦发布了新的文献求助10
25秒前
不要引力完成签到,获得积分10
26秒前
不要引力发布了新的文献求助10
28秒前
高分求助中
The ACS Guide to Scholarly Communication 2500
Sustainability in Tides Chemistry 2000
Pharmacogenomics: Applications to Patient Care, Third Edition 1000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
Genera Insectorum: Mantodea, Fam. Mantidæ, Subfam. Hymenopodinæ (Classic Reprint) 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3085525
求助须知:如何正确求助?哪些是违规求助? 2738394
关于积分的说明 7549581
捐赠科研通 2388186
什么是DOI,文献DOI怎么找? 1266339
科研通“疑难数据库(出版商)”最低求助积分说明 613430
版权声明 598591