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 哲学 认识论
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
1秒前
LQX2141完成签到 ,获得积分10
2秒前
4秒前
啦啦啦完成签到,获得积分10
4秒前
是个帅哥发布了新的文献求助10
5秒前
纯牛奶完成签到,获得积分20
6秒前
戴先森发布了新的文献求助10
6秒前
indec发布了新的文献求助10
7秒前
8秒前
满意沅发布了新的文献求助40
10秒前
是个帅哥完成签到,获得积分10
11秒前
yahonyoyoyo发布了新的文献求助10
14秒前
yyw发布了新的文献求助10
14秒前
852应助Crystal采纳,获得10
14秒前
小二郎应助corazon采纳,获得30
16秒前
充电宝应助GERRARD采纳,获得10
16秒前
Li发布了新的文献求助30
17秒前
不安青牛给潇洒毛的求助进行了留言
18秒前
飞跃完成签到 ,获得积分10
19秒前
能干的孤丝完成签到 ,获得积分10
19秒前
烂漫的静枫完成签到,获得积分10
19秒前
JamesPei应助liu采纳,获得10
19秒前
FashionBoy应助夕荀采纳,获得10
19秒前
Lumos发布了新的文献求助30
21秒前
Orange应助嘿嘿嘿采纳,获得10
21秒前
Geralt完成签到,获得积分10
23秒前
圈儿完成签到,获得积分10
24秒前
restudy68发布了新的文献求助10
25秒前
栗子应助奕初阳采纳,获得10
27秒前
思源应助瘦瘦达采纳,获得10
27秒前
vicky完成签到,获得积分10
27秒前
jiangchuansm完成签到,获得积分10
27秒前
宜醉宜游宜睡应助米月采纳,获得10
28秒前
30秒前
30秒前
30秒前
陈元元K发布了新的文献求助20
30秒前
小鱼发布了新的文献求助10
30秒前
indec完成签到,获得积分10
32秒前
32秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
юрские динозавры восточного забайкалья 800
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
Chen Hansheng: China’s Last Romantic Revolutionary 500
China's Relations With Japan 1945-83: The Role of Liao Chengzhi 400
Classics in Total Synthesis IV 400
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 3150133
求助须知:如何正确求助?哪些是违规求助? 2801290
关于积分的说明 7843877
捐赠科研通 2458770
什么是DOI,文献DOI怎么找? 1308652
科研通“疑难数据库(出版商)”最低求助积分说明 628556
版权声明 601721