PolypMixNet: Enhancing semi-supervised polyp segmentation with polyp-aware augmentation

计算机科学 分割 人工智能 一致性(知识库) 机器学习 水准点(测量) 结肠镜检查 模式识别(心理学) 结直肠癌 医学 癌症 大地测量学 内科学 地理
作者
Xiao Jia,Yutian Shen,Yang Jian-hong,Ran Song,Wei Zhang,Max Q.‐H. Meng,Joseph C. Liao,Lei Xing
出处
期刊:Computers in Biology and Medicine [Elsevier]
卷期号:170: 108006-108006 被引量:1
标识
DOI:10.1016/j.compbiomed.2024.108006
摘要

AI-assisted polyp segmentation in colonoscopy plays a crucial role in enabling prompt diagnosis and treatment of colorectal cancer. However, the lack of sufficient annotated data poses a significant challenge for supervised learning approaches. Existing semi-supervised learning methods also suffer from performance degradation, mainly due to task-specific characteristics, such as class imbalance in polyp segmentation. The purpose of this work is to develop an effective semi-supervised learning framework for accurate polyp segmentation in colonoscopy, addressing limited annotated data and class imbalance challenges. We proposed PolypMixNet, a semi-supervised framework, for colorectal polyp segmentation, utilizing novel augmentation techniques and a Mean Teacher architecture to improve model performance. PolypMixNet introduces the polyp-aware mixup (PolypMix) algorithm and incorporates dual-level consistency regularization. PolypMix addresses the class imbalance in colonoscopy datasets and enhances the diversity of training data. By performing a polyp-aware mixup on unlabeled samples, it generates mixed images with polyp context along with their artificial labels. A polyp-directed soft pseudo-labeling (PDSPL) mechanism was proposed to generate high-quality pseudo labels and eliminate the dilution of lesion features caused by mixup operations. To ensure consistency in the training phase, we introduce the PolypMix prediction consistency (PMPC) loss and PolypMix attention consistency (PMAC) loss, enforcing consistency at both image and feature levels. Code is available at https://github.com/YChienHung/PolypMix. PolypMixNet was evaluated on four public colonoscopy datasets, achieving 88.97% Dice and 88.85% mIoU on the benchmark dataset of Kvasir-SEG. In scenarios where the labeled training data is limited to 15%, PolypMixNet outperforms the state-of-the-art semi-supervised approaches with a 2.88-point improvement in Dice. It also shows the ability to reach performance comparable to the fully supervised counterpart. Additionally, we conducted extensive ablation studies to validate the effectiveness of each module and highlight the superiority of our proposed approach. PolypMixNet effectively addresses the challenges posed by limited annotated data and unbalanced class distributions in polyp segmentation. By leveraging unlabeled data and incorporating novel augmentation and consistency regularization techniques, our method achieves state-of-the-art performance. We believe that the insights and contributions presented in this work will pave the way for further advancements in semi-supervised polyp segmentation and inspire future research in the medical imaging domain.
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
刚刚
yyyyyyy发布了新的文献求助10
1秒前
AN发布了新的文献求助10
2秒前
will完成签到,获得积分10
2秒前
17835152738发布了新的文献求助10
2秒前
柠木关注了科研通微信公众号
3秒前
kento应助科研通管家采纳,获得100
7秒前
Owen应助科研通管家采纳,获得10
7秒前
情怀应助科研通管家采纳,获得10
7秒前
丘比特应助科研通管家采纳,获得10
8秒前
墨墨发布了新的文献求助10
9秒前
tangt糖糖完成签到,获得积分10
9秒前
左丘冥完成签到,获得积分10
10秒前
答案。完成签到 ,获得积分10
10秒前
10秒前
Tonnyjing应助yyyyyyy采纳,获得10
11秒前
11秒前
路人丨安完成签到,获得积分10
12秒前
goodesBright应助令莞采纳,获得10
12秒前
12秒前
13秒前
14秒前
田様应助左丘冥采纳,获得10
14秒前
15秒前
93发布了新的文献求助10
17秒前
xumodehudie完成签到 ,获得积分10
18秒前
19秒前
尛瞐慶成发布了新的文献求助10
20秒前
hj发布了新的文献求助10
21秒前
偶吼吼完成签到,获得积分10
21秒前
22秒前
22秒前
fifteen发布了新的文献求助10
22秒前
LSX完成签到,获得积分10
23秒前
内向的小凡完成签到,获得积分10
23秒前
yy完成签到,获得积分20
24秒前
25秒前
25秒前
重景完成签到 ,获得积分10
25秒前
Stove完成签到,获得积分10
26秒前
高分求助中
좌파는 어떻게 좌파가 됐나:한국 급진노동운동의 형성과 궤적 2500
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
CLSI EP47 Evaluation of Reagent Carryover Effects on Test Results, 1st Edition 800
Cognitive linguistics critical concepts in linguistics 800
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
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 3053642
求助须知:如何正确求助?哪些是违规求助? 2710842
关于积分的说明 7423746
捐赠科研通 2355391
什么是DOI,文献DOI怎么找? 1247143
科研通“疑难数据库(出版商)”最低求助积分说明 606239
版权声明 595992