Cell classification with worse-case boosting for intelligent cervical cancer screening

Boosting(机器学习) 分类器(UML) 概化理论 人工智能 计算机科学 机器学习 训练集 梯度升压 宫颈癌 模式识别(心理学) 医学 数学 统计 癌症 随机森林 内科学
作者
Youyi Song,Jing Zou,Kup‐Sze Choi,Baiying Lei,Jing Qin
出处
期刊:Medical Image Analysis [Elsevier]
卷期号:91: 103014-103014
标识
DOI:10.1016/j.media.2023.103014
摘要

Cell classification underpins intelligent cervical cancer screening, a cytology examination that effectively decreases both the morbidity and mortality of cervical cancer. This task, however, is rather challenging, mainly due to the difficulty of collecting a training dataset representative sufficiently of the unseen test data, as there are wide variations of cells' appearance and shape at different cancerous statuses. This difficulty makes the classifier, though trained properly, often classify wrongly for cells that are underrepresented by the training dataset, eventually leading to a wrong screening result. To address it, we propose a new learning algorithm, called worse-case boosting, for classifiers effectively learning from under-representative datasets in cervical cell classification. The key idea is to learn more from worse-case data for which the classifier has a larger gradient norm compared to other training data, so these data are more likely to correspond to underrepresented data, by dynamically assigning them more training iterations and larger loss weights for boosting the generalizability of the classifier on underrepresented data. We achieve this idea by sampling worse-case data per the gradient norm information and then enhancing their loss values to update the classifier. We demonstrate the effectiveness of this new learning algorithm on two publicly available cervical cell classification datasets (the two largest ones to the best of our knowledge), and positive results (4% accuracy improvement) yield in the extensive experiments. The source codes are available at: https://github.com/YouyiSong/Worse-Case-Boosting.
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
orixero应助聆听采纳,获得10
1秒前
木中一完成签到,获得积分10
2秒前
秦春歌完成签到,获得积分10
2秒前
wu发布了新的文献求助150
2秒前
2秒前
3秒前
星辰大海应助十七采纳,获得10
4秒前
4秒前
4秒前
5秒前
5秒前
Akim应助刘璞采纳,获得10
7秒前
fu完成签到,获得积分10
7秒前
liang发布了新的文献求助10
7秒前
Cathy完成签到,获得积分10
8秒前
Sepsp完成签到,获得积分10
8秒前
情怀应助九月采纳,获得10
10秒前
我爱学习发布了新的文献求助10
10秒前
Hi发布了新的文献求助10
10秒前
kitty发布了新的文献求助10
10秒前
天真的万天完成签到,获得积分10
12秒前
星辰大海应助刘璞采纳,获得10
12秒前
安详靖柏发布了新的文献求助10
12秒前
jpp发布了新的文献求助10
13秒前
15秒前
16秒前
16秒前
艾妮妮完成签到,获得积分10
16秒前
17秒前
圣光之翼发布了新的文献求助30
17秒前
科研通AI2S应助原野采纳,获得10
18秒前
艾妮妮发布了新的文献求助10
19秒前
额度无法完成签到,获得积分20
19秒前
无花果应助小丁采纳,获得10
20秒前
姜且完成签到 ,获得积分10
20秒前
十七完成签到,获得积分10
21秒前
宇文雅琴完成签到,获得积分10
22秒前
九月发布了新的文献求助10
22秒前
23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
Genera Insectorum: Mantodea, Fam. Mantidæ, Subfam. Hymenopodinæ (Classic Reprint) 800
Ethnicities: Media, Health, and Coping 700
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 3086831
求助须知:如何正确求助?哪些是违规求助? 2739532
关于积分的说明 7554956
捐赠科研通 2389212
什么是DOI,文献DOI怎么找? 1267053
科研通“疑难数据库(出版商)”最低求助积分说明 613616
版权声明 598592