The effect of data diversity on the performance of deep learning models for predicting early gastric cancer under endoscopy

作者
Conghui Shi,Jia Li,Lianlian Wu
标识
DOI:10.55976/jdh.1202214319-24
摘要

Aims To explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy. Methods Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models were constructed, which were respectively CNN 1, CNN 2, and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3 respectively), and their performance on each test set was respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real-time. Results On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp), and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052), and 94.60% respectively. The Acc, Sn, Sp, and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71), and 90.93% respectively. The Acc, Sn, Sp, and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123), 94.89% respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn, and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138), and 94.44% (17/18) respectively. Conclusions The deep learning model with the most diverse training data has the best diagnostic effect.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
共享精神应助yplsw90采纳,获得10
2秒前
3秒前
务实映之完成签到,获得积分10
3秒前
李爱国应助二等饼干采纳,获得10
3秒前
dx3906完成签到,获得积分20
4秒前
Ava应助Baylin采纳,获得10
4秒前
Shellbeaze发布了新的文献求助30
7秒前
田様应助shihun采纳,获得10
9秒前
淡然的寻雪完成签到,获得积分10
9秒前
上官若男应助研友_5Zl4VZ采纳,获得10
9秒前
10秒前
10秒前
10秒前
科研通AI6.4应助辣椒油采纳,获得10
11秒前
lebrongsy完成签到,获得积分10
12秒前
刘克发布了新的文献求助10
13秒前
Tony121发布了新的文献求助10
14秒前
YQQ发布了新的文献求助10
14秒前
辣椒油完成签到,获得积分10
16秒前
18秒前
杨乐完成签到,获得积分10
18秒前
可爱的函函应助Shellbeaze采纳,获得10
19秒前
20秒前
21秒前
22秒前
JamesPei应助清脆冰岚采纳,获得10
22秒前
23秒前
23秒前
酷酷的思萱完成签到 ,获得积分10
24秒前
24秒前
二等饼干发布了新的文献求助10
26秒前
晨晨晨完成签到,获得积分10
26秒前
Jasper应助add采纳,获得10
27秒前
研友_5Zl4VZ发布了新的文献求助10
27秒前
珊明治完成签到,获得积分10
27秒前
海洋发布了新的文献求助10
28秒前
忆_完成签到 ,获得积分10
29秒前
29秒前
温暖山晴完成签到,获得积分10
30秒前
ALALAL发布了新的文献求助30
32秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
China Pluperfect I: Epistemology of Past and Outside in Chinese Art 520
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Cosmos as Art Object: Studies in Plato's Timaeus and Other Dialogues 500
What is the Future of Psychotherapy in Digital Age? Technology, AI Bots, and Psychotherapy after Covid 444
Management and the Arts 310
Teaching Social and Emotional Learning in Physical Education 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7635929
求助须知:如何正确求助?哪些是违规求助? 9209864
关于积分的说明 19753841
捐赠科研通 7203694
什么是DOI,文献DOI怎么找? 3275325
关于科研通互助平台的介绍 2437151
邀请新用户注册赠送积分活动 2272434