Deep transfer learning from limited source for abdominal CT and MR image segmentation

人工智能 计算机科学 图像分割 学习迁移 计算机视觉 分割
作者
Chetana Krishnan,Elizabeth Schmidt,Ezinwanne Onuoha,Michal Mrug,Carlos Cárdenas,Hyung Min Kim
标识
DOI:10.1117/12.3006814
摘要

Medical image segmentation benefits from machine learning advancements, offering potential automation. Yet, accuracy depends on substantial annotated data and significant computing resources. Transfer learning addresses these challenges by leveraging a model's knowledge from one task for another with minor adjustments. The idea is to adapt learned features to new tasks, even with differing datasets but shared characteristics. Studies explore the impact of using large source datasets for limited target datasets. This investigation focuses on transferring knowledge from a limited source to enhance model versatility across various tasks. Our goal involved transferring knowledge from an advanced model trained on T2 weighted MR images related to Autosomal Dominant Polycystic Kidney Disease (ADPKD) for kidney and cyst segmentation (referred to as "Lsource"). This transfer was directed towards five distinct target datasets: CT liver, CT kidneys, CT spleen, MRI kidneys, and CT multimodal data (target datasets 1 through 5). The primary objective was to achieve accurate segmentation on these target datasets while saving time and computational resources. This approach is especially valuable when obtaining a substantial, labeled mouse PKD MRI target dataset is challenging, and the source dataset itself is resource-intensive. Using transfer learning from source 1 onto target sets 1 to 5 resulted in mean Dice Similarity Coefficients (DSCs) of 0.94±0.04, 0.97±0.02, 0.95±0.03, 0.96±0.01, 0.93±0.02, respectively. Similarly, employing source 2 yielded mean DSCs of 0.95±0.04, 0.96±0.02, 0.95±0.02, 0.96±0.02, and 0.93±0.02 for the same target sets. Despite variations in pathological conditions, image characteristics, and imaging modalities, the transfer learning approach produced DSC values comparable to the initial published outcomes. This accomplishment was achieved with reduced training requirements, faster convergence times, and decreased computational complexities.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
落后的瑾瑜完成签到,获得积分10
刚刚
PANYS完成签到 ,获得积分10
1秒前
yin完成签到,获得积分10
1秒前
bernie1023完成签到,获得积分10
3秒前
静默向上发布了新的文献求助10
3秒前
清秀龙猫完成签到 ,获得积分10
3秒前
4秒前
黄花完成签到 ,获得积分10
4秒前
5秒前
情殇完成签到,获得积分10
5秒前
YUNG完成签到 ,获得积分10
5秒前
byby完成签到,获得积分10
8秒前
yy14207发布了新的文献求助10
9秒前
橙子完成签到 ,获得积分10
10秒前
11秒前
Keyuuu30完成签到,获得积分0
11秒前
小小完成签到 ,获得积分10
12秒前
柠檬完成签到 ,获得积分10
13秒前
14秒前
14秒前
yuan完成签到,获得积分10
14秒前
lazy完成签到,获得积分20
15秒前
莫三颜完成签到,获得积分10
15秒前
小牛完成签到 ,获得积分10
15秒前
PANYS发布了新的文献求助10
16秒前
蠢宝贝完成签到,获得积分10
18秒前
18秒前
舒心的久完成签到 ,获得积分10
20秒前
时尚雨兰完成签到,获得积分10
24秒前
小超人完成签到 ,获得积分10
24秒前
Lyubb完成签到,获得积分10
25秒前
25秒前
肉片牛帅帅完成签到,获得积分10
25秒前
const完成签到,获得积分10
25秒前
半颗橙子完成签到 ,获得积分10
26秒前
贼吖完成签到 ,获得积分10
27秒前
无忧完成签到,获得积分20
28秒前
王二八发布了新的文献求助10
31秒前
古藤完成签到 ,获得积分10
31秒前
可靠之玉完成签到,获得积分10
31秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968578
求助须知:如何正确求助?哪些是违规求助? 3513393
关于积分的说明 11167478
捐赠科研通 3248836
什么是DOI,文献DOI怎么找? 1794499
邀请新用户注册赠送积分活动 875131
科研通“疑难数据库(出版商)”最低求助积分说明 804664