基于数字乳腺断层合成数据集的肿瘤分割深度学习模型对比分析。

Cristina Alfaro Vergara, Nicolás Araya Caro, Domingo Mery Quiroz, Claudia Prieto Vasquez
{"title":"基于数字乳腺断层合成数据集的肿瘤分割深度学习模型对比分析。","authors":"Cristina Alfaro Vergara, Nicolás Araya Caro, Domingo Mery Quiroz, Claudia Prieto Vasquez","doi":"10.1007/s10278-025-01626-z","DOIUrl":null,"url":null,"abstract":"<p><p>The scarcity of publicly available digital breast tomosynthesis (DBT) datasets significantly limits the development of robust deep learning (DL) models for breast tumor segmentation. In this exploratory proof-of-concept study, we assess the viability of in silico-generated DBT data as a training source for tumor segmentation. A dataset of 230 two-dimensional (2D) regions of interest (ROIs) derived from FDA-cleared software and encompassing a spectrum of breast densities and tumor complexities, was used to train 13 DL models, including U-Net, FCN, DeepLabv3, and DeepLabv3 + architectures. Each model was trained either from scratch or fine-tuned using COCO-pretrained weights (ResNet50/101 backbones). Performance was evaluated using F1-score, intersection over union (IoU), precision, and recall. Among all models, U-Net trained from scratch and DeepLabv3 + fine-tuned with ResNet50 achieved the highest and most consistent results (F1-scores of 82.52% and 84.98%, and per-image IoUs of 78.49% and 83.77%, respectively). No statistically significant differences were found using the Wilcoxon signed-rank test and post hoc Bonferroni correction (α > 0.0042). To evaluate generalization across domains, the baseline U-Net model was retrained from scratch on a hybrid dataset combining in silico and real-world DBT ROIs, yielding promising results (F1-score of 79%). Despite the domain shift, these findings support the utility of in silico DBT as a complementary resource for training and benchmarking DL models, particularly in data-limited environments. This study provides foundational experimental evidence for integrating computationally generated in silico data into AI-based DBT tumor segmentation research workflows.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"In Silico Digital Breast Tomosynthesis Dataset for the Comparative Analysis of Deep Learning Models in Tumor Segmentation.\",\"authors\":\"Cristina Alfaro Vergara, Nicolás Araya Caro, Domingo Mery Quiroz, Claudia Prieto Vasquez\",\"doi\":\"10.1007/s10278-025-01626-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The scarcity of publicly available digital breast tomosynthesis (DBT) datasets significantly limits the development of robust deep learning (DL) models for breast tumor segmentation. In this exploratory proof-of-concept study, we assess the viability of in silico-generated DBT data as a training source for tumor segmentation. A dataset of 230 two-dimensional (2D) regions of interest (ROIs) derived from FDA-cleared software and encompassing a spectrum of breast densities and tumor complexities, was used to train 13 DL models, including U-Net, FCN, DeepLabv3, and DeepLabv3 + architectures. Each model was trained either from scratch or fine-tuned using COCO-pretrained weights (ResNet50/101 backbones). Performance was evaluated using F1-score, intersection over union (IoU), precision, and recall. Among all models, U-Net trained from scratch and DeepLabv3 + fine-tuned with ResNet50 achieved the highest and most consistent results (F1-scores of 82.52% and 84.98%, and per-image IoUs of 78.49% and 83.77%, respectively). No statistically significant differences were found using the Wilcoxon signed-rank test and post hoc Bonferroni correction (α > 0.0042). To evaluate generalization across domains, the baseline U-Net model was retrained from scratch on a hybrid dataset combining in silico and real-world DBT ROIs, yielding promising results (F1-score of 79%). Despite the domain shift, these findings support the utility of in silico DBT as a complementary resource for training and benchmarking DL models, particularly in data-limited environments. This study provides foundational experimental evidence for integrating computationally generated in silico data into AI-based DBT tumor segmentation research workflows.</p>\",\"PeriodicalId\":516858,\"journal\":{\"name\":\"Journal of imaging informatics in medicine\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-08-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of imaging informatics in medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s10278-025-01626-z\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of imaging informatics in medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10278-025-01626-z","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

公开可用的数字乳腺断层合成(DBT)数据集的稀缺性极大地限制了用于乳腺肿瘤分割的鲁棒深度学习(DL)模型的发展。在这个探索性的概念验证研究中,我们评估了在硅中生成的DBT数据作为肿瘤分割的训练源的可行性。由230个二维感兴趣区域(roi)组成的数据集来自fda批准的软件,包含乳腺密度和肿瘤复杂性的谱,用于训练13个深度学习模型,包括U-Net、FCN、DeepLabv3和DeepLabv3 +架构。每个模型要么从零开始训练,要么使用coco预训练的权重(ResNet50/101主干)进行微调。性能评估使用f1评分,交叉优于联合(IoU),精度和召回率。在所有模型中,从头开始训练的U-Net和使用ResNet50进行微调的DeepLabv3 +获得了最高和最一致的结果(f1得分分别为82.52%和84.98%,每张图像IoUs分别为78.49%和83.77%)。经Wilcoxon符号秩检验和事后Bonferroni校正(α > 0.0042),两组间差异无统计学意义。为了评估跨域的泛化,基线U-Net模型在结合了计算机和现实DBT roi的混合数据集上从零开始重新训练,产生了有希望的结果(f1得分为79%)。尽管领域发生了变化,但这些发现支持了DBT作为DL模型训练和基准测试的补充资源的实用性,特别是在数据有限的环境中。本研究为将计算机生成的数据集成到基于人工智能的DBT肿瘤分割研究工作流程中提供了基础实验证据。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
In Silico Digital Breast Tomosynthesis Dataset for the Comparative Analysis of Deep Learning Models in Tumor Segmentation.

The scarcity of publicly available digital breast tomosynthesis (DBT) datasets significantly limits the development of robust deep learning (DL) models for breast tumor segmentation. In this exploratory proof-of-concept study, we assess the viability of in silico-generated DBT data as a training source for tumor segmentation. A dataset of 230 two-dimensional (2D) regions of interest (ROIs) derived from FDA-cleared software and encompassing a spectrum of breast densities and tumor complexities, was used to train 13 DL models, including U-Net, FCN, DeepLabv3, and DeepLabv3 + architectures. Each model was trained either from scratch or fine-tuned using COCO-pretrained weights (ResNet50/101 backbones). Performance was evaluated using F1-score, intersection over union (IoU), precision, and recall. Among all models, U-Net trained from scratch and DeepLabv3 + fine-tuned with ResNet50 achieved the highest and most consistent results (F1-scores of 82.52% and 84.98%, and per-image IoUs of 78.49% and 83.77%, respectively). No statistically significant differences were found using the Wilcoxon signed-rank test and post hoc Bonferroni correction (α > 0.0042). To evaluate generalization across domains, the baseline U-Net model was retrained from scratch on a hybrid dataset combining in silico and real-world DBT ROIs, yielding promising results (F1-score of 79%). Despite the domain shift, these findings support the utility of in silico DBT as a complementary resource for training and benchmarking DL models, particularly in data-limited environments. This study provides foundational experimental evidence for integrating computationally generated in silico data into AI-based DBT tumor segmentation research workflows.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信