下载PDF
{"title":"Improving Computer-aided Detection for Digital Breast Tomosynthesis by Incorporating Temporal Change.","authors":"Yinhao Ren, Zisheng Liang, Jun Ge, Xiaoming Xu, Jonathan Go, Derek L Nguyen, Joseph Y Lo, Lars J Grimm","doi":"10.1148/ryai.230391","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To develop a deep learning algorithm that uses temporal information to improve the performance of a previously published framework of cancer lesion detection for digital breast tomosynthesis. Materials and Methods This retrospective study analyzed the current and the 1-year-prior Hologic digital breast tomosynthesis screening examinations from eight different institutions between 2016 and 2020. The dataset contained 973 cancer and 7123 noncancer cases. The front end of this algorithm was an existing deep learning framework that performed single-view lesion detection followed by ipsilateral view matching. For this study, PriorNet was implemented as a cascaded deep learning module that used the additional growth information to refine the final probability of malignancy. Data from seven of the eight sites were used for training and validation, while the eighth site was reserved for external testing. Model performance was evaluated using localization receiver operating characteristic curves. Results On the validation set, PriorNet showed an area under the receiver operating characteristic curve (AUC) of 0.931 (95% CI: 0.930, 0.931), which outperformed both baseline models using single-view detection (AUC, 0.892 [95% CI: 0.891, 0.892]; <i>P</i> < .001) and ipsilateral matching (AUC, 0.915 [95% CI: 0.914, 0.915]; <i>P</i> < .001). On the external test set, PriorNet achieved an AUC of 0.896 (95% CI: 0.885, 0.896), outperforming both baselines (AUC, 0.846 [95% CI: 0.846, 0.847]; <i>P</i> < .001 and AUC, 0.865 [95% CI: 0.865, 0.866]; <i>P</i> < .001, respectively). In the high sensitivity range of 0.9 to 1.0, the partial AUC of PriorNet was significantly higher (<i>P</i> < .001) relative to both baselines. Conclusion PriorNet using temporal information further improved the breast cancer detection performance of an existing digital breast tomosynthesis cancer detection framework. <b>Keywords:</b> Digital Breast Tomosynthesis, Computer-aided Detection, Breast Cancer, Deep Learning © RSNA, 2024 See also commentary by Lee in this issue.</p>","PeriodicalId":29787,"journal":{"name":"Radiology-Artificial Intelligence","volume":" ","pages":"e230391"},"PeriodicalIF":8.1000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11427939/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology-Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryai.230391","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
引用
批量引用
Abstract
Purpose To develop a deep learning algorithm that uses temporal information to improve the performance of a previously published framework of cancer lesion detection for digital breast tomosynthesis. Materials and Methods This retrospective study analyzed the current and the 1-year-prior Hologic digital breast tomosynthesis screening examinations from eight different institutions between 2016 and 2020. The dataset contained 973 cancer and 7123 noncancer cases. The front end of this algorithm was an existing deep learning framework that performed single-view lesion detection followed by ipsilateral view matching. For this study, PriorNet was implemented as a cascaded deep learning module that used the additional growth information to refine the final probability of malignancy. Data from seven of the eight sites were used for training and validation, while the eighth site was reserved for external testing. Model performance was evaluated using localization receiver operating characteristic curves. Results On the validation set, PriorNet showed an area under the receiver operating characteristic curve (AUC) of 0.931 (95% CI: 0.930, 0.931), which outperformed both baseline models using single-view detection (AUC, 0.892 [95% CI: 0.891, 0.892]; P < .001) and ipsilateral matching (AUC, 0.915 [95% CI: 0.914, 0.915]; P < .001). On the external test set, PriorNet achieved an AUC of 0.896 (95% CI: 0.885, 0.896), outperforming both baselines (AUC, 0.846 [95% CI: 0.846, 0.847]; P < .001 and AUC, 0.865 [95% CI: 0.865, 0.866]; P < .001, respectively). In the high sensitivity range of 0.9 to 1.0, the partial AUC of PriorNet was significantly higher (P < .001) relative to both baselines. Conclusion PriorNet using temporal information further improved the breast cancer detection performance of an existing digital breast tomosynthesis cancer detection framework. Keywords: Digital Breast Tomosynthesis, Computer-aided Detection, Breast Cancer, Deep Learning © RSNA, 2024 See also commentary by Lee in this issue.
通过纳入时间变化改进数字乳腺断层合成的计算机辅助检测。
"刚刚接受 "的论文经过同行评审,已被接受在《放射学》上发表:人工智能》上发表。这篇文章在以最终版本发表之前,还将经过校对、排版和校对审核。请注意,在制作最终校对稿的过程中,可能会发现一些可能影响内容的错误。目的 开发一种利用时间信息的深度学习算法,以提高以前发表的数字乳腺断层合成(DBT)癌症病灶检测框架的性能。材料与方法 这项回顾性研究分析了 8 家不同机构在 2016 年至 2020 年期间进行的当前和之前 1 年的 Hologic DBT 筛查检查。数据集包含 973 例癌症病例和 7123 例非癌症病例。该算法的前端是一个现有的深度学习框架,可进行单视图病变检测,然后进行同侧视图匹配。在本研究中,PriorNet 是作为级联深度学习模块实施的,它使用额外的生长信息来完善恶性肿瘤的最终概率。八个部位中七个部位的数据用于训练和验证,而第八个部位则用于外部测试。使用定位接收器操作特征曲线(ROC)对模型性能进行评估。结果 在验证集上,PriorNet 的 ROC 曲线下面积(AUC)为 0.931(95% CI 0.930-0.931),优于使用单视角检测(AUC,0.892(95% CI 0.891-0.892),P < .001)和同侧匹配(AUC,0.915(95% CI 0.914-0.915),P < .001)的两个基线模型。在外部测试集上,PriorNet 的 AUC 为 0.896(95% CI 0.885-0.896),优于两个基线(AUC 分别为 0.846(95% CI 0.846-0.847,P < .001)和 0.865(95% CI 0.865-0.866),P < .001)。在 0.9 至 1.0 的高灵敏度范围内,PriorNet 的部分 AUC 明显高于两种基线(P < .001)。结论 使用时间信息的 PriorNet 进一步提高了现有 DBT 癌症检测框架的乳腺癌检测性能。©RSNA, 2024.
本文章由计算机程序翻译,如有差异,请以英文原文为准。