评估可解释多模态深度学习中用于癌症预测的新兴预训练策略。

IF 4 3区 生物学 Q1 MATHEMATICAL & COMPUTATIONAL BIOLOGY Biodata Mining Pub Date : 2023-07-22 DOI:10.1186/s13040-023-00338-w
Zarif L Azher, Anish Suvarna, Ji-Qing Chen, Ze Zhang, Brock C Christensen, Lucas A Salas, Louis J Vaickus, Joshua J Levy
{"title":"评估可解释多模态深度学习中用于癌症预测的新兴预训练策略。","authors":"Zarif L Azher,&nbsp;Anish Suvarna,&nbsp;Ji-Qing Chen,&nbsp;Ze Zhang,&nbsp;Brock C Christensen,&nbsp;Lucas A Salas,&nbsp;Louis J Vaickus,&nbsp;Joshua J Levy","doi":"10.1186/s13040-023-00338-w","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to \"pretrain\" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.</p><p><strong>Methods: </strong>Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.</p><p><strong>Results: </strong>Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.</p><p><strong>Discussion: </strong>Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"16 1","pages":"23"},"PeriodicalIF":4.0000,"publicationDate":"2023-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10363299/pdf/","citationCount":"2","resultStr":"{\"title\":\"Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication.\",\"authors\":\"Zarif L Azher,&nbsp;Anish Suvarna,&nbsp;Ji-Qing Chen,&nbsp;Ze Zhang,&nbsp;Brock C Christensen,&nbsp;Lucas A Salas,&nbsp;Louis J Vaickus,&nbsp;Joshua J Levy\",\"doi\":\"10.1186/s13040-023-00338-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to \\\"pretrain\\\" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.</p><p><strong>Methods: </strong>Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.</p><p><strong>Results: </strong>Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.</p><p><strong>Discussion: </strong>Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.</p>\",\"PeriodicalId\":48947,\"journal\":{\"name\":\"Biodata Mining\",\"volume\":\"16 1\",\"pages\":\"23\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2023-07-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10363299/pdf/\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biodata Mining\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1186/s13040-023-00338-w\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biodata Mining","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s13040-023-00338-w","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 2

摘要

背景:深度学习模型可以从分子和解剖病理信息中推断癌症患者的预后。最近的研究利用了来自互补多模态数据的信息,改善了预测,进一步说明了这些方法的潜在效用。然而,目前的方法:1)没有全面利用生物和组织形态学的关系,2)利用新兴的策略来“预训练”模型(即,在稍微正交的数据集/建模目标上训练模型),这可能通过减少实现最佳性能所需的信息量来帮助预测。此外,通过培养从业者对技术的理解和信任,模型解释对于促进临床采用深度学习方法至关重要。方法:在这里,我们开发了一个可解释的多模态建模框架,该框架结合了DNA甲基化、基因表达和组织病理学(即组织切片)数据,并将跨模态预训练、对比学习和迁移学习的性能与标准程序进行了比较。结果:我们的模型优于现有的最先进的方法(平均11.54%的c -指数增加)和基线临床驱动模型(平均11.7%的c -指数增加)。模型解释阐明了在进行预后预测时考虑生物学上有意义的因素。讨论:我们的研究结果表明,选择预训练策略对于获得高度准确的预测模型至关重要,甚至比设计创新的模型架构更重要,并进一步强调了肿瘤微环境在疾病进展中的重要作用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

摘要图片

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication.

Background: Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to "pretrain" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.

Methods: Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.

Results: Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.

Discussion: Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.

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
Biodata Mining
Biodata Mining MATHEMATICAL & COMPUTATIONAL BIOLOGY-
CiteScore
7.90
自引率
0.00%
发文量
28
审稿时长
23 weeks
期刊介绍: BioData Mining is an open access, open peer-reviewed journal encompassing research on all aspects of data mining applied to high-dimensional biological and biomedical data, focusing on computational aspects of knowledge discovery from large-scale genetic, transcriptomic, genomic, proteomic, and metabolomic data. Topical areas include, but are not limited to: -Development, evaluation, and application of novel data mining and machine learning algorithms. -Adaptation, evaluation, and application of traditional data mining and machine learning algorithms. -Open-source software for the application of data mining and machine learning algorithms. -Design, development and integration of databases, software and web services for the storage, management, retrieval, and analysis of data from large scale studies. -Pre-processing, post-processing, modeling, and interpretation of data mining and machine learning results for biological interpretation and knowledge discovery.
期刊最新文献
Deep learning-based Emergency Department In-hospital Cardiac Arrest Score (Deep EDICAS) for early prediction of cardiac arrest and cardiopulmonary resuscitation in the emergency department. Supervised multiple kernel learning approaches for multi-omics data integration. Transcriptome-based network analysis related to regulatory T cells infiltration identified RCN1 as a potential biomarker for prognosis in clear cell renal cell carcinoma. Deciphering the tissue-specific functional effect of Alzheimer risk SNPs with deep genome annotation. Investigating potential drug targets for IgA nephropathy and membranous nephropathy through multi-queue plasma protein analysis: a Mendelian randomization study based on SMR and co-localization analysis.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1