Vu Pham Thao Vy, Jerry Chin-Wei Chien, Wiwan Irama, Hao-Yang Wu, Tzu-I Wu, Wei-Yu Chen, Chia-Hao Liang, Truong Nguyen Khanh Hung, Wilson T Lao, Wing P Chan
{"title":"Machine learning models using multiparametric MRI for preoperative risk stratification in endometrial cancer.","authors":"Vu Pham Thao Vy, Jerry Chin-Wei Chien, Wiwan Irama, Hao-Yang Wu, Tzu-I Wu, Wei-Yu Chen, Chia-Hao Liang, Truong Nguyen Khanh Hung, Wilson T Lao, Wing P Chan","doi":"10.62347/MALY3908","DOIUrl":null,"url":null,"abstract":"<p><p>This study evaluated the efficacy of machine learning and radiomics of preoperative multiparameter MRIs in predicting low- vs high-risk histopathologic features and early vs advanced FIGO stage (IA vs IB or higher) in endometrial cancer. This retrospective study of patients with endometrial cancer histologically confirmed from 2008 through 2023 excluded those with: (a) previous treatment for endometrial carcinoma, (b) incomplete MRI examinations or low-quality MR images, (c) incomplete pathology reports, (d) non-visualized tumors on MRI, or (e) distant metastases. In total, 110 radiomic features were extracted using commercial PACS built-in software following segmentation after sagittal T2-weighted imaging (T2WI), contrast enhanced T1-weighted imaging (CE-T1WI), and diffusion weighted imaging (DWI). The radiomic features from each imaging sequence were utilized for initial modeling. A combined model, which included features retained from all 3 sequences, was then established. The area under the receiver operating characteristic curve (AUC) determined the efficacy of each model. For 5 specific histopathologic features, the combined model achieved AUCs of 0.87 (95% CI, 0.85-0.90), 0.90 (95% CI, 0.88-0.92), 0.88 (95% CI, 0.87-0.90), 0.88 (95% CI, 0.86-0.92), and 0.87 (95% CI, 0.86-0.90). This model incorporated 38 radiomic features: 12 from T2WI, 17 from CE-T1WI, and 9 from DWI. In conclusion, an MRI radiomics-based model can differentiate between early- and advanced-stage endometrial cancer and between low- and high-risk histologic markers, giving it the potential to predict high risk and stratify preoperative risk in those with endometrial cancer. The findings may aid personalized preoperative assessments to guide clinical decision-making in endometrial cancer.</p>","PeriodicalId":7437,"journal":{"name":"American journal of cancer research","volume":"14 11","pages":"5400-5410"},"PeriodicalIF":3.6000,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11626267/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of cancer research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.62347/MALY3908","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
This study evaluated the efficacy of machine learning and radiomics of preoperative multiparameter MRIs in predicting low- vs high-risk histopathologic features and early vs advanced FIGO stage (IA vs IB or higher) in endometrial cancer. This retrospective study of patients with endometrial cancer histologically confirmed from 2008 through 2023 excluded those with: (a) previous treatment for endometrial carcinoma, (b) incomplete MRI examinations or low-quality MR images, (c) incomplete pathology reports, (d) non-visualized tumors on MRI, or (e) distant metastases. In total, 110 radiomic features were extracted using commercial PACS built-in software following segmentation after sagittal T2-weighted imaging (T2WI), contrast enhanced T1-weighted imaging (CE-T1WI), and diffusion weighted imaging (DWI). The radiomic features from each imaging sequence were utilized for initial modeling. A combined model, which included features retained from all 3 sequences, was then established. The area under the receiver operating characteristic curve (AUC) determined the efficacy of each model. For 5 specific histopathologic features, the combined model achieved AUCs of 0.87 (95% CI, 0.85-0.90), 0.90 (95% CI, 0.88-0.92), 0.88 (95% CI, 0.87-0.90), 0.88 (95% CI, 0.86-0.92), and 0.87 (95% CI, 0.86-0.90). This model incorporated 38 radiomic features: 12 from T2WI, 17 from CE-T1WI, and 9 from DWI. In conclusion, an MRI radiomics-based model can differentiate between early- and advanced-stage endometrial cancer and between low- and high-risk histologic markers, giving it the potential to predict high risk and stratify preoperative risk in those with endometrial cancer. The findings may aid personalized preoperative assessments to guide clinical decision-making in endometrial cancer.
期刊介绍:
The American Journal of Cancer Research (AJCR) (ISSN 2156-6976), is an independent open access, online only journal to facilitate rapid dissemination of novel discoveries in basic science and treatment of cancer. It was founded by a group of scientists for cancer research and clinical academic oncologists from around the world, who are devoted to the promotion and advancement of our understanding of the cancer and its treatment. The scope of AJCR is intended to encompass that of multi-disciplinary researchers from any scientific discipline where the primary focus of the research is to increase and integrate knowledge about etiology and molecular mechanisms of carcinogenesis with the ultimate aim of advancing the cure and prevention of this increasingly devastating disease. To achieve these aims AJCR will publish review articles, original articles and new techniques in cancer research and therapy. It will also publish hypothesis, case reports and letter to the editor. Unlike most other open access online journals, AJCR will keep most of the traditional features of paper print that we are all familiar with, such as continuous volume, issue numbers, as well as continuous page numbers to retain our comfortable familiarity towards an academic journal.