Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study
Purpose: To evaluate the effectiveness of machine learning model based on magnetic resonance imaging (MRI) in identifying microsatellite instability (MSI) status and PD-L1 expression in endometrial cancer (EC). Methods: This retrospective study included 82 EC patients from 2 independent centers. Rad...
| Principais autores: | , , , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | English |
| Publicado em: |
Elsevier
2023-12-01
|
| coleção: | Heliyon |
| Assuntos: | |
| Acesso em linha: | http://www.sciencedirect.com/science/article/pii/S2405844023103744 |
| _version_ | 1827577384536113152 |
|---|---|
| author | Qianling Li Ya'nan Huang Yang Xia Meiping Li Wei Tang Minming Zhang Zhenhua Zhao |
| author_facet | Qianling Li Ya'nan Huang Yang Xia Meiping Li Wei Tang Minming Zhang Zhenhua Zhao |
| author_sort | Qianling Li |
| collection | DOAJ |
| description | Purpose: To evaluate the effectiveness of machine learning model based on magnetic resonance imaging (MRI) in identifying microsatellite instability (MSI) status and PD-L1 expression in endometrial cancer (EC). Methods: This retrospective study included 82 EC patients from 2 independent centers. Radiomics features from the intratumoral and peritumoral regions, obtained from four conventional MRI sequences (T2-weighted images; contrast-enhanced T1-weighted images; diffusion-weighted images; apparent diffusion coefficient), were combined with clinicopathologic characteristics to develop machine learning model for predicting MSI status and PD-L1 expression. 60 patients from center 1 were used as the training set for model construction, while 22 patients from center 2 were used as an external validation set for model evaluation. Results: For predicting MSI status, the clinicopathologic model, radscore model, and combination model achieved area under the curves (AUCs) of 0.728, 0.833, and 0.889 in the training set, respectively, and 0.595, 0.790, and 0.848 in the validation set, respectively. For predicting PD-L1 expression, the clinicopathologic model, radscore model, and combination model achieved AUCs of 0.648, 0.814, and 0.834 in the training set, respectively, and 0.660, 0.708, and 0.764 in the validation set, respectively. Calibration curve analysis and decision curve analysis demonstrated good calibration and clinical utility of the combination model. Conclusion: The machine learning model incorporating MRI-based radiomics features and clinicopathologic characteristics could be a potential tool for predicting MSI status and PD-L1 expression in EC. This approach may contribute to precision medicine for EC patients. |
| first_indexed | 2024-03-08T21:27:03Z |
| format | Article |
| id | doaj.art-40a9fa8cc0fe49bf98efaf45142dea82 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T21:27:03Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-40a9fa8cc0fe49bf98efaf45142dea822023-12-21T07:35:52ZengElsevierHeliyon2405-84402023-12-01912e23166Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter studyQianling Li0Ya'nan Huang1Yang Xia2Meiping Li3Wei Tang4Minming Zhang5Zhenhua Zhao6Department of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School of Medicine), Zhejiang University School of Medicine, Shaoxing, 312000, ChinaDepartment of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School of Medicine), Shaoxing, 312000, ChinaDepartment of Radiology, Shaoxing Maternity and Child Health Care Hospital, Shaoxing, 312000, ChinaDepartment of Pathology, Shaoxing Maternity and Child Health Care Hospital, Shaoxing, Zhejiang, 312000, ChinaDepartment of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School of Medicine), Shaoxing, 312000, ChinaDepartment of Radiology, The Second Affiliated Hospital of Zhejiang University, Hangzhou, 310000, ChinaDepartment of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School of Medicine), Shaoxing, 312000, China; Corresponding author. Department of Radiology, Shaoxing People's Hospital (Shaoxing Hospital, Zhejiang University School), No. 568, North Zhongxing Road, Yuecheng District, Shaoxing City 312000, Zhejiang Province, China.Purpose: To evaluate the effectiveness of machine learning model based on magnetic resonance imaging (MRI) in identifying microsatellite instability (MSI) status and PD-L1 expression in endometrial cancer (EC). Methods: This retrospective study included 82 EC patients from 2 independent centers. Radiomics features from the intratumoral and peritumoral regions, obtained from four conventional MRI sequences (T2-weighted images; contrast-enhanced T1-weighted images; diffusion-weighted images; apparent diffusion coefficient), were combined with clinicopathologic characteristics to develop machine learning model for predicting MSI status and PD-L1 expression. 60 patients from center 1 were used as the training set for model construction, while 22 patients from center 2 were used as an external validation set for model evaluation. Results: For predicting MSI status, the clinicopathologic model, radscore model, and combination model achieved area under the curves (AUCs) of 0.728, 0.833, and 0.889 in the training set, respectively, and 0.595, 0.790, and 0.848 in the validation set, respectively. For predicting PD-L1 expression, the clinicopathologic model, radscore model, and combination model achieved AUCs of 0.648, 0.814, and 0.834 in the training set, respectively, and 0.660, 0.708, and 0.764 in the validation set, respectively. Calibration curve analysis and decision curve analysis demonstrated good calibration and clinical utility of the combination model. Conclusion: The machine learning model incorporating MRI-based radiomics features and clinicopathologic characteristics could be a potential tool for predicting MSI status and PD-L1 expression in EC. This approach may contribute to precision medicine for EC patients.http://www.sciencedirect.com/science/article/pii/S2405844023103744Endometrial cancerMicrosatellite instabilityMismatch repair deficiencyPD-L1Magnetic resonance imagingMachine learning |
| spellingShingle | Qianling Li Ya'nan Huang Yang Xia Meiping Li Wei Tang Minming Zhang Zhenhua Zhao Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study Heliyon Endometrial cancer Microsatellite instability Mismatch repair deficiency PD-L1 Magnetic resonance imaging Machine learning |
| title | Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study |
| title_full | Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study |
| title_fullStr | Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study |
| title_full_unstemmed | Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study |
| title_short | Radiogenomics for predicting microsatellite instability status and PD-L1 expression with machine learning in endometrial cancers: A multicenter study |
| title_sort | radiogenomics for predicting microsatellite instability status and pd l1 expression with machine learning in endometrial cancers a multicenter study |
| topic | Endometrial cancer Microsatellite instability Mismatch repair deficiency PD-L1 Magnetic resonance imaging Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023103744 |
| work_keys_str_mv | AT qianlingli radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT yananhuang radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT yangxia radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT meipingli radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT weitang radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT minmingzhang radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy AT zhenhuazhao radiogenomicsforpredictingmicrosatelliteinstabilitystatusandpdl1expressionwithmachinelearninginendometrialcancersamulticenterstudy |