Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients
Abstract Background This study aimed to investigate the value of nonenhanced computed tomography (CT)‐based radiomics in determining disease progression in breast cancer patients with bone marrow metastases and to develop a model for assessing treatment efficacy. Methods A total of 134 breast cancer...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | Thoracic Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/1759-7714.15199 |
| _version_ | 1797311666221744128 |
|---|---|
| author | Miao He Dongdong Wang Huijie Li Meili Sun Peng Yan Yongyuan Zhang Li Li Dexin Yu Xiuwen Wang Yu Hu |
| author_facet | Miao He Dongdong Wang Huijie Li Meili Sun Peng Yan Yongyuan Zhang Li Li Dexin Yu Xiuwen Wang Yu Hu |
| author_sort | Miao He |
| collection | DOAJ |
| description | Abstract Background This study aimed to investigate the value of nonenhanced computed tomography (CT)‐based radiomics in determining disease progression in breast cancer patients with bone marrow metastases and to develop a model for assessing treatment efficacy. Methods A total of 134 breast cancer patients with bone metastases were enrolled from three hospitals. Nonenhanced CT was performed after two cycles of drug treatment. The images were categorized into an invalid and a valid group according to disease progression status. The largest osteolytic lesions' maximum cross‐sections in the CT images were selected as regions of interest (ROIs) for feature extraction. Variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) were used to reduce feature dimensionality. K‐nearest neighbor algorithm (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) algorithms were trained to establish radiomics models. Receiver operating characteristic (ROC) curves were generated to evaluate the diagnostic performance of the models. Results The KNN classifier demonstrated the best performance compared to the random grouping method. In the validation group, the area under the ROC curve (AUC) was 0.810. In the cross‐validation method, the RF classifier showed the best performance with an AUC of 0.84. Conclusion Nonenhanced CT‐based radiomics provides a promising method for evaluating the efficacy of systemic drug therapy in breast cancer patients with osteolytic bone metastases. |
| first_indexed | 2024-03-08T02:03:57Z |
| format | Article |
| id | doaj.art-a95cb767b26a40e587aedb7da241e07e |
| institution | Directory Open Access Journal |
| issn | 1759-7706 1759-7714 |
| language | English |
| last_indexed | 2024-03-08T02:03:57Z |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Thoracic Cancer |
| spelling | doaj.art-a95cb767b26a40e587aedb7da241e07e2024-02-14T02:05:54ZengWileyThoracic Cancer1759-77061759-77142024-02-0115536136810.1111/1759-7714.15199Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patientsMiao He0Dongdong Wang1Huijie Li2Meili Sun3Peng Yan4Yongyuan Zhang5Li Li6Dexin Yu7Xiuwen Wang8Yu Hu9Department of Medical Oncology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Radiology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Oncology Affiliated Hospital of Shandong University of Traditional Chinese Medicine Jinan ChinaDepartment of Oncology Jinan Central Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Oncology Jinan Central Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Medical Affairs Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Medical Oncology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Radiology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Medical Oncology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaDepartment of Medical Oncology Qilu Hospital, Cheeloo College of Medicine, Shandong University Jinan ChinaAbstract Background This study aimed to investigate the value of nonenhanced computed tomography (CT)‐based radiomics in determining disease progression in breast cancer patients with bone marrow metastases and to develop a model for assessing treatment efficacy. Methods A total of 134 breast cancer patients with bone metastases were enrolled from three hospitals. Nonenhanced CT was performed after two cycles of drug treatment. The images were categorized into an invalid and a valid group according to disease progression status. The largest osteolytic lesions' maximum cross‐sections in the CT images were selected as regions of interest (ROIs) for feature extraction. Variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) were used to reduce feature dimensionality. K‐nearest neighbor algorithm (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) algorithms were trained to establish radiomics models. Receiver operating characteristic (ROC) curves were generated to evaluate the diagnostic performance of the models. Results The KNN classifier demonstrated the best performance compared to the random grouping method. In the validation group, the area under the ROC curve (AUC) was 0.810. In the cross‐validation method, the RF classifier showed the best performance with an AUC of 0.84. Conclusion Nonenhanced CT‐based radiomics provides a promising method for evaluating the efficacy of systemic drug therapy in breast cancer patients with osteolytic bone metastases.https://doi.org/10.1111/1759-7714.15199bone metastasesbreast cancerCTradiomicstherapeutic evaluation |
| spellingShingle | Miao He Dongdong Wang Huijie Li Meili Sun Peng Yan Yongyuan Zhang Li Li Dexin Yu Xiuwen Wang Yu Hu Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients Thoracic Cancer bone metastases breast cancer CT radiomics therapeutic evaluation |
| title | Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| title_full | Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| title_fullStr | Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| title_full_unstemmed | Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| title_short | Value of CT‐based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| title_sort | value of ct based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients |
| topic | bone metastases breast cancer CT radiomics therapeutic evaluation |
| url | https://doi.org/10.1111/1759-7714.15199 |
| work_keys_str_mv | AT miaohe valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT dongdongwang valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT huijieli valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT meilisun valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT pengyan valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT yongyuanzhang valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT lili valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT dexinyu valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT xiuwenwang valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients AT yuhu valueofctbasedradiomicsinevaluatingtheresponseofbonemetastasestosystemicdrugtherapyinbreastcancerpatients |