Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids
Objectives: To develop and apply magnetic resonance imaging (MRI) parameter-based machine learning (ML) models to predict non-perfused volume (NPV) reduction and residual regrowth of uterine fibroids after high-intensity focused ultrasound (HIFU) ablation.Methods: MRI data of 573 uterine fibroids in...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | International Journal of Hyperthermia |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/02656736.2022.2090622 |
| _version_ | 1811332768850771968 |
|---|---|
| author | Jinwei Zhang Chao Yang Chunmei Gong Ye Zhou Chenghai Li Faqi Li |
| author_facet | Jinwei Zhang Chao Yang Chunmei Gong Ye Zhou Chenghai Li Faqi Li |
| author_sort | Jinwei Zhang |
| collection | DOAJ |
| description | Objectives: To develop and apply magnetic resonance imaging (MRI) parameter-based machine learning (ML) models to predict non-perfused volume (NPV) reduction and residual regrowth of uterine fibroids after high-intensity focused ultrasound (HIFU) ablation.Methods: MRI data of 573 uterine fibroids in 410 women who underwent HIFU ablation from the Chongqing Haifu Hospital (training set, N = 405) and the First Affiliated Hospital of Chongqing Medical University (testing set, N = 168) were retrospectively analyzed. Fourteen MRI parameters were screened for important predictors using the Boruta algorithm. Multiple ML models were constructed to predict NPV reduction and residual fibroid regrowth in a median of 203.0 (interquartile range: 122.5–367.5) days. Furthermore, optimal models were used to plot prognostic prediction curves.Results: Fourteen features, including postoperative NPV, indicated predictive ability for NPV reduction. Based on the 10-fold cross-validation, the best average performance of multilayer perceptron achieved with R2 was 0.907. In the testing set, the best model was linear regression (R2 =0.851). Ten features, including the maximum thickness of residual fibroids, revealed predictive power for residual fibroid regrowth. Random forest model achieved the best performance with an average area under the curve (AUC) of 0.904 (95% confidence interval (CI), 0.869–0.939), which was maintained in the testing set with an AUC of 0.891 (95% CI, 0.850–0.929).Conclusions: ML models based on MRI parameters can be used for prognostic prediction of uterine fibroids after HIFU ablation. They can potentially serve as a new method for learning more about ablated fibroids. |
| first_indexed | 2024-04-13T16:41:58Z |
| format | Article |
| id | doaj.art-6c4cffdb2f344a3d89b399c84c6681cd |
| institution | Directory Open Access Journal |
| issn | 0265-6736 1464-5157 |
| language | English |
| last_indexed | 2024-04-13T16:41:58Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Hyperthermia |
| spelling | doaj.art-6c4cffdb2f344a3d89b399c84c6681cd2022-12-22T02:39:13ZengTaylor & Francis GroupInternational Journal of Hyperthermia0265-67361464-51572022-12-0139183584610.1080/02656736.2022.2090622Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroidsJinwei Zhang0Chao Yang1Chunmei Gong2Ye Zhou3Chenghai Li4Faqi Li5State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaState Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaState Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaState Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaState Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaState Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Key Laboratory of Biomedical Engineering, Chongqing Medical University, Chongqing, ChinaObjectives: To develop and apply magnetic resonance imaging (MRI) parameter-based machine learning (ML) models to predict non-perfused volume (NPV) reduction and residual regrowth of uterine fibroids after high-intensity focused ultrasound (HIFU) ablation.Methods: MRI data of 573 uterine fibroids in 410 women who underwent HIFU ablation from the Chongqing Haifu Hospital (training set, N = 405) and the First Affiliated Hospital of Chongqing Medical University (testing set, N = 168) were retrospectively analyzed. Fourteen MRI parameters were screened for important predictors using the Boruta algorithm. Multiple ML models were constructed to predict NPV reduction and residual fibroid regrowth in a median of 203.0 (interquartile range: 122.5–367.5) days. Furthermore, optimal models were used to plot prognostic prediction curves.Results: Fourteen features, including postoperative NPV, indicated predictive ability for NPV reduction. Based on the 10-fold cross-validation, the best average performance of multilayer perceptron achieved with R2 was 0.907. In the testing set, the best model was linear regression (R2 =0.851). Ten features, including the maximum thickness of residual fibroids, revealed predictive power for residual fibroid regrowth. Random forest model achieved the best performance with an average area under the curve (AUC) of 0.904 (95% confidence interval (CI), 0.869–0.939), which was maintained in the testing set with an AUC of 0.891 (95% CI, 0.850–0.929).Conclusions: ML models based on MRI parameters can be used for prognostic prediction of uterine fibroids after HIFU ablation. They can potentially serve as a new method for learning more about ablated fibroids.https://www.tandfonline.com/doi/10.1080/02656736.2022.2090622High-intensity focused ultrasounduterine fibroidsmachine learningprognosisresidual fibroids |
| spellingShingle | Jinwei Zhang Chao Yang Chunmei Gong Ye Zhou Chenghai Li Faqi Li Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids International Journal of Hyperthermia High-intensity focused ultrasound uterine fibroids machine learning prognosis residual fibroids |
| title | Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids |
| title_full | Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids |
| title_fullStr | Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids |
| title_full_unstemmed | Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids |
| title_short | Magnetic resonance imaging parameter-based machine learning for prognosis prediction of high-intensity focused ultrasound ablation of uterine fibroids |
| title_sort | magnetic resonance imaging parameter based machine learning for prognosis prediction of high intensity focused ultrasound ablation of uterine fibroids |
| topic | High-intensity focused ultrasound uterine fibroids machine learning prognosis residual fibroids |
| url | https://www.tandfonline.com/doi/10.1080/02656736.2022.2090622 |
| work_keys_str_mv | AT jinweizhang magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids AT chaoyang magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids AT chunmeigong magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids AT yezhou magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids AT chenghaili magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids AT faqili magneticresonanceimagingparameterbasedmachinelearningforprognosispredictionofhighintensityfocusedultrasoundablationofuterinefibroids |