Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography
Abstract Objective To develop a multi-modality machine learning-based radiomics model utilizing Magnetic Resonance Imaging (MRI), Ultrasound (US), and Mammography (MMG) for the differentiation of benign and malignant breast nodules. Methods This study retrospectively collected data from 204 patients...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01767-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238126286864384 |
|---|---|
| author | Jiao Wu YongXin Li Wanqing Gong Qian Li Xue Han Tingting Zhang |
| author_facet | Jiao Wu YongXin Li Wanqing Gong Qian Li Xue Han Tingting Zhang |
| author_sort | Jiao Wu |
| collection | DOAJ |
| description | Abstract Objective To develop a multi-modality machine learning-based radiomics model utilizing Magnetic Resonance Imaging (MRI), Ultrasound (US), and Mammography (MMG) for the differentiation of benign and malignant breast nodules. Methods This study retrospectively collected data from 204 patients across three hospitals, including MRI, US, and MMG imaging data along with confirmed pathological diagnoses. Lesions on 2D US, 2D MMG, and 3D MRI images were selected to outline the areas of interest, which were then automatically expanded outward by 3 mm, 5 mm, and 8 mm to extract radiomic features within and around the tumor. ANOVA, the maximum correlation minimum redundancy (mRMR) algorithm, and the least absolute shrinkage and selection operator (LASSO) were used to select features for breast cancer diagnosis through logistic regression analysis. The performance of the radiomics models was evaluated using receiver operating characteristic (ROC) curve analysis, curves decision curve analysis (DCA), and calibration curves. Results Among the various radiomics models tested, the MRI_US_MMG multi-modality logistic regression model with 5 mm peritumoral features demonstrated the best performance. In the test cohort, this model achieved an AUC of 0.905(95% confidence interval [CI]: 0.805–1). These results suggest that the inclusion of peritumoral features, specifically at a 5 mm expansion, significantly enhanced the diagnostic efficiency of the multi-modality radiomics model in differentiating benign from malignant breast nodules. Conclusions The multi-modality radiomics model based on MRI, ultrasound, and mammography can predict benign and malignant breast lesions. |
| format | Article |
| id | doaj-art-210317ebf7ff4093abe0bd157b6c8720 |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-210317ebf7ff4093abe0bd157b6c87202025-08-20T04:01:43ZengBMCBMC Medical Imaging1471-23422025-07-0125111210.1186/s12880-025-01767-1Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammographyJiao Wu0YongXin Li1Wanqing Gong2Qian Li3Xue Han4Tingting Zhang5Department of Radiology, The First College of Clinical Medical Science, Yichang Central People’s Hospital, ChinaThree Gorges UniversitySchool of Automation and Intelligence, Beijing Jiaotong UniversityDepartment of Radiology, The First College of Clinical Medical Science, Yichang Central People’s Hospital, ChinaThree Gorges UniversityDepartment of Thoracic Surgery, China Aerospace Science and Industry Corporation 731 HospitalDepartment of Breast Surgery Ward 1000, The First Hospital Of China Medical UniversityDepartment of Radiology, The First College of Clinical Medical Science, Yichang Central People’s Hospital, ChinaThree Gorges UniversityAbstract Objective To develop a multi-modality machine learning-based radiomics model utilizing Magnetic Resonance Imaging (MRI), Ultrasound (US), and Mammography (MMG) for the differentiation of benign and malignant breast nodules. Methods This study retrospectively collected data from 204 patients across three hospitals, including MRI, US, and MMG imaging data along with confirmed pathological diagnoses. Lesions on 2D US, 2D MMG, and 3D MRI images were selected to outline the areas of interest, which were then automatically expanded outward by 3 mm, 5 mm, and 8 mm to extract radiomic features within and around the tumor. ANOVA, the maximum correlation minimum redundancy (mRMR) algorithm, and the least absolute shrinkage and selection operator (LASSO) were used to select features for breast cancer diagnosis through logistic regression analysis. The performance of the radiomics models was evaluated using receiver operating characteristic (ROC) curve analysis, curves decision curve analysis (DCA), and calibration curves. Results Among the various radiomics models tested, the MRI_US_MMG multi-modality logistic regression model with 5 mm peritumoral features demonstrated the best performance. In the test cohort, this model achieved an AUC of 0.905(95% confidence interval [CI]: 0.805–1). These results suggest that the inclusion of peritumoral features, specifically at a 5 mm expansion, significantly enhanced the diagnostic efficiency of the multi-modality radiomics model in differentiating benign from malignant breast nodules. Conclusions The multi-modality radiomics model based on MRI, ultrasound, and mammography can predict benign and malignant breast lesions.https://doi.org/10.1186/s12880-025-01767-1Breast cancerMagnetic resonance imagingUltrasoundMammographyRadiomics |
| spellingShingle | Jiao Wu YongXin Li Wanqing Gong Qian Li Xue Han Tingting Zhang Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography BMC Medical Imaging Breast cancer Magnetic resonance imaging Ultrasound Mammography Radiomics |
| title | Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography |
| title_full | Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography |
| title_fullStr | Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography |
| title_full_unstemmed | Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography |
| title_short | Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography |
| title_sort | multi modality radiomics diagnosis of breast cancer based on mri ultrasound and mammography |
| topic | Breast cancer Magnetic resonance imaging Ultrasound Mammography Radiomics |
| url | https://doi.org/10.1186/s12880-025-01767-1 |
| work_keys_str_mv | AT jiaowu multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography AT yongxinli multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography AT wanqinggong multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography AT qianli multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography AT xuehan multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography AT tingtingzhang multimodalityradiomicsdiagnosisofbreastcancerbasedonmriultrasoundandmammography |