Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study
Purpose To compare the diagnostic efficiencies of deep learning single-modal and multi-modal for the classification of benign and malignant breast mass lesions. Methods We retrospectively collected data from 203 patients (207 lesions, 101 benign and 106 malignant) with breast tumors who underwent br...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-07-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1460.pdf |
| _version_ | 1797777068221530112 |
|---|---|
| author | Weixia Tang Ming Zhang Changyan Xu Yeqin Shao Jiahuan Tang Shenchu Gong Hao Dong Meihong Sheng |
| author_facet | Weixia Tang Ming Zhang Changyan Xu Yeqin Shao Jiahuan Tang Shenchu Gong Hao Dong Meihong Sheng |
| author_sort | Weixia Tang |
| collection | DOAJ |
| description | Purpose To compare the diagnostic efficiencies of deep learning single-modal and multi-modal for the classification of benign and malignant breast mass lesions. Methods We retrospectively collected data from 203 patients (207 lesions, 101 benign and 106 malignant) with breast tumors who underwent breast magnetic resonance imaging (MRI) before surgery or biopsy between January 2014 and October 2020. Mass segmentation was performed based on the three dimensions-region of interest (3D-ROI) minimum bounding cube at the edge of the lesion. We established single-modal models based on a convolutional neural network (CNN) including T2WI and non-fs T1WI, the dynamic contrast-enhanced (DCE-MRI) first phase was pre-contrast T1WI (d1), and Phases 2, 4, and 6 were post-contrast T1WI (d2, d4, d6); and Multi-modal fusion models with a Sobel operator (four_mods:T2WI, non-fs-T1WI, d1, d2). Training set (n = 145), validation set (n = 22), and test set (n = 40). Five-fold cross validation was performed. Accuracy, sensitivity, specificity, negative predictive value, positive predictive value, and area under the ROC curve (AUC) were used as evaluation indicators. Delong’s test compared the diagnostic performance of the multi-modal and single-modal models. Results All models showed good performance, and the AUC values were all greater than 0.750. Among the single-modal models, T2WI, non-fs-T1WI, d1, and d2 had specificities of 77.1%, 77.2%, 80.2%, and 78.2%, respectively. d2 had the highest accuracy of 78.5% and showed the best diagnostic performance with an AUC of 0.827. The multi-modal model with the Sobel operator performed better than single-modal models, with an AUC of 0.887, sensitivity of 79.8%, specificity of 86.1%, and positive prediction value of 85.6%. Delong’s test showed that the diagnostic performance of the multi-modal fusion models was higher than that of the six single-modal models (T2WI, non-fs-T1WI, d1, d2, d4, d6); the difference was statistically significant (p = 0.043, 0.017, 0.006, 0.017, 0.020, 0.004, all were greater than 0.05). Conclusions Multi-modal fusion deep learning models with a Sobel operator had excellent diagnostic value in the classification of breast masses, and further increase the efficiency of diagnosis. |
| first_indexed | 2024-03-12T22:58:51Z |
| format | Article |
| id | doaj.art-72848c2b5e9342418dfb5a2c853487f6 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-12T22:58:51Z |
| publishDate | 2023-07-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-72848c2b5e9342418dfb5a2c853487f62023-07-19T15:05:07ZengPeerJ Inc.PeerJ Computer Science2376-59922023-07-019e146010.7717/peerj-cs.1460Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective studyWeixia Tang0Ming Zhang1Changyan Xu2Yeqin Shao3Jiahuan Tang4Shenchu Gong5Hao Dong6Meihong Sheng7Radiology Department, Affiliated Hospital 2 of Nantong University, Nantong First People’s Hospital, NanTong, Jiangsu, ChinaRadiology Department, Affiliated Hospital 2 of Nantong University, Nantong First People’s Hospital, NanTong, Jiangsu, ChinaSchool of Transportation and Civil Engineering, Nantong University, Nantong, ChinaSchool of Transportation and Civil Engineering, Nantong University, Nantong, ChinaRadiology Department, Affiliated Hospital 2 of Nantong University, Nantong First People’s Hospital, NanTong, Jiangsu, ChinaRadiology Department, Affiliated Hospital 2 of Nantong University, Nantong First People’s Hospital, NanTong, Jiangsu, ChinaDepartment of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., Ltd., Beijing, ChinaRadiology Department, Affiliated Hospital 2 of Nantong University, Nantong First People’s Hospital, NanTong, Jiangsu, ChinaPurpose To compare the diagnostic efficiencies of deep learning single-modal and multi-modal for the classification of benign and malignant breast mass lesions. Methods We retrospectively collected data from 203 patients (207 lesions, 101 benign and 106 malignant) with breast tumors who underwent breast magnetic resonance imaging (MRI) before surgery or biopsy between January 2014 and October 2020. Mass segmentation was performed based on the three dimensions-region of interest (3D-ROI) minimum bounding cube at the edge of the lesion. We established single-modal models based on a convolutional neural network (CNN) including T2WI and non-fs T1WI, the dynamic contrast-enhanced (DCE-MRI) first phase was pre-contrast T1WI (d1), and Phases 2, 4, and 6 were post-contrast T1WI (d2, d4, d6); and Multi-modal fusion models with a Sobel operator (four_mods:T2WI, non-fs-T1WI, d1, d2). Training set (n = 145), validation set (n = 22), and test set (n = 40). Five-fold cross validation was performed. Accuracy, sensitivity, specificity, negative predictive value, positive predictive value, and area under the ROC curve (AUC) were used as evaluation indicators. Delong’s test compared the diagnostic performance of the multi-modal and single-modal models. Results All models showed good performance, and the AUC values were all greater than 0.750. Among the single-modal models, T2WI, non-fs-T1WI, d1, and d2 had specificities of 77.1%, 77.2%, 80.2%, and 78.2%, respectively. d2 had the highest accuracy of 78.5% and showed the best diagnostic performance with an AUC of 0.827. The multi-modal model with the Sobel operator performed better than single-modal models, with an AUC of 0.887, sensitivity of 79.8%, specificity of 86.1%, and positive prediction value of 85.6%. Delong’s test showed that the diagnostic performance of the multi-modal fusion models was higher than that of the six single-modal models (T2WI, non-fs-T1WI, d1, d2, d4, d6); the difference was statistically significant (p = 0.043, 0.017, 0.006, 0.017, 0.020, 0.004, all were greater than 0.05). Conclusions Multi-modal fusion deep learning models with a Sobel operator had excellent diagnostic value in the classification of breast masses, and further increase the efficiency of diagnosis.https://peerj.com/articles/cs-1460.pdfBreastMassMagnetic resonanceDeep learningMulti-modalSobel operator |
| spellingShingle | Weixia Tang Ming Zhang Changyan Xu Yeqin Shao Jiahuan Tang Shenchu Gong Hao Dong Meihong Sheng Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study PeerJ Computer Science Breast Mass Magnetic resonance Deep learning Multi-modal Sobel operator |
| title | Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study |
| title_full | Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study |
| title_fullStr | Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study |
| title_full_unstemmed | Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study |
| title_short | Diagnostic efficiency of multi-modal MRI based deep learning with Sobel operator in differentiating benign and malignant breast mass lesions—a retrospective study |
| title_sort | diagnostic efficiency of multi modal mri based deep learning with sobel operator in differentiating benign and malignant breast mass lesions a retrospective study |
| topic | Breast Mass Magnetic resonance Deep learning Multi-modal Sobel operator |
| url | https://peerj.com/articles/cs-1460.pdf |
| work_keys_str_mv | AT weixiatang diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT mingzhang diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT changyanxu diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT yeqinshao diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT jiahuantang diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT shenchugong diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT haodong diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy AT meihongsheng diagnosticefficiencyofmultimodalmribaseddeeplearningwithsobeloperatorindifferentiatingbenignandmalignantbreastmasslesionsaretrospectivestudy |