Diagnostic value of mammography density of breast masses by using deep learning
ObjectiveIn order to explore the relationship between mammographic density of breast mass and its surrounding area and benign or malignant breast, this paper proposes a deep learning model based on C2FTrans to diagnose the breast mass using mammographic density.MethodsThis retrospective study includ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1110657/full |
| _version_ | 1797813589918089216 |
|---|---|
| author | Qian-qian Chen Shu-ting Lin Jia-yi Ye Yun-fei Tong Shu Lin Shu Lin Si-qing Cai |
| author_facet | Qian-qian Chen Shu-ting Lin Jia-yi Ye Yun-fei Tong Shu Lin Shu Lin Si-qing Cai |
| author_sort | Qian-qian Chen |
| collection | DOAJ |
| description | ObjectiveIn order to explore the relationship between mammographic density of breast mass and its surrounding area and benign or malignant breast, this paper proposes a deep learning model based on C2FTrans to diagnose the breast mass using mammographic density.MethodsThis retrospective study included patients who underwent mammographic and pathological examination. Two physicians manually depicted the lesion edges and used a computer to automatically extend and segment the peripheral areas of the lesion (0, 1, 3, and 5 mm, including the lesion). We then obtained the mammary glands’ density and the different regions of interest (ROI). A diagnostic model for breast mass lesions based on C2FTrans was constructed based on a 7: 3 ratio between the training and testing sets. Finally, receiver operating characteristic (ROC) curves were plotted. Model performance was assessed using the area under the ROC curve (AUC) with 95% confidence intervals (CI), sensitivity, and specificity.ResultsIn total, 401 lesions (158 benign and 243 malignant) were included in this study. The probability of breast cancer in women was positively correlated with age and mass density and negatively correlated with breast gland classification. The largest correlation was observed for age (r = 0.47). Among all models, the single mass ROI model had the highest specificity (91.8%) with an AUC = 0.823 and the perifocal 5mm ROI model had the highest sensitivity (86.9%) with an AUC = 0.855. In addition, by combining the cephalocaudal and mediolateral oblique views of the perifocal 5 mm ROI model, we obtained the highest AUC (AUC = 0.877 P < 0.001).ConclusionsDeep learning model of mammographic density can better distinguish benign and malignant mass-type lesions in digital mammography images and may become an auxiliary diagnostic tool for radiologists in the future. |
| first_indexed | 2024-03-13T07:55:01Z |
| format | Article |
| id | doaj.art-4eaf108ba9fb425c9febea9446b8d8b8 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-03-13T07:55:01Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-4eaf108ba9fb425c9febea9446b8d8b82023-06-02T06:06:30ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-06-011310.3389/fonc.2023.11106571110657Diagnostic value of mammography density of breast masses by using deep learningQian-qian Chen0Shu-ting Lin1Jia-yi Ye2Yun-fei Tong3Shu Lin4Shu Lin5Si-qing Cai6Department of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, ChinaDepartment of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, ChinaDepartment of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, ChinaShanghai Yanghe Huajian Artificial Intelligence Technology Co. Ltd., Shanghai, ChinaCentre of Neurological and Metabolic Research, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, ChinaDepartment of Neuroendocrinology, Group of Neuroendocrinology, Garvan Institute of Medical Research, Sydney, AustraliaDepartment of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, ChinaObjectiveIn order to explore the relationship between mammographic density of breast mass and its surrounding area and benign or malignant breast, this paper proposes a deep learning model based on C2FTrans to diagnose the breast mass using mammographic density.MethodsThis retrospective study included patients who underwent mammographic and pathological examination. Two physicians manually depicted the lesion edges and used a computer to automatically extend and segment the peripheral areas of the lesion (0, 1, 3, and 5 mm, including the lesion). We then obtained the mammary glands’ density and the different regions of interest (ROI). A diagnostic model for breast mass lesions based on C2FTrans was constructed based on a 7: 3 ratio between the training and testing sets. Finally, receiver operating characteristic (ROC) curves were plotted. Model performance was assessed using the area under the ROC curve (AUC) with 95% confidence intervals (CI), sensitivity, and specificity.ResultsIn total, 401 lesions (158 benign and 243 malignant) were included in this study. The probability of breast cancer in women was positively correlated with age and mass density and negatively correlated with breast gland classification. The largest correlation was observed for age (r = 0.47). Among all models, the single mass ROI model had the highest specificity (91.8%) with an AUC = 0.823 and the perifocal 5mm ROI model had the highest sensitivity (86.9%) with an AUC = 0.855. In addition, by combining the cephalocaudal and mediolateral oblique views of the perifocal 5 mm ROI model, we obtained the highest AUC (AUC = 0.877 P < 0.001).ConclusionsDeep learning model of mammographic density can better distinguish benign and malignant mass-type lesions in digital mammography images and may become an auxiliary diagnostic tool for radiologists in the future.https://www.frontiersin.org/articles/10.3389/fonc.2023.1110657/fullmammographic densitydeep learning modelconvolutional neural networkregions of interestbreast mass |
| spellingShingle | Qian-qian Chen Shu-ting Lin Jia-yi Ye Yun-fei Tong Shu Lin Shu Lin Si-qing Cai Diagnostic value of mammography density of breast masses by using deep learning Frontiers in Oncology mammographic density deep learning model convolutional neural network regions of interest breast mass |
| title | Diagnostic value of mammography density of breast masses by using deep learning |
| title_full | Diagnostic value of mammography density of breast masses by using deep learning |
| title_fullStr | Diagnostic value of mammography density of breast masses by using deep learning |
| title_full_unstemmed | Diagnostic value of mammography density of breast masses by using deep learning |
| title_short | Diagnostic value of mammography density of breast masses by using deep learning |
| title_sort | diagnostic value of mammography density of breast masses by using deep learning |
| topic | mammographic density deep learning model convolutional neural network regions of interest breast mass |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1110657/full |
| work_keys_str_mv | AT qianqianchen diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT shutinglin diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT jiayiye diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT yunfeitong diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT shulin diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT shulin diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning AT siqingcai diagnosticvalueofmammographydensityofbreastmassesbyusingdeeplearning |