A novel approach for segmentation and quantitative analysis of breast calcification in mammograms
BackgroundBreast cancer is a major threat to women’s health globally. Early detection of breast cancer is crucial for saving lives. One important early sign is the appearance of breast calcification in mammograms. Accurate segmentation and analysis of calcification can improve diagnosis and prognosi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2024.1281885/full |
| _version_ | 1827293253749178368 |
|---|---|
| author | Yunfei Tong Jianrong Jiang Fang Chen Guanghua Guo Chaoren Zhang Tiana Deng |
| author_facet | Yunfei Tong Jianrong Jiang Fang Chen Guanghua Guo Chaoren Zhang Tiana Deng |
| author_sort | Yunfei Tong |
| collection | DOAJ |
| description | BackgroundBreast cancer is a major threat to women’s health globally. Early detection of breast cancer is crucial for saving lives. One important early sign is the appearance of breast calcification in mammograms. Accurate segmentation and analysis of calcification can improve diagnosis and prognosis. However, small size and diffuse distribution make calcification prone to oversight.PurposeThis study aims to develop an efficient approach for segmenting and quantitatively analyzing breast calcification from mammograms. The goal is to assist radiologists in discerning benign versus malignant lesions to guide patient management.MethodsThis study develops a framework for breast calcification segmentation and analysis using mammograms. A Pro_UNeXt algorithm is proposed to accurately segment calcification lesions by enhancing the UNeXt architecture with a microcalcification detection block, fused-MBConv modules, multiple-loss-function training, and data augmentation. Quantitative features are then extracted from the segmented calcification, including morphology, size, density, and spatial distribution. These features are used to train machine learning classifiers to categorize lesions as malignant or benign.ResultsThe proposed Pro_UNeXt algorithm achieved superior segmentation performance versus UNet and UNeXt models on both public and private mammogram datasets. It attained a Dice score of 0.823 for microcalcification detection on the public dataset, demonstrating its accuracy for small lesions. For quantitative analysis, the extracted calcification features enabled high malignant/benign classification, with AdaBoost reaching an AUC of 0.97 on the private dataset. The consistent results across datasets validate the representative and discerning capabilities of the proposed features.ConclusionThis study develops an efficient framework integrating customized segmentation and quantitative analysis of breast calcification. Pro_UNeXt offers precise localization of calcification lesions. Subsequent feature quantification and machine learning classification provide comprehensive malignant/benign assessment. This end-to-end solution can assist clinicians in early diagnosis, treatment planning, and follow-up for breast cancer patients. |
| first_indexed | 2024-04-24T13:22:26Z |
| format | Article |
| id | doaj.art-4452f14009b549d1aed49f4619cd5101 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-24T13:22:26Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-4452f14009b549d1aed49f4619cd51012024-04-04T12:17:40ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-04-011410.3389/fonc.2024.12818851281885A novel approach for segmentation and quantitative analysis of breast calcification in mammogramsYunfei Tong0Jianrong Jiang1Fang Chen2Guanghua Guo3Chaoren Zhang4Tiana Deng5Shanghai Yanghe Huajian Artificial Intelligence Technology Co., Ltd., Shanghai, ChinaMindong Hospital Affiliated to Fujian Medical University, Ningde, Fujian, ChinaMindong Hospital Affiliated to Fujian Medical University, Ningde, Fujian, ChinaMindong Hospital Affiliated to Fujian Medical University, Ningde, Fujian, ChinaShanghai Yanghe Huajian Artificial Intelligence Technology Co., Ltd., Shanghai, ChinaShanghai Yanghe Huajian Artificial Intelligence Technology Co., Ltd., Shanghai, ChinaBackgroundBreast cancer is a major threat to women’s health globally. Early detection of breast cancer is crucial for saving lives. One important early sign is the appearance of breast calcification in mammograms. Accurate segmentation and analysis of calcification can improve diagnosis and prognosis. However, small size and diffuse distribution make calcification prone to oversight.PurposeThis study aims to develop an efficient approach for segmenting and quantitatively analyzing breast calcification from mammograms. The goal is to assist radiologists in discerning benign versus malignant lesions to guide patient management.MethodsThis study develops a framework for breast calcification segmentation and analysis using mammograms. A Pro_UNeXt algorithm is proposed to accurately segment calcification lesions by enhancing the UNeXt architecture with a microcalcification detection block, fused-MBConv modules, multiple-loss-function training, and data augmentation. Quantitative features are then extracted from the segmented calcification, including morphology, size, density, and spatial distribution. These features are used to train machine learning classifiers to categorize lesions as malignant or benign.ResultsThe proposed Pro_UNeXt algorithm achieved superior segmentation performance versus UNet and UNeXt models on both public and private mammogram datasets. It attained a Dice score of 0.823 for microcalcification detection on the public dataset, demonstrating its accuracy for small lesions. For quantitative analysis, the extracted calcification features enabled high malignant/benign classification, with AdaBoost reaching an AUC of 0.97 on the private dataset. The consistent results across datasets validate the representative and discerning capabilities of the proposed features.ConclusionThis study develops an efficient framework integrating customized segmentation and quantitative analysis of breast calcification. Pro_UNeXt offers precise localization of calcification lesions. Subsequent feature quantification and machine learning classification provide comprehensive malignant/benign assessment. This end-to-end solution can assist clinicians in early diagnosis, treatment planning, and follow-up for breast cancer patients.https://www.frontiersin.org/articles/10.3389/fonc.2024.1281885/fullbreast cancerbreast calcificationsegmentationPro_UNeXtmachine learning |
| spellingShingle | Yunfei Tong Jianrong Jiang Fang Chen Guanghua Guo Chaoren Zhang Tiana Deng A novel approach for segmentation and quantitative analysis of breast calcification in mammograms Frontiers in Oncology breast cancer breast calcification segmentation Pro_UNeXt machine learning |
| title | A novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| title_full | A novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| title_fullStr | A novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| title_full_unstemmed | A novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| title_short | A novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| title_sort | novel approach for segmentation and quantitative analysis of breast calcification in mammograms |
| topic | breast cancer breast calcification segmentation Pro_UNeXt machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2024.1281885/full |
| work_keys_str_mv | AT yunfeitong anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT jianrongjiang anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT fangchen anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT guanghuaguo anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT chaorenzhang anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT tianadeng anovelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT yunfeitong novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT jianrongjiang novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT fangchen novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT guanghuaguo novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT chaorenzhang novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms AT tianadeng novelapproachforsegmentationandquantitativeanalysisofbreastcalcificationinmammograms |