Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images
Mammography images contain a lot of information about not only the mammary glands but also the skin, adipose tissue, and stroma, which may reflect the risk of developing breast cancer. We aimed to establish a method to predict breast cancer risk using radiomics features of mammography images and to...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Journal of Personalized Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4426/13/11/1528 |
_version_ | 1797458693750521856 |
---|---|
author | Yusuke Suzuki Shouhei Hanaoka Masahiko Tanabe Takeharu Yoshikawa Yasuyuki Seto |
author_facet | Yusuke Suzuki Shouhei Hanaoka Masahiko Tanabe Takeharu Yoshikawa Yasuyuki Seto |
author_sort | Yusuke Suzuki |
collection | DOAJ |
description | Mammography images contain a lot of information about not only the mammary glands but also the skin, adipose tissue, and stroma, which may reflect the risk of developing breast cancer. We aimed to establish a method to predict breast cancer risk using radiomics features of mammography images and to enable further examinations and prophylactic treatment to reduce breast cancer mortality. We used mammography images of 4000 women with breast cancer and 1000 healthy women from the ‘starting point set’ of the OPTIMAM dataset, a public dataset. We trained a Light Gradient Boosting Machine using radiomics features extracted from mammography images of women with breast cancer (only the healthy side) and healthy women. This model was a binary classifier that could discriminate whether a given mammography image was of the contralateral side of women with breast cancer or not, and its performance was evaluated using five-fold cross-validation. The average area under the curve for five folds was 0.60122. Some radiomics features, such as ‘wavelet-H_glcm_Correlation’ and ‘wavelet-H_firstorder_Maximum’, showed distribution differences between the malignant and normal groups. Therefore, a single radiomics feature might reflect the breast cancer risk. The odds ratio of breast cancer incidence was 7.38 in women whose estimated malignancy probability was ≥0.95. Radiomics features from mammography images can help predict breast cancer risk. |
first_indexed | 2024-03-09T16:40:49Z |
format | Article |
id | doaj.art-1b35cbf43e6a4a2f8bd4c0b8d23ccd06 |
institution | Directory Open Access Journal |
issn | 2075-4426 |
language | English |
last_indexed | 2024-03-09T16:40:49Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Personalized Medicine |
spelling | doaj.art-1b35cbf43e6a4a2f8bd4c0b8d23ccd062023-11-24T14:51:16ZengMDPI AGJournal of Personalized Medicine2075-44262023-10-011311152810.3390/jpm13111528Predicting Breast Cancer Risk Using Radiomics Features of Mammography ImagesYusuke Suzuki0Shouhei Hanaoka1Masahiko Tanabe2Takeharu Yoshikawa3Yasuyuki Seto4Department of Breast and Endocrine Surgery, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, JapanDepartment of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, JapanDepartment of Breast and Endocrine Surgery, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, JapanDepartment of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, JapanDepartment of Breast and Endocrine Surgery, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, JapanMammography images contain a lot of information about not only the mammary glands but also the skin, adipose tissue, and stroma, which may reflect the risk of developing breast cancer. We aimed to establish a method to predict breast cancer risk using radiomics features of mammography images and to enable further examinations and prophylactic treatment to reduce breast cancer mortality. We used mammography images of 4000 women with breast cancer and 1000 healthy women from the ‘starting point set’ of the OPTIMAM dataset, a public dataset. We trained a Light Gradient Boosting Machine using radiomics features extracted from mammography images of women with breast cancer (only the healthy side) and healthy women. This model was a binary classifier that could discriminate whether a given mammography image was of the contralateral side of women with breast cancer or not, and its performance was evaluated using five-fold cross-validation. The average area under the curve for five folds was 0.60122. Some radiomics features, such as ‘wavelet-H_glcm_Correlation’ and ‘wavelet-H_firstorder_Maximum’, showed distribution differences between the malignant and normal groups. Therefore, a single radiomics feature might reflect the breast cancer risk. The odds ratio of breast cancer incidence was 7.38 in women whose estimated malignancy probability was ≥0.95. Radiomics features from mammography images can help predict breast cancer risk.https://www.mdpi.com/2075-4426/13/11/1528breast cancerLight GBMmammographyradiomicsrisk prediction |
spellingShingle | Yusuke Suzuki Shouhei Hanaoka Masahiko Tanabe Takeharu Yoshikawa Yasuyuki Seto Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images Journal of Personalized Medicine breast cancer Light GBM mammography radiomics risk prediction |
title | Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images |
title_full | Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images |
title_fullStr | Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images |
title_full_unstemmed | Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images |
title_short | Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images |
title_sort | predicting breast cancer risk using radiomics features of mammography images |
topic | breast cancer Light GBM mammography radiomics risk prediction |
url | https://www.mdpi.com/2075-4426/13/11/1528 |
work_keys_str_mv | AT yusukesuzuki predictingbreastcancerriskusingradiomicsfeaturesofmammographyimages AT shouheihanaoka predictingbreastcancerriskusingradiomicsfeaturesofmammographyimages AT masahikotanabe predictingbreastcancerriskusingradiomicsfeaturesofmammographyimages AT takeharuyoshikawa predictingbreastcancerriskusingradiomicsfeaturesofmammographyimages AT yasuyukiseto predictingbreastcancerriskusingradiomicsfeaturesofmammographyimages |