Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features
PurposeTo develop nomograms for predicting breast malignancy in BI-RADS ultrasound (US) category 4 or 5 lesions based on radiomics features.MethodsBetween January 2020 and January 2022, we prospectively collected and retrospectively analyzed the medical records of 496 patients pathologically proven...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-09-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.894476/full |
_version_ | 1798000474107936768 |
---|---|
author | Zhi-Liang Hong Zhi-Liang Hong Sheng Chen Sheng Chen Xiao-Rui Peng Jian-Wei Li Jian-Wei Li Jian-Chuan Yang Jian-Chuan Yang Song-Song Wu Song-Song Wu |
author_facet | Zhi-Liang Hong Zhi-Liang Hong Sheng Chen Sheng Chen Xiao-Rui Peng Jian-Wei Li Jian-Wei Li Jian-Chuan Yang Jian-Chuan Yang Song-Song Wu Song-Song Wu |
author_sort | Zhi-Liang Hong |
collection | DOAJ |
description | PurposeTo develop nomograms for predicting breast malignancy in BI-RADS ultrasound (US) category 4 or 5 lesions based on radiomics features.MethodsBetween January 2020 and January 2022, we prospectively collected and retrospectively analyzed the medical records of 496 patients pathologically proven breast lesions in our hospital. The data set was divided into model training group and validation testing group with a 75/25 split. Radiomics features were obtained using the PyRadiomics package, and the radiomics score was established by least absolute shrinkage and selection operator regression. A nomogram was developed for BI-RADS US category 4 or 5 lesions according to the results of multivariate regression analysis from the training group.ResultThe AUCs of radiomics score consisting of 31 US features was 0.886. The AUC of the model constructed with radiomics score, patient age, lesion diameter identified by US and BI-RADS category involved was 0.956 (95% CI, 0.910–0.972) for the training group and 0.937 (95% CI, 0.893–0.965) for the validation cohort. The calibration curves showed good agreement between the predictions and observations.ConclusionsBoth nomogram and radiomics score can be used as methods to assist radiologists and clinicians in predicting breast malignancy in BI-RADS US category 4 or 5 lesions. |
first_indexed | 2024-04-11T11:20:51Z |
format | Article |
id | doaj.art-a8fa9e64ece943d49b8d962baab69a40 |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-04-11T11:20:51Z |
publishDate | 2022-09-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-a8fa9e64ece943d49b8d962baab69a402022-12-22T04:27:02ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-09-011210.3389/fonc.2022.894476894476Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics featuresZhi-Liang Hong0Zhi-Liang Hong1Sheng Chen2Sheng Chen3Xiao-Rui Peng4Jian-Wei Li5Jian-Wei Li6Jian-Chuan Yang7Jian-Chuan Yang8Song-Song Wu9Song-Song Wu10Shengli Clinical Medical College of Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, Fujian Provincial Hospital, Fuzhou, ChinaShengli Clinical Medical College of Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, Fujian Provincial Hospital, Fuzhou, ChinaClinical Skills Teaching Center, Fujian Medical University, Fuzhou, ChinaShengli Clinical Medical College of Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, Fujian Provincial Hospital, Fuzhou, ChinaShengli Clinical Medical College of Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, Fujian Provincial Hospital, Fuzhou, ChinaShengli Clinical Medical College of Fujian Medical University, Fuzhou, ChinaDepartment of Ultrasound, Fujian Provincial Hospital, Fuzhou, ChinaPurposeTo develop nomograms for predicting breast malignancy in BI-RADS ultrasound (US) category 4 or 5 lesions based on radiomics features.MethodsBetween January 2020 and January 2022, we prospectively collected and retrospectively analyzed the medical records of 496 patients pathologically proven breast lesions in our hospital. The data set was divided into model training group and validation testing group with a 75/25 split. Radiomics features were obtained using the PyRadiomics package, and the radiomics score was established by least absolute shrinkage and selection operator regression. A nomogram was developed for BI-RADS US category 4 or 5 lesions according to the results of multivariate regression analysis from the training group.ResultThe AUCs of radiomics score consisting of 31 US features was 0.886. The AUC of the model constructed with radiomics score, patient age, lesion diameter identified by US and BI-RADS category involved was 0.956 (95% CI, 0.910–0.972) for the training group and 0.937 (95% CI, 0.893–0.965) for the validation cohort. The calibration curves showed good agreement between the predictions and observations.ConclusionsBoth nomogram and radiomics score can be used as methods to assist radiologists and clinicians in predicting breast malignancy in BI-RADS US category 4 or 5 lesions.https://www.frontiersin.org/articles/10.3389/fonc.2022.894476/fullbreast cancerradiomicsultrasoundnomogramsBI-RADS |
spellingShingle | Zhi-Liang Hong Zhi-Liang Hong Sheng Chen Sheng Chen Xiao-Rui Peng Jian-Wei Li Jian-Wei Li Jian-Chuan Yang Jian-Chuan Yang Song-Song Wu Song-Song Wu Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features Frontiers in Oncology breast cancer radiomics ultrasound nomograms BI-RADS |
title | Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features |
title_full | Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features |
title_fullStr | Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features |
title_full_unstemmed | Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features |
title_short | Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features |
title_sort | nomograms for prediction of breast cancer in breast imaging reporting and data system bi rads ultrasound category 4 or 5 lesions a single center retrospective study based on radiomics features |
topic | breast cancer radiomics ultrasound nomograms BI-RADS |
url | https://www.frontiersin.org/articles/10.3389/fonc.2022.894476/full |
work_keys_str_mv | AT zhilianghong nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT zhilianghong nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT shengchen nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT shengchen nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT xiaoruipeng nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT jianweili nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT jianweili nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT jianchuanyang nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT jianchuanyang nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT songsongwu nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures AT songsongwu nomogramsforpredictionofbreastcancerinbreastimagingreportinganddatasystembiradsultrasoundcategory4or5lesionsasinglecenterretrospectivestudybasedonradiomicsfeatures |