Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer
Purpose The purpose of this study was to evaluate the predictive performance of ultrasonography (US)-based radiomics for axillary lymph node metastasis and to compare it with that of a clinicopathologic model. Methods A total of 496 patients (mean age, 52.5±10.9 years) who underwent breast cancer su...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Society of Ultrasound in Medicine
2021-01-01
|
| Series: | Ultrasonography |
| Subjects: | |
| Online Access: | http://www.e-ultrasonography.org/upload/usg-20026.pdf |
| _version_ | 1818383626816978944 |
|---|---|
| author | Si Eun Lee Yongsik Sim Sungwon Kim Eun-Kyung Kim |
| author_facet | Si Eun Lee Yongsik Sim Sungwon Kim Eun-Kyung Kim |
| author_sort | Si Eun Lee |
| collection | DOAJ |
| description | Purpose The purpose of this study was to evaluate the predictive performance of ultrasonography (US)-based radiomics for axillary lymph node metastasis and to compare it with that of a clinicopathologic model. Methods A total of 496 patients (mean age, 52.5±10.9 years) who underwent breast cancer surgery between January 2014 and December 2014 were included in this study. Among them, 306 patients who underwent surgery between January 2014 and August 2014 were enrolled as a training cohort, and 190 patients who underwent surgery between September 2014 and December 2014 were enrolled as a validation cohort. To predict axillary lymph node metastasis in breast cancer, we developed a preoperative clinicopathologic model using multivariable logistic regression and constructed a radiomics model using 23 radiomic features selected via least absolute shrinkage and selection operator regression. Results In the training cohort, the areas under the curve (AUC) were 0.760, 0.812, and 0.858 for the clinicopathologic, radiomics, and combined models, respectively. In the validation cohort, the AUCs were 0.708, 0.831, and 0.810, respectively. The combined model showed significantly better diagnostic performance than the clinicopathologic model. Conclusion A radiomics model based on the US features of primary breast cancers showed additional value when combined with a clinicopathologic model to predict axillary lymph node metastasis. |
| first_indexed | 2024-12-14T03:09:22Z |
| format | Article |
| id | doaj.art-dcd3a0c72da84417a8ce598168f2bb96 |
| institution | Directory Open Access Journal |
| issn | 2288-5919 2288-5943 |
| language | English |
| last_indexed | 2024-12-14T03:09:22Z |
| publishDate | 2021-01-01 |
| publisher | Korean Society of Ultrasound in Medicine |
| record_format | Article |
| series | Ultrasonography |
| spelling | doaj.art-dcd3a0c72da84417a8ce598168f2bb962022-12-21T23:19:19ZengKorean Society of Ultrasound in MedicineUltrasonography2288-59192288-59432021-01-014019310210.14366/usg.200261103Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancerSi Eun Lee0Yongsik Sim1Sungwon Kim2Eun-Kyung Kim3 Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, Seoul, Korea Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, Seoul, Korea Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, Seoul, Korea Department of Radiology, Severance Hospital, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, Seoul, KoreaPurpose The purpose of this study was to evaluate the predictive performance of ultrasonography (US)-based radiomics for axillary lymph node metastasis and to compare it with that of a clinicopathologic model. Methods A total of 496 patients (mean age, 52.5±10.9 years) who underwent breast cancer surgery between January 2014 and December 2014 were included in this study. Among them, 306 patients who underwent surgery between January 2014 and August 2014 were enrolled as a training cohort, and 190 patients who underwent surgery between September 2014 and December 2014 were enrolled as a validation cohort. To predict axillary lymph node metastasis in breast cancer, we developed a preoperative clinicopathologic model using multivariable logistic regression and constructed a radiomics model using 23 radiomic features selected via least absolute shrinkage and selection operator regression. Results In the training cohort, the areas under the curve (AUC) were 0.760, 0.812, and 0.858 for the clinicopathologic, radiomics, and combined models, respectively. In the validation cohort, the AUCs were 0.708, 0.831, and 0.810, respectively. The combined model showed significantly better diagnostic performance than the clinicopathologic model. Conclusion A radiomics model based on the US features of primary breast cancers showed additional value when combined with a clinicopathologic model to predict axillary lymph node metastasis.http://www.e-ultrasonography.org/upload/usg-20026.pdfbreast neoplasmslymph nodesultrasonographycomputer-aided designpreoperative period |
| spellingShingle | Si Eun Lee Yongsik Sim Sungwon Kim Eun-Kyung Kim Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer Ultrasonography breast neoplasms lymph nodes ultrasonography computer-aided design preoperative period |
| title | Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| title_full | Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| title_fullStr | Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| title_full_unstemmed | Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| title_short | Predictive performance of ultrasonography-based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| title_sort | predictive performance of ultrasonography based radiomics for axillary lymph node metastasis in the preoperative evaluation of breast cancer |
| topic | breast neoplasms lymph nodes ultrasonography computer-aided design preoperative period |
| url | http://www.e-ultrasonography.org/upload/usg-20026.pdf |
| work_keys_str_mv | AT sieunlee predictiveperformanceofultrasonographybasedradiomicsforaxillarylymphnodemetastasisinthepreoperativeevaluationofbreastcancer AT yongsiksim predictiveperformanceofultrasonographybasedradiomicsforaxillarylymphnodemetastasisinthepreoperativeevaluationofbreastcancer AT sungwonkim predictiveperformanceofultrasonographybasedradiomicsforaxillarylymphnodemetastasisinthepreoperativeevaluationofbreastcancer AT eunkyungkim predictiveperformanceofultrasonographybasedradiomicsforaxillarylymphnodemetastasisinthepreoperativeevaluationofbreastcancer |