Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx
Rationale and Objectives<p>The human epidermal growth factor receptor 2 (HER2) gene status is crucial for determining treatment efficacy. This study assessed preoperative HER2 classification in breast cancer using machine learning based on clinicopathological and MRI characteristics.</p>...
Tallennettuna:
| Päätekijä: | |
|---|---|
| Muut tekijät: | , , , , |
| Julkaistu: |
2025
|
| Aiheet: | |
| Tagit: |
Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!
|
| _version_ | 1849927622684835840 |
|---|---|
| author | Suhong Zhao (10057478) |
| author2 | Zhaohua Li (433864) Yanan Wang (123548) Fang Zhao (11980) Peipei Chen (1605268) Guodong Pang (20927963) |
| author2_role | author author author author author |
| author_facet | Suhong Zhao (10057478) Zhaohua Li (433864) Yanan Wang (123548) Fang Zhao (11980) Peipei Chen (1605268) Guodong Pang (20927963) |
| author_role | author |
| dc.creator.none.fl_str_mv | Suhong Zhao (10057478) Zhaohua Li (433864) Yanan Wang (123548) Fang Zhao (11980) Peipei Chen (1605268) Guodong Pang (20927963) |
| dc.date.none.fl_str_mv | 2025-11-26T06:34:07Z |
| dc.identifier.none.fl_str_mv | 10.3389/fcell.2025.1669651.s001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Data_Sheet_1_Enhancing_preoperative_HER2_status_classification_of_invasive_breast_cancers_using_machine_learning_models_based_on_clinicopathological_and_MRI_features_a_multicenter_study_docx/30718817 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Cell Biology magnetic resonance imaging clinicopathological features breast cancer humanepidermal growth factor 2 machine learning |
| dc.title.none.fl_str_mv | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | Rationale and Objectives<p>The human epidermal growth factor receptor 2 (HER2) gene status is crucial for determining treatment efficacy. This study assessed preoperative HER2 classification in breast cancer using machine learning based on clinicopathological and MRI characteristics.</p>Materials and Methods<p>This retrospective study involved 1,015 patients (1,030 lesions) across two centers. Patients were divided into training, internal validation, and external validation sets. Nomograms were developed using clinicopathological and MRI features. Predictive models were constructed using decision trees (DT), support vector machines (SVM), k-nearest neighbors (k-NN), artificial neural networks (ANN), and multivariable logistic regression (LR). Model performance was evaluated using receiver operating characteristic curves, decision curve analysis, and calibration curves. Model interpretability was achieved by developing nomograms and employing SHAP (SHapley Additive exPlanations) analysis.</p>Results<p>Key variables for distinguishing HER2-positive from HER2-negative cases included regional N category, estrogen receptor, PR (progesterone receptor) status, Ki-67 status, lesion number, distribution quadrant, and accompanying signs. The SVM model achieved the highest AUC of 0.86 (95% confidence interval (CI): 0.81–0.90) in the training set, while the ANN model had an AUC of 0.77 (95% CI: 0.67–0.86) in the internal validation set. In the external validation set, the LR model achieved the highest AUC of 0.66 (95% CI: 0.56–0.76), although the overall performance was modest. For HER2-low versus HER2-zero differentiation, Ki-67 status, lesion number, distribution quadrant, mass shape, early enhancement rate, and ADC (apparent diffusion coefficient) were significant. The SVM model attained the highest AUC of 0.87 (95% CI: 0.83–0.91) in the training set, while the LR model demonstrated superior generalizability, yielding the highest AUCs in both the internal and external validation sets (internal: 0.67, 95% CI: 0.58–0.76; external: 0.74, 95% CI: 0.65–0.83). Radiologists benefited from the nomogram for improved diagnostic accuracy, especially junior radiologists. SHAP analysis revealed that PR status was paramount for HER2-positive classification, whereas mass shape and ADC values were dominant for identifying HER2-low status.</p>Conclusion<p>Integrating machine learning with clinicopathological and MRI characteristics improves the accuracy of HER2 status classification in breast cancer and enhances diagnostic capabilities for radiologists in clinical practice.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_b854d28be1af89e9cdf4b62fc1ff0abb |
| identifier_str_mv | 10.3389/fcell.2025.1669651.s001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30718817 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docxSuhong Zhao (10057478)Zhaohua Li (433864)Yanan Wang (123548)Fang Zhao (11980)Peipei Chen (1605268)Guodong Pang (20927963)Cell Biologymagnetic resonance imagingclinicopathological featuresbreast cancerhumanepidermal growth factor 2machine learningRationale and Objectives<p>The human epidermal growth factor receptor 2 (HER2) gene status is crucial for determining treatment efficacy. This study assessed preoperative HER2 classification in breast cancer using machine learning based on clinicopathological and MRI characteristics.</p>Materials and Methods<p>This retrospective study involved 1,015 patients (1,030 lesions) across two centers. Patients were divided into training, internal validation, and external validation sets. Nomograms were developed using clinicopathological and MRI features. Predictive models were constructed using decision trees (DT), support vector machines (SVM), k-nearest neighbors (k-NN), artificial neural networks (ANN), and multivariable logistic regression (LR). Model performance was evaluated using receiver operating characteristic curves, decision curve analysis, and calibration curves. Model interpretability was achieved by developing nomograms and employing SHAP (SHapley Additive exPlanations) analysis.</p>Results<p>Key variables for distinguishing HER2-positive from HER2-negative cases included regional N category, estrogen receptor, PR (progesterone receptor) status, Ki-67 status, lesion number, distribution quadrant, and accompanying signs. The SVM model achieved the highest AUC of 0.86 (95% confidence interval (CI): 0.81–0.90) in the training set, while the ANN model had an AUC of 0.77 (95% CI: 0.67–0.86) in the internal validation set. In the external validation set, the LR model achieved the highest AUC of 0.66 (95% CI: 0.56–0.76), although the overall performance was modest. For HER2-low versus HER2-zero differentiation, Ki-67 status, lesion number, distribution quadrant, mass shape, early enhancement rate, and ADC (apparent diffusion coefficient) were significant. The SVM model attained the highest AUC of 0.87 (95% CI: 0.83–0.91) in the training set, while the LR model demonstrated superior generalizability, yielding the highest AUCs in both the internal and external validation sets (internal: 0.67, 95% CI: 0.58–0.76; external: 0.74, 95% CI: 0.65–0.83). Radiologists benefited from the nomogram for improved diagnostic accuracy, especially junior radiologists. SHAP analysis revealed that PR status was paramount for HER2-positive classification, whereas mass shape and ADC values were dominant for identifying HER2-low status.</p>Conclusion<p>Integrating machine learning with clinicopathological and MRI characteristics improves the accuracy of HER2 status classification in breast cancer and enhances diagnostic capabilities for radiologists in clinical practice.</p>2025-11-26T06:34:07ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/fcell.2025.1669651.s001https://figshare.com/articles/dataset/Data_Sheet_1_Enhancing_preoperative_HER2_status_classification_of_invasive_breast_cancers_using_machine_learning_models_based_on_clinicopathological_and_MRI_features_a_multicenter_study_docx/30718817CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/307188172025-11-26T06:34:07Z |
| spellingShingle | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx Suhong Zhao (10057478) Cell Biology magnetic resonance imaging clinicopathological features breast cancer humanepidermal growth factor 2 machine learning |
| status_str | publishedVersion |
| title | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| title_full | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| title_fullStr | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| title_full_unstemmed | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| title_short | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| title_sort | Data Sheet 1_Enhancing preoperative HER2 status classification of invasive breast cancers using machine learning models based on clinicopathological and MRI features: a multicenter study.docx |
| topic | Cell Biology magnetic resonance imaging clinicopathological features breast cancer humanepidermal growth factor 2 machine learning |