A Machine Learning Approach for Breast Cancer Risk Prediction in Digital Mammography DOI Creative Commons
Francesca Angelone, Alfonso Maria Ponsiglione, Carlo Ricciardi

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10315 - 10315

Published: Nov. 9, 2024

Breast cancer is among the most prevalent cancers in female population globally. Therefore, screening campaigns as well approaches to identify patients at risk are particularly important for early detection of suspect lesions. This study aims propose a workflow automatic classification based on one relevant factors breast cancer, which represented by density. The proposed methodology takes advantage features automatically extracted from mammographic images, digital mammography represents major tool women. Textural were parenchyma through radiomics approach, and they used train different machine learning algorithms neural network models classify density according standard Imaging Reporting Data System (BI-RADS) guidelines. Both binary multiclass tasks have been carried out compared terms performance metrics. Preliminary results show interesting accuracy (93.55% task 82.14% task), promising current literature. As relies straightforward computationally efficient algorithms, it could serve basis fast-track protocol mammograms reduce radiologists’ workload.

Language: Английский

Integration of longitudinal load-bearing tissue MRI radiomics and neural network to predict knee osteoarthritis incidence DOI Creative Commons
Tianyu Chen,

Jian Chen,

Hao Liu

et al.

Journal of Orthopaedic Translation, Journal Year: 2025, Volume and Issue: 51, P. 187 - 197

Published: March 1, 2025

Language: Английский

Citations

1
Interpretable machine learning and radiomics in hip MRI diagnostics: comparing ONFH and OA predictions to experts DOI Creative Commons
Tariq Alkhatatbeh,

Ahmad Alkhatatbeh,

Qin Guo

et al.

Frontiers in Immunology, Journal Year: 2025, Volume and Issue: 16

Published: Jan. 29, 2025

Purpose Distinguishing between Osteonecrosis of the femoral head (ONFH) and Osteoarthritis (OA) can be subjective vary users with different backgrounds expertise. This study aimed to construct evaluate several Radiomics-based machine learning models using MRI differentiate those two disorders compare their efficacies medical experts. Methods 140 scans were retrospectively collected from electronic records. They split into training testing sets in a 7:3 ratio. Handcrafted radiomics features harvested following careful manual segmentation regions interest (ROI). After thoroughly selecting these features, various have been constructed. The evaluation was carried out receiver operating characteristic (ROC) curves. Then NaiveBayes (NB) selected establish our final Radiomics-model as it performed best. Three expertise diagnosed labeled dataset either OA or ONFH. Their results compared Radiomics-model. Results amount handcrafted 1197 before processing; after selection, only 12 key retained used. User 1 had an AUC 0.632 (95% CI 0.4801-0.7843), 2 recorded 0.565 0.4102-0.7196); while 3 on top 0.880 0.7753-0.9843). On other hand, Radiomics model attained 0.971 0.9298-1.0000); showing greater efficacy than all users. It also demonstrated sensitivity 0.937 specificity 0.885. DCA (Decision Curve Analysis displayed that radiomics-model clinical benefit differentiating Conclusion We successfully constructed evaluated interpretable radiomics-based could distinguish method has ability aid both junior senior professionals precisely diagnose take prompt treatment measures.

Language: Английский

Citations

0
eXtended Reality and Artificial Intelligence in Medicine and Rehabilitation DOI Creative Commons
Tomas Krilavičius, Lucio Tommaso De Paolis, Valerio De Luca

et al.

Information Systems Frontiers, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 29, 2025

Language: Английский

Citations

0
Classification of Parotid Tumors with Robust Radiomic Features from DCE- and DW-MRI DOI Creative Commons
Francesca Angelone,

Silvia Tortora,

Francesca Patella

et al.

Journal of Imaging, Journal Year: 2025, Volume and Issue: 11(4), P. 122 - 122

Published: April 17, 2025

This study aims to evaluate the role of MRI-based radiomic analysis and machine learning using both DWI with multiple B-values dynamic contrast-enhanced T1-weighted sequences differentiate benign (B) malignant (M) parotid tumors. Patients underwent DCE- DW-MRI. An expert radiologist performed manual selection 3D ROIs. Classification vs. tumors was based on features extracted from DCE-based DW-based parametric maps. Care taken in robustness evaluation no-bias features. Several classifiers were employed. Sensitivity specificity ranged 0.6 0.8. The combination LASSO + neural networks achieved highest performance (0.76 sensitivity 0.75 specificity). Our identified a few robust respect ROI that can effectively be adopted classifying

Language: Английский

Citations

0
A Machine Learning Approach for Breast Cancer Risk Prediction in Digital Mammography DOI Creative Commons
Francesca Angelone, Alfonso Maria Ponsiglione, Carlo Ricciardi

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10315 - 10315

Published: Nov. 9, 2024

Breast cancer is among the most prevalent cancers in female population globally. Therefore, screening campaigns as well approaches to identify patients at risk are particularly important for early detection of suspect lesions. This study aims propose a workflow automatic classification based on one relevant factors breast cancer, which represented by density. The proposed methodology takes advantage features automatically extracted from mammographic images, digital mammography represents major tool women. Textural were parenchyma through radiomics approach, and they used train different machine learning algorithms neural network models classify density according standard Imaging Reporting Data System (BI-RADS) guidelines. Both binary multiclass tasks have been carried out compared terms performance metrics. Preliminary results show interesting accuracy (93.55% task 82.14% task), promising current literature. As relies straightforward computationally efficient algorithms, it could serve basis fast-track protocol mammograms reduce radiologists’ workload.

Language: Английский

Citations

3