Melike Gümüş Değidiben
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Melike Gümüş Değidiben has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Emel Esmerer
Department of Radiology, Basaksehir Cam and Sakura City Hospital, Istanbul, Turkey
1 shared publication - Eren Tahir
Data Science and Big Data Master’s Program, Institute of Science and Technology, Yildiz Technical University, Zeytinburnu, Istanbul 34220, Turkey
1 shared publication - Mehmet Ali Nazlı
Department of Radiology, Basaksehir Cam and Sakura City Hospital, Istanbul, Turkey
1 shared publication - Mert Bal
Department of Mathematical Engineering, Yildiz Technical University, Davutpasa, Istanbul 34220, Turkey
1 shared publication - Merve Soyleyici
Department of Radiology, Basaksehir Cam and Sakura City Hospital, İstanbul, Türkiye
1 shared publication - Meryem Uzun-Per
Istanbul Health and Technology University Department of Computer Engineering
1 shared publication
Latest Publications
- Open Access
- 22 April 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (9) , 1249
An NLP-Driven Framework for Automated Radiology–Pathology Concordance Assessment in Breast Biopsy
Background/Objectives: To develop and assess the feasibility of a natural language processing (NLP) framework for automated assessment of radiology–pathology concordance in breast biopsy using machine learning-based analysis of unstructured reports. Methods: This retrospective study included 766 paired radiology and pathology reports from ultrasound- or mammography-guided breast biopsies (August 2020–May 2024). Reports underwent translation, normalization, tokenization, lemmatization, and synonym expansion, followed by structured encoding of BI-RADS and pathology categories. Three models were trained: a Decision Tree, a LightGBM classifier, and a fine-tuned BioBERT model. Concordance labels were defined by multidisciplinary consensus. Performance metrics included accuracy, sensitivity, specificity, F1-score, area under the curve (AUC), and Cohen’s kappa. SHapley Additive exPlanations (SHAP) analysis was used to identify influential features. Results: Among 766 cases, 707 (92.3%) were concordant and 59 (7.7%) were initially discordant. After excluding B3 lesions (n = 46), 13 true discordant cases remained (1.7%). Including B3 lesions increased clinically non-concordant or indeterminate cases from 1.7% to 7.7%, indicating that the apparent performance of the models is likely sensitive to case definition and dataset composition. BI-RADS 4a was the most common category (31.3%), and benign pathology (B2) accounted for 64.4% of biopsies. Within this dataset, LightGBM yielded the highest apparent AUC (0.999) (however, given the extremely small number of true discordant cases, this estimate is likely unstable and should be interpreted with caution), while BioBERT showed the strongest agreement with expert consensus (κ = 0.89). SHAP analysis identified clinically meaningful terms such as calcification, hypoechoic, ductal, and carcinoma as key contributors to model predictions. Given the very limited number of true discordant cases, these performance estimates are likely unstable and should be regarded as preliminary, requiring validation in larger, multi-center cohorts. Conclusions: This study presents a proof-of-concept NLP-based framework for radiology–pathology concordance assessment. The models showed promising performance in identifying potentially discordant cases; however, given the limited number of true discordant samples, these findings should be considered preliminary and require further validation in larger, multi-center datasets before clinical implementation.
- 22 April 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (9) , 1249
Open AccessAn NLP-Driven Framework for Automated Radiology–Pathology Concordance Assessment in Breast Biopsy
Background/Objectives: To develop and assess the feasibility of a natural language processing (NLP) framework for automated assessment of radiology–pathology concordance in breast biopsy using machine learning-based analysis of unstructured reports. Methods: This retrospective study included 766 paired radiology and pathology reports from ultrasound- or mammography-guided breast biopsies (August 2020–May 2024). Reports underwent translation, normalization, tokenization, lemmatization, and synonym expansion, followed by structured encoding of BI-RADS and pathology categories. Three models were trained: a Decision Tree, a LightGBM classifier, and a fine-tuned BioBERT model. Concordance labels were defined by multidisciplinary consensus. Performance metrics included accuracy, sensitivity, specificity, F1-score, area under the curve (AUC), and Cohen’s kappa. SHapley Additive exPlanations (SHAP) analysis was used to identify influential features. Results: Among 766 cases, 707 (92.3%) were concordant and 59 (7.7%) were initially discordant. After excluding B3 lesions (n = 46), 13 true discordant cases remained (1.7%). Including B3 lesions increased clinically non-concordant or indeterminate cases from 1.7% to 7.7%, indicating that the apparent performance of the models is likely sensitive to case definition and dataset composition. BI-RADS 4a was the most common category (31.3%), and benign pathology (B2) accounted for 64.4% of biopsies. Within this dataset, LightGBM yielded the highest apparent AUC (0.999) (however, given the extremely small number of true discordant cases, this estimate is likely unstable and should be interpreted with caution), while BioBERT showed the strongest agreement with expert consensus (κ = 0.89). SHAP analysis identified clinically meaningful terms such as calcification, hypoechoic, ductal, and carcinoma as key contributors to model predictions. Given the very limited number of true discordant cases, these performance estimates are likely unstable and should be regarded as preliminary, requiring validation in larger, multi-center cohorts. Conclusions: This study presents a proof-of-concept NLP-based framework for radiology–pathology concordance assessment. The models showed promising performance in identifying potentially discordant cases; however, given the limited number of true discordant samples, these findings should be considered preliminary and require further validation in larger, multi-center datasets before clinical implementation.