25gmds188 10.3205/25gmds188 urn:nbn:de:0183-25gmds1882 Meeting Abstract Alickovic Alickovic Fatma F

Institute of Medical Biostatistics, Epidemiology and Informatics (IMBEI), University Medical Center, Johannes Gutenberg University Mainz, Mainz, Germany

author Khan Khan Tamsila T author van de Vooren van de Vooren Wim W author Warm Warm Mathias M

University of Cologne, Medical Faculty and University Clinic of Cologne, Center for Integrated Oncology Aachen Bonn Cologne Düsseldorf, Department of Gynecology and Gynecologic Oncology, Cologne, Germany Breast Center, Municipal Hospital Holweide, Cologne, Germany

author Eichler Eichler Christian C

University of Cologne, Medical Faculty and University Clinic of Cologne, Center for Integrated Oncology Aachen Bonn Cologne Düsseldorf, Department of Gynecology and Gynecologic Oncology, Cologne, Germany Breast Center, St. Franziskus Hospital Münster, Münster, Germany

author Malter Malter Wolfram W

University of Cologne, Medical Faculty and University Clinic of Cologne, Center for Integrated Oncology Aachen Bonn Cologne Düsseldorf, Department of Gynecology and Gynecologic Oncology, Cologne, Germany

author Fischer Fischer Lotta A. LA

Breast Center, Municipal Hospital Holweide, Cologne, Germany

author German Medical Science GMS Publishing House

Düsseldorf

610 deep convolutional neural network ResNet-50 model U-Net breast cancer breast ultrasound medical imaging computer-aided diagnosis (CAD) 20260401 engl This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 License. Dieser Artikel ist ein Open-Access-Artikel und steht unter den Lizenzbedingungen der Creative Commons Attribution 4.0 License (Namensnennung). M0631 188 Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie 70. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (GMDS) V: Bilddaten Jena 20250907 20250911 Abstr. 72 TextIntroduction: Breast cancer remains the most prevalent cancer among women, making early detection critical for reducing mortality rates. Ultrasound imaging is a valuable diagnostic tool due to its accessibility and non-invasiveness; however, its accuracy depends heavily on the expertise of the sonographers, which may lead to diagnostic errors . To address this challenge and support clinicians, particularly those with limited experience, a prototype computer-aided diagnosis (CAD) tool is proposed that integrates deep convolutional neural networks (DCNNs) for breast lesion classification and segmentation in ultrasound images.Methods: The classification model is based on a dual-path convolutional neural network (DPCNN) , which utilizes a pre-trained ResNet-50 backbone, leveraging transfer learning to improve performance with limited data. To delineate the contours of the lesions, we implemented a U-Net model by Baccouche et al. for segmentation. The models were trained on a curated dataset comprising 1,120 ultrasound images from 218 patients, covering three BI-RADS categories: B1, B2, and B5. The ground truth masks were generated through a hybrid approach combining manual annotation and Meta AI’s Segment Anything tool. In order to mitigate overfitting, a range of data augmentation techniques such as random rotations (±10%), random zoom (±20%), horizontal mirroring, and combinations of these transformations were applied.Results: The classification model achieved a sensitivity and positive predictive value (PPV) of 99.4%, thereby affirming its reliability in differentiating between benign and malignant lesions. Moreover, the U-Net segmentation model yielded a Dice coefficient of 97.3%, indicating high spatial accuracy in lesion segmentation. The prototype provides visual and probabilistic feedback through a user-friendly interface, marking the lesion area and displaying the model's confidence scores. However, the prototype's performance on the external BUSI dataset dropped significantly (accuracy: 60%, Dice: 17%), highlighting challenges in model generalizability due to domain-specific differences.Discussion: A comparison of the prototype's performance with commercially available systems, such as Samsung’s S-Detect tool (sensitivity: 95.8%, specificity: 62–93.8%) and the research-based segmentation model by Baccouche et al. (Dice > 95%), reveals that our prototype demonstrates competitive results despite the limited dataset. Nevertheless, differences in dataset composition and model architecture preclude direct comparison. Identified limitations include the restricted spectrum of BI-RADS categories and a certain degree of similarity between the training and test datasets due to the limited number of patients, which may contribute to optimistic performance estimates.Conclusion: This study presents a deep learning-based CAD prototype for the analysis of breast ultrasound images, incorporating lesion classification and segmentation. Despite strong internal performance, external validation results emphasize the need for broader datasets and cross-device training to ensure clinical robustness. Future efforts should focus on expanding the dataset to cover the full BI-RADS spectrum and performing evaluations across multiple imaging devices to enhance model generalizability.The authors declare that they have no competing interests.The authors declare that a positive ethics committee vote has been obtained. Brunetti N Calabrese M Martinoli C Tagliafico AS Artificial Intelligence in Breast Ultrasound: From Diagnosis to Prognosis — A Rapid Review 2021 J Ultrasound 11–21 Brunetti N, Calabrese M, Martinoli C, Tagliafico AS. Artificial Intelligence in Breast Ultrasound: From Diagnosis to Prognosis — A Rapid Review. J Ultrasound. 2021;25(1):11–21. Shahzad A Mushtaq A Sabeeh AQ Ghadi YY Mushtaq Z Arif S Automated Uterine Fibroids Detection in Ultrasound Images Using Deep Convolutional Neural Networks 2023 Healthcare (Basel) 1–14 Shahzad A, Mushtaq A, Sabeeh AQ, Ghadi YY, Mushtaq Z, Arif S, et al. Automated Uterine Fibroids Detection in Ultrasound Images Using Deep Convolutional Neural Networks. Healthcare (Basel). 2023;11(6):1–14. Baccouche A Garcia-Zapirain B Castillo Olea C Elmaghraby AS Connected-UNets: a deep learning architecture for breast mass segmentation 2021 NPJ breast cancer 151 Baccouche A, Garcia-Zapirain B, Castillo Olea C, Elmaghraby AS. Connected-UNets: a deep learning architecture for breast mass segmentation. NPJ breast cancer. 2021;7(1):151. Al-Dhabyani W Gomaa M Khaled H Fahmy A Dataset of breast ultrasound images 2020 Data brief 104863 Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A. Dataset of breast ultrasound images. Data brief. 2020;28:104863. Xia Q Cheng Y Hu J Huang J Yu Y Xie H Differential diagnosis of breast cancer assisted by S-Detect artificial intelligence system 2021 Math Biosci Eng 3680–89 Xia Q, Cheng Y, Hu J, Huang J, Yu Y, Xie H, et al. Differential diagnosis of breast cancer assisted by S-Detect artificial intelligence system. Math Biosci Eng. 2021;18(3):3680–89. 0 0 0 0