Enhancing Ductal Carcinoma Classification Using Transfer Learning with 3D U-Net Models in Breast Cancer Imaging

• Published in: Applied sciences Vol. 13; no. 7; p. 4255
• Main Authors: Khalil, Saman, Nawaz, Uroosa, Zubariah, Mushtaq, Zohaib, Arif, Saad, ur Rehman, Muhammad Zia, Qureshi, Muhammad Farrukh, Malik, Abdul, Aleid, Adham, Alhussaini, Khalid
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.03.2023
• Subjects: Accuracy; Artificial intelligence; Breast cancer; breast cancer detection; Cancer; Carcinoma; Classification; Data augmentation; Datasets; Deep learning; Diagnosis; ductal carcinoma; Histopathology; Image processing; intelligent healthcare; Magnetic resonance imaging; Mammography; Medical imaging; MRI; Research design; Transfer learning; Tumors; U-Nets; Ultrasonic imaging; Pakistan
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app13074255

Breast cancer ranks among the leading causes of death for women globally, making it imperative to swiftly and precisely detect the condition to ensure timely treatment and enhanced chances of recovery. This study focuses on transfer learning with 3D U-Net models to classify ductal carcinoma, the most frequent subtype of breast cancer, in histopathology imaging. In this research work, a dataset of 162 microscopic images of breast cancer specimens is utilized for breast histopathology analysis. Preprocessing the original image data includes shrinking the images, standardizing the intensities, and extracting patches of size 50 × 50 pixels. The retrieved patches were employed to construct a basic 3D U-Net model and a refined 3D U-Net model that had been previously trained on an extensive medical image segmentation dataset. The findings revealed that the fine-tuned 3D U-Net model (97%) outperformed the simple 3D U-Net model (87%) in identifying ductal cancer in breast histopathology imaging. The fine-tuned model exhibited a smaller loss (0.003) on the testing data (0.041) in comparison to the simple model. The disparity in the training and testing accuracy reveals that the fine-tuned model may have overfitted to the training data indicating that there is room for improvement. To progress in computer-aided diagnosis, the research study also adopted various data augmentation methodologies. The experimental approach that was put forward achieved state-of-the-art performance, surpassing the benchmark techniques used in previous studies in the same field, and exhibiting greater accuracy. The presented scheme has promising potential for better cancer detection and diagnosis in practical applications of mammography.