AUTHOR=Mehmood Mubashar , Abbasi Sadam Hussain , Aurangzeb Khursheed , Majeed Muhammad Faran , Anwar Muhammad Shahid , Alhussein Musaed 

TITLE=A classifier model for prostate cancer diagnosis using CNNs and transfer learning with multi-parametric MRI

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1225490

DOI=10.3389/fonc.2023.1225490

ISSN=2234-943X

ABSTRACT=Prostate cancer (PCa) is a major global concern, particularly for men, emphasizing the urgency of early detection to reduce mortality. As the second leading cause of cancer-related male deaths worldwide, precise and efficient diagnostic methods are crucial. Due to the complexity of high-resolution MRI in PCa, computer-aided diagnostic (CAD) methods have emerged to assist radiologists in identifying anomalies. However, the rapid advancement of medical technology has led to the adoption of deep learning methods. These techniques enhance diagnostic efficiency, reduce observer variability, and consistently outperform traditional approaches. Resource constraints that can distinguish whether a cancer is aggressive or not is a significant problem in PCa treatment. This can lead to over-diagnosis, as statistic shows that the mortality rate for PCa is about 1 in 41 men. This over-diagnosis can cause unnecessary surgeries, chemotherapy, biopsies, radiotherapy, and patient anxiety. The efficient diagnostic approach can reduce these unwarranted and unnecessary practices. This study aims to identify PCa using MRI images by combining deep learning and transfer learning (TL). Researchers have explored numerous CNN-based Deep Learning methods for classifying MRI images related to PCa. In this paper, the authors have developed an approach for the classification of PCa using transfer learning on a limited number of images to achieve high performance and help radiologists instantly identify PCa. The proposed approach adopts the EfficientNet architecture, pre-trained on the ImageNet dataset, and incorporates three branches for feature extraction from different MRI sequences. The extracted features are then combined, significantly enhancing the model's ability to distinguish 1 Mehmood et al.MRI images accurately. The proposed approach can learn more distinctive features in prostate images and correctly identify cancer.