article · BMC Medical Informatics and Decision Making
Prostate cancer is the most common cancer affecting men, with outcomes heavily dependent on early detection. However, traditional screening methods often struggle with balancing early detection against overdiagnosis, particularly when medical imaging is difficult to interpret. To address this challenge, a deep learning architecture named the Prostate Cancer Detection Model was developed for automated diagnosis. Built upon a modified ResNet50 framework, the system incorporates faster region-based convolutional neural networks alongside dual optimisers to enhance detection performance. Evaluated on an extensive dataset of annotated medical images, the model surpassed established architectures such as standard ResNet50 and VGG19. It achieved an overall diagnostic accuracy of 95.24 percent, alongside sensitivity of 97.40 percent, specificity of 97.09 percent, and precision of 97.56 percent, demonstrating strong capabilities for assisting clinicians in real-world healthcare settings.
Early diagnosis of prostate cancer significantly improves patient survival, yet interpreting complex medical scans remains difficult and prone to diagnostic debate. By introducing an automated detection model with high sensitivity and accuracy, healthcare providers can better identify cancerous tissue in challenging imaging scenarios. This supports earlier intervention while helping clinicians manage cases more reliably in everyday healthcare environments.
The model is an applied software tool intended to assist clinical teams and healthcare facilities with automated prostate cancer diagnosis and management. Having been trained and validated on a large annotated medical imaging dataset, the technology sits at an applied and tested stage. Further clinical integration could enable diagnostic software vendors to incorporate the architecture into radiology decision-support platforms for routine hospital use.
AI-generated from the published abstract. Always read the original work before citing.
Prostate cancer, the most common cancer in men, is influenced by age, family history, genetics, and lifestyle factors. Early detection of prostate cancer using screening methods improves outcomes, but the balance between overdiagnosis and early detection remains debated. Using Deep Learning (DL) algorithms for prostate cancer detection offers a promising solution for accurate and efficient diagnosis, particularly in cases where prostate imaging is challenging. In this paper, we propose a Prostate Cancer Detection Model (PCDM) model for the automatic diagnosis of prostate cancer. It proves its clinical applicability to aid in the early detection and management of prostate cancer in real-world healthcare environments. The PCDM model is a modified ResNet50-based architecture that integrates faster R-CNN and dual optimizers to improve the performance of the detection process. The model is trained on a large dataset of annotated medical images, and the experimental results show that the proposed model outperforms both ResNet50 and VGG19 architectures. Specifically, the proposed model achieves high sensitivity, specificity, precision, and accuracy rates of 97.40%, 97.09%, 97.56%, and 95.24%, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s12911-024-02419-0
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
