Multi-modal Analysis of Bi-Parametric MRI Slices for Lesion Detection in Prostate Cancer Screening

Prostate cancer is a leading cause of cancer-related mortality among men, with early detection playing a critical role in improving patient outcomes. While deep learning has significantly advanced prostate cancer detection in Magnetic Resonance Imaging (MRI), most existing models depend on full 3D scans, posing challenges for real-time deployment in clinical practice. Our work addresses this problem by leveraging a slice-based approach that balances accuracy with efficiency, ensuring scalability for real-world applications. We present a dual-branch, multi-modal deep learning framework focusing on individual bi-parametric MRI slices to detect clinically significant prostate cancer areas (csPCa). The proposed approach combines pixel-level segmentation via UNet++ and instance-level classification using EfficientNet to enhance lesion localization and reduce false positives. We evaluated our framework on the PI-CAI (Prostate Imaging: Cancer AI) dataset, achieving perforamances that outperform other 2D segmentation models. The study highlights the feasibility of slice-based MRI analysis for prostate cancer screening in resource-limited clinical settings, highlight the potential of this approach as a clinical decision support tool, reducing interpretation burden and aiding radiologists in prostate cancer screening.