Radiomic Pipelines for Prostate Cancer in External Beam Radiation Therapy: A Review of Methods and Future Directions

Area of Science:

• Oncology
• Medical Imaging
• Data Science

Background:

• Prostate Cancer (PCa) often requires active surveillance due to early asymptomatic nature.
• External Beam Radiotherapy (EBRT) is a key treatment for localized and advanced PCa, but recurrence rates range from 17.4% to 39.4%.
• Radiomics, using image data characterization algorithms, offers quantitative analysis for predicting PCa treatment outcomes.

Purpose of the Study:

• To review original studies on radiomics for Prostate Cancer (PCa) in the context of External Beam Radiotherapy (EBRT).
• To analyze datasets, imaging modalities, segmentation, feature extraction, and model-building methods used in PCa radiomics research.

Main Methods:

• Systematic literature review following PRISMA guidelines.
• Inclusion of 73 original studies on radiomics for PCa and EBRT.
• Analysis of various radiomic workflow components: datasets, imaging, segmentation, feature extraction, and model building.

Main Results:

• Magnetic Resonance Imaging (MRI) is the most common imaging modality for PCa radiomics.
• Computed Tomography (CT), Positron Emission Tomography (PET), and Ultrasound (US) also provide valuable tumor characterization and treatment response insights.
• Radiomic studies frequently utilize small, private datasets without external validation.

Conclusions:

• Current radiomic studies for PCa treated with EBRT suffer from limitations in dataset size, homogeneity, and validation.
• Future research must prioritize collaborative efforts for large, multicentric datasets.
• Standardized methodologies are crucial to realize the full clinical potential of radiomics in PCa management.