Introduction: This study investigates advanced deep learning methods to improve the detection of periportal fibrosis (PPF) in medical imaging. Schistosoma mansoni infection affects over 54 million individuals globally, predominantly in sub-Saharan Africa, with around 20 million experiencing chronic complications. PPF, present in up to 42% of these cases, is a leading outcome of chronic liver disease, significantly contributing to morbidity and mortality. Early and accurate detection is critical for timely intervention, yet conventional ultrasound diagnosis remains highly operator-dependent. We developed a convolutional neural network (CNN) model trained on non-invasive ultrasound images to automatically identify and classify PPF severity.

Methods: This research leveraged a CNN for automated detection of PPF. The model was trained and evaluated on a curated subset of 200 ultrasound images from a total pool of 371 images, evenly split between cases and controls, and sourced from the U-SMRC study, which investigates risk factors associated with advanced schistosomiasis morbidity in Lake Albert and Lake Victoria. Images were annotated according to the Niamey protocol, where a pattern score of ≥2 denoted the presence of PPF. The dataset was randomly split into training (80%) and validation (20%) sets to optimize performance.

Results: The approach achieved a diagnostic accuracy of 80%, with a sensitivity and specificity of 80% and 84%, respectively.

Conclusion: These findings highlight the potential of deep learning to reduce diagnostic subjectivity and support scalable screening programs. Future work will focus on validation with larger datasets and multi-class fibrosis grading to enhance clinical utility.