Paul Chukwurah ¹, Daniel Chukwurah ², Uthman Oyebanji ³, Ala Al-Kafri ⁴ and Mohammad Alkasasbeh ⁵, ¹ The Owl Therapy Centre, United Kingdom, ² Afrinvest West Africa, Nigeria, ³ SSE Renewables, United Kingdom, ⁴ Teesside University, United Kingdom, ⁵ East Lancashire Hospitals NHS Trust, United Kingdom

Disc bulge happens when the nucleus pulposus pushes outward through the annulus fibrosus and progresses over time, which can result in disc degeneration problems such as spinal stenosis and sciatica. Serious bulges on the disc can put pressure on the surrounding nerve roots, sending pain down the spine and into other body regions. In this paper, a convolutional neural network (CNN) model was developed to diagnose composite axial MRI scans. The dataset used comprises 515 patients who reported lower back pain. It includes the last 3 lumbar spine discs, D3 (L3-L4), D4 (L4-L5), and D5 (L5-S1) for each of the patients. The model achieved remarkable accuracy, recall, precision and F1 score of 89%. Local Interpretable Model-Agnostic Explanations (LIME) was also implemented to explain the model's decision, hence removing the black box problem generally associated with AI models. This ensures the model provides interpretable insights, making it accurate and reliable.

Artificial Intelligence, Convolutional Neural Networks, Disc Bulge, Interpretable Diagnosis.