In a significant advancement at the junction of artificial intelligence and healthcare, Tobi Titus Oyekanmi, a computer scientist from New Mexico Highlands University, has introduced a deep learning model poised to transform the diagnosis of brain cancer, especially in areas with limited resources. His research, titled “Deep Learning-Based Diagnosis of Brain Cancer Using Convolutional Neural Networks on MRI Scans: A Comparative Study of Model Architectures and Tumor Classification Accuracy,” features the innovative LightBT-CNN system which has achieved an impressive 98% diagnostic accuracy on MRI scans.
This study, published in the American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), positions Oyekanmi at the forefront of the burgeoning field of explainable artificial intelligence (XAI) applied to medical imaging. Brain cancer is among the most lethal cancers worldwide, with its diagnosis often reliant on the manual interpretation of MRI scans, a method that can be lengthy and susceptible to inaccuracies.
Oyekanmi stated, “AI can help level the playing field. The goal was to build a lightweight yet powerful neural network that can analyze brain MRI scans with accuracy comparable to expert radiologists but without the need for expensive infrastructure.” To accomplish this, he spearheaded a multidisciplinary team including Peter Adigun, Nelson Azeez, and Ayodeji Adeniyi, developing the LightBT-CNN. This convolutional neural network is capable of classifying four types of tumors: glioma, meningioma, pituitary tumors, and healthy brain scans, using a dataset of over 7,000 MRI images.
In contrast to larger deep learning architectures such as VGG16 or ResNet50, which demand high-end GPUs, Oyekanmi”s model operates with just 3.6 million trainable parameters, rendering it compact and cost-effective, making it particularly suitable for hospitals in developing nations. Constructed using Python and TensorFlow, the model has recorded outstanding precision and recall rates exceeding 95% across all tumor categories.
A notable feature of this model is its interpretability. By employing Gradient-weighted Class Activation Mapping (Grad-CAM), the system visually indicates which brain regions influenced its predictions, offering clinicians clear insights into each diagnosis. Oyekanmi emphasized, “Trust is everything in medicine. If an AI can show why it made a decision, clinicians are more likely to adopt it.”
Despite being based in the United States, Oyekanmi maintains strong ties to Nigerian research networks, collaborating with physicist Nelson Abimbola Azeez from the University of Abuja. Their joint efforts aim to leverage AI to tackle diagnostic issues across Africa, addressing challenges from brain tumors to pneumonia detection. “This is not just about publishing papers,” Oyekanmi stressed. “It”s about creating practical tools that improve patient outcomes and build local capacity in medical AI.”
His previous work with Adigun and Adeniyi on AI-driven X-ray interpretation for pneumonia detection laid the groundwork for this comprehensive brain cancer initiative, showcasing a consistent dedication to utilizing AI for societal benefits. Earlier in the year, Oyekanmi was honored with the 2025 NIPES Award for Outstanding Contribution to Research and Innovation, conferred by the National Institute of Professional Engineers and Scientists (NIPES). Selected from over 1,200 nominations across four countries, his contributions were recognized for their originality and significant impact.
Oyekanmi remarked, “Recognition from NIPES means a lot to me. It reminds me that impactful research isn”t just about algorithms, it”s about improving lives.” Experts have praised his work for merging academic rigor with practical relevance. The study benchmarks the performance of LightBT-CNN against global standards like ResNet and EfficientNet, demonstrating comparable accuracy with significantly lower computational requirements, a vital benefit for healthcare facilities with limited digital capabilities. “AI doesn”t have to be complicated to be effective. Sometimes simplicity and efficiency matter more than brute-force computation,” Oyekanmi added.
Looking forward, Oyekanmi aims to collaborate with clinical partners to validate the model using real patient data and investigate multi-modal imaging that combines MRI with CT and PET scans. He is also advocating for cross-institutional AI training programs in Nigerian universities to prepare the next generation of scientists with hands-on experience in medical machine learning. “This work reminds us that innovation isn”t confined to big tech companies. With the right vision, collaboration, and compassion, AI can become a tool for equity, helping every patient, everywhere, get the care they deserve,” he reflected.
