# CerevianNet: parameter efficient multi-class brain tumor classification using custom lightweight CNN

## TL;DR

A new lightweight CNN model is developed for brain tumor classification, achieving high accuracy with fewer resources and faster training.

## Contribution

The novel lightweight CNN model achieves 98% accuracy with 4.1× fewer parameters than other top models.

## Key findings

- The custom lightweight CNN achieved 98% accuracy with significantly fewer parameters and reduced training time.
- EfficientNetb3 achieved the highest accuracy of 99.11% across datasets.
- The model performed best on larger datasets but struggled with smaller and imbalanced ones.

## Abstract

Brain tumors are a life-threatening condition, and their early detection is crucial for effective treatment and improved survival rates. Traditional manual evaluation techniques, such as expert radiologist assessments and visual inspections, are widely used for diagnosing brain tumors. While these methods can be highly reliable, they are often time-consuming, prone to human error, and challenging to scale for large datasets. Consequently, there is a growing demand for Computer-Aided Diagnostic (CAD) systems to overcome these limitations and deliver fast, accurate, and scalable solutions. Despite these promising advancements, the study highlights potential limitations, including susceptibility to overfitting due to the limited availability of labeled data and the need for extensive hyperparameter tuning to generalize across diverse datasets. This study proposes a scalable multi-class brain tumor classification framework optimized for small-form-factor devices. We introduced a novel, lightweight custom convolutional neural network (CNN) that maintains high classification accuracy while significantly reducing computational complexity. We evaluated the model's capacity by training and testing it on five different datasets, and it performed well on all five. We observed a significant improvement in performance with the model on larger datasets, but it struggled with smaller and imbalanced datasets. We achieved significant scores on the datasets, and we had the highest testing accuracy on Dataset-5 (99.67% training accuracy, 98.17% validation accuracy, and 98.30% testing accuracy). What is important to note is that we had the lowest testing accuracy on Dataset-3 (99.99% training accuracy, 74.11% validation accuracy, and 75.63% testing accuracy). The proposed framework leverages state-of-the-art pretrained deep learning models, including EfficientNetb3, ResNet-101, ResNet-50, Xception, AlexNet, DenseNet121, Swin Transformer, and our custom lightweight CNN model. Experimental evaluations demonstrate that EfficientNetb3 achieves the highest accuracy of 99.11%, while the custom lightweight CNN attains 98% accuracy with 4.1 × fewer parameters and reduced training time. These results highlight the effectiveness of computer-aided approaches in achieving near-expert performance, making them suitable for integration into clinical workflows. This research paves the way for deploying efficient and scalable deep learning models in real-world medical applications, thereby expanding accessibility to accurate brain tumor diagnosis.