Novel Deep Learning Architectures for Classification and Segmentation of Brain Tumors from MRI Images
Sayan Das, Arghadip Biswas
2025-12-10
Summary
This paper focuses on improving the detection of brain tumors using artificial intelligence, specifically deep learning. It introduces two new computer models designed to both identify the *type* of tumor and precisely outline its boundaries within MRI scans.
What's the problem?
Currently, doctors manually analyze MRI scans to find brain tumors, which is slow and can be difficult, especially as more and more cases appear, particularly in young people. Existing AI models aren't consistently accurate when tested on new data, meaning they don't generalize well and could miss tumors or misdiagnose them. This is a critical issue because early and accurate detection is key for effective treatment.
What's the solution?
The researchers created two new deep learning models. The first, called SAETCN, is designed to classify different types of brain tumors – glioma, meningioma, and pituitary tumors – as well as identify scans without tumors. It achieved a very high accuracy rate of 99.38% when tested. The second model, SAS-Net, focuses on *segmentation*, meaning it precisely outlines the tumor's shape within the MRI image, achieving 99.23% pixel accuracy. Both models use a technique called 'self-attention' to help them focus on the most important parts of the image.
Why it matters?
These new models could significantly speed up and improve the accuracy of brain tumor diagnosis. By automating the process and achieving high accuracy, doctors can make faster, more informed decisions about patient care, potentially leading to better outcomes. The improved accuracy over existing models suggests these could be valuable tools in a clinical setting.
Abstract
Brain tumors pose a significant threat to human life, therefore it is very much necessary to detect them accurately in the early stages for better diagnosis and treatment. Brain tumors can be detected by the radiologist manually from the MRI scan images of the patients. However, the incidence of brain tumors has risen amongst children and adolescents in recent years, resulting in a substantial volume of data, as a result, it is time-consuming and difficult to detect manually. With the emergence of Artificial intelligence in the modern world and its vast application in the medical field, we can make an approach to the CAD (Computer Aided Diagnosis) system for the early detection of Brain tumors automatically. All the existing models for this task are not completely generalized and perform poorly on the validation data. So, we have proposed two novel Deep Learning Architectures - (a) SAETCN (Self-Attention Enhancement Tumor Classification Network) for the classification of different kinds of brain tumors. We have achieved an accuracy of 99.38% on the validation dataset making it one of the few Novel Deep learning-based architecture that is capable of detecting brain tumors accurately. We have trained the model on the dataset, which contains images of 3 types of tumors (glioma, meningioma, and pituitary tumors) and non-tumor cases. and (b) SAS-Net (Self-Attentive Segmentation Network) for the accurate segmentation of brain tumors. We have achieved an overall pixel accuracy of 99.23%.