Realism in Action: Anomaly-Aware Diagnosis of Brain Tumors from Medical Images Using YOLOv8 and DeiT

TL;DR

This paper introduces a robust, anomaly-aware brain tumor diagnosis framework combining YOLOv8 detection and DeiT classification, tailored for imbalanced clinical data and evaluated with a novel patient-level reliability metric.

Contribution

It presents a clinically inspired, end-to-end tumor detection and classification system using YOLOv8 and knowledge distillation with DeiT, addressing low incidence rates and data imbalance.

Findings

YOLOv8n achieved high detection accuracy on imbalanced MRI data.

DeiT student model attained an F1-score of 0.92 after 20 epochs.

The framework demonstrates robustness in realistic clinical scenarios.

Abstract

Reliable diagnosis of brain tumors remains challenging due to low clinical incidence rates of such cases. However, this low rate is neglected in most of proposed methods. We propose a clinically inspired framework for anomaly-resilient tumor detection and classification. Detection leverages YOLOv8n fine-tuned on a realistically imbalanced dataset (1:9 tumor-to-normal ratio; 30,000 MRI slices from 81 patients). In addition, we propose a novel Patient-to-Patient (PTP) metric that evaluates diagnostic reliability at the patient level. Classification employs knowledge distillation: a Data Efficient Image Transformer (DeiT) student model is distilled from a ResNet152 teacher. The distilled ViT achieves an F1-score of 0.92 within 20 epochs, matching near teacher performance (F1=0.97) with significantly reduced computational resources. This end-to-end framework demonstrates high robustness in clinically representative anomaly-distributed data, offering a viable tool that adheres to realistic situations in clinics.