General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification

TL;DR

This study compares the effectiveness of domain-specific versus general-purpose pre-trained CNNs for brain MRI tumor classification, revealing that modern general CNNs outperform domain-specific models in limited data scenarios.

Contribution

It provides a comparative analysis showing that general-purpose CNNs can outperform domain-specific models in medical imaging tasks with limited data.

Findings

ConvNeXt-Tiny achieved 93% accuracy

General CNNs outperformed domain-specific models

Pre-training on diverse datasets can be more effective

Abstract

The accurate identification of brain tumors from magnetic resonance imaging (MRI) is essential for timely diagnosis and effective therapeutic intervention. While deep convolutional neural networks (CNNs), particularly those pre-trained on extensive datasets, have shown considerable promise in medical image analysis, a key question arises when working with limited data: do models pre-trained on specialized medical image repositories outperform those pre-trained on diverse, general-domain datasets? This research presents a comparative analysis of three distinct pre-trained CNN architectures for brain tumor classification: RadImageNet DenseNet121, which leverages pre-training on medical-domain data, alongside two modern general-purpose networks, EfficientNetV2S and ConvNeXt-Tiny. All models were trained and fine-tuned under uniform experimental conditions using a modestly sized brain MRI dataset to maintain consistency in evaluation. The experimental outcomes indicate that ConvNeXt-Tiny delivered the best performance, achieving 93% test accuracy, followed by EfficientNetV2S at 85%. In contrast, RadImageNet DenseNet121 attained only 68% accuracy and exhibited higher loss, indicating limited generalization capability despite its domain-specific pre-training. These observations imply that pre-training on medical-domain data does not necessarily guarantee superior performance in data-scarce scenarios. Conversely, contemporary general-purpose CNNs with deeper architectures, pre-trained on large-scale diverse datasets, may offer more effective transfer learning for specialized diagnostic tasks in medical imaging.