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

• URL: http://arxiv.org/abs/2511.18326v1
• Date: Sun, 23 Nov 2025 07:31:41 GMT
• Title: General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification
• Authors: Helia Abedini, Saba Rahimi, Reza Vaziri,
• Abstract summary: Deep convolutional neural networks (CNNs) have demonstrated strong performance in medical imaging tasks.<n>It remains unclear which type of pretrained model performs better when only a small dataset is available.
• Score: 0.5907996850796289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Brain tumor detection from MRI scans plays a crucial role in early diagnosis and treatment planning. Deep convolutional neural networks (CNNs) have demonstrated strong performance in medical imaging tasks, particularly when pretrained on large datasets. However, it remains unclear which type of pretrained model performs better when only a small dataset is available: those trained on domain-specific medical data or those pretrained on large general datasets. In this study, we systematically evaluate three pretrained CNN architectures for brain tumor classification: RadImageNet DenseNet121 with medical-domain pretraining, EfficientNetV2S, and ConvNeXt-Tiny, which are modern general-purpose CNNs. All models were trained and fine-tuned under identical conditions using a limited-size brain MRI dataset to ensure a fair comparison. Our results reveal that ConvNeXt-Tiny achieved the highest accuracy, followed by EfficientNetV2S, while RadImageNet DenseNet121, despite being pretrained on domain-specific medical data, exhibited poor generalization with lower accuracy and higher loss. These findings suggest that domain-specific pretraining may not generalize well under small-data conditions. In contrast, modern, deeper general-purpose CNNs pretrained on large-scale datasets can offer superior transfer learning performance in specialized medical imaging tasks.

Related papers

• Optimizing the nnU-Net model for brain tumor (Glioma) segmentation Using a BraTS Sub-Saharan Africa (SSA) dataset [0.0]
  This study used the BraTS Sub-Saharan Africa dataset, a selected subset of the BraTS dataset that included 60 multimodal MRI cases from patients with glioma.<n>Surprisingly, the nnU Net model trained on the initial 60 instances performed better than the network trained on an offline-augmented dataset of 360 cases.
  arXiv  Detail & Related papers  (2025-11-04T15:58:07Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Comparative Analysis of Resource-Efficient CNN Architectures for Brain Tumor Classification [0.0]
  This study presents a comparative analysis of effective yet simple Convolutional Neural Network (CNN) architecture and pre-trained ResNet18, and VGG16 models for brain tumor classification.<n>The custom CNN architecture, despite its lower complexity, demonstrates competitive performance with the pre-trained ResNet18 and VGG16 models.
  arXiv  Detail & Related papers  (2024-11-23T16:13:40Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Deep neuroevolution for limited, heterogeneous data: proof-of-concept application to Neuroblastoma brain metastasis using a small virtual pooled image collection [0.0]
  We seek to address both overfitting and generalizability by applying DNE to a virtually pooled data set consisting of images from various institutions. Our use case is classifying neuroblastoma brain metastases on MRI. Neuroblastoma is well-suited for our goals because it is a rare cancer. As in prior DNE work, we used a small training set, consisting of 30 normal and 30 metastasis-containing post-contrast MRI brain scans, with 37% outside images.
  arXiv  Detail & Related papers  (2022-11-26T07:03:37Z)
• Medulloblastoma Tumor Classification using Deep Transfer Learning with Multi-Scale EfficientNets [63.62764375279861]
  We propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions. Using a data set with 161 cases, we demonstrate that pre-trained EfficientNets with larger input resolutions lead to significant performance improvements.
  arXiv  Detail & Related papers  (2021-09-10T13:07:11Z)
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning [2.1446056201053185]
  We propose an extensive benchmark of recent state-of-the-art (SOTA) 3D CNN, evaluating also the benefits of data augmentation and deep ensemble learning. Experiments were conducted on a large multi-site 3D brain anatomical MRI data-set comprising N=10k scans on 3 challenging tasks: age prediction, sex classification, and schizophrenia diagnosis. We found that all models provide significantly better predictions with VBM images than quasi-raw data. DenseNet and tiny-DenseNet, a lighter version that we proposed, provide a good compromise in terms of performance in all data regime
  arXiv  Detail & Related papers  (2021-06-02T13:00:35Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)
• Interpretation of 3D CNNs for Brain MRI Data Classification [56.895060189929055]
  We extend the previous findings in gender differences from diffusion-tensor imaging on T1 brain MRI scans. We provide the voxel-wise 3D CNN interpretation comparing the results of three interpretation methods.
  arXiv  Detail & Related papers  (2020-06-20T17:56:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.