Scholarlink

Purpose <p>To quantitatively compare end-to-end training of a convolutional neural network (CNN) with transfer learning using a frozen VGG16 feature extractor for multiclass brain tumor classification on contrast-enhanced magnetic resonance (MR) images.</p> Methods <p>A publicly available dataset of 6,056 contrast-enhanced T1-weighted brain MRI images (glioma, <i>n</i> = 2,004; meningioma, <i>n</i> = 2,004; and brain tumor, <i>n</i> = 2,048) was preprocessed (resized to 224 × 224, intensity-normalized, pseudo-RGB) and stratified (70/15/15 split). Five independent runs with distinct random seeds (42, 123, 2024, 7, 999) compared (1) a custom CNN trained end-to-end and (2) a frozen VGG16 with a task-specific head under identical conditions. Performance was assessed via accuracy, precision, recall, F1 score, ROC-AUC, and generalization gap (Δ_gen = training–testing accuracy) with paired t tests and Cohen’s d.</p> Results <p>The frozen VGG16 model achieved a mean test accuracy of 94.4% ± 0.4% (95% CI ± 0.35%), significantly outperforming the baseline CNN (58.8% ± 25.0%; paired t test p = 0.032; Cohen’s d = 1.45). VGG16 showed a near-zero generalization gap (Δ_gen =  − 0.022) versus severe overfitting at baseline (Δ_gen =  + 0.344).</p> Conclusion <p>Under strictly controlled single-dataset conditions, frozen VGG16 feature extraction establishes a statistically robust and reproducible baseline that demonstrates significant superiority over end-to-end training of a lightweight CNN (mean test accuracy 94.4% ± 0.4% vs. 58.8% ± 25.0%; paired t test <i>p</i> = 0.032; Cohen’s d = 1.45). External multicenter validation on diverse scanners and populations, together with quantitative interpretability analyses, remain essential prerequisites for clinical translation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating transfer learning for brain tumor MRI classification: frozen VGG16 feature extraction versus end-to-end CNN training

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月21日

查看全文
  • Areej H. Al-Sarairah,
  • Omar Abd Al Mjed Al-Lasasmeh,
  • Arar Al Tawil,
  • Mus’ab S Alkasasbeh,
  • Nadeer M Gharaibeh

摘要

Purpose

To quantitatively compare end-to-end training of a convolutional neural network (CNN) with transfer learning using a frozen VGG16 feature extractor for multiclass brain tumor classification on contrast-enhanced magnetic resonance (MR) images.

Methods

A publicly available dataset of 6,056 contrast-enhanced T1-weighted brain MRI images (glioma, n = 2,004; meningioma, n = 2,004; and brain tumor, n = 2,048) was preprocessed (resized to 224 × 224, intensity-normalized, pseudo-RGB) and stratified (70/15/15 split). Five independent runs with distinct random seeds (42, 123, 2024, 7, 999) compared (1) a custom CNN trained end-to-end and (2) a frozen VGG16 with a task-specific head under identical conditions. Performance was assessed via accuracy, precision, recall, F1 score, ROC-AUC, and generalization gap (Δ_gen = training–testing accuracy) with paired t tests and Cohen’s d.

Results

The frozen VGG16 model achieved a mean test accuracy of 94.4% ± 0.4% (95% CI ± 0.35%), significantly outperforming the baseline CNN (58.8% ± 25.0%; paired t test p = 0.032; Cohen’s d = 1.45). VGG16 showed a near-zero generalization gap (Δ_gen =  − 0.022) versus severe overfitting at baseline (Δ_gen =  + 0.344).

Conclusion

Under strictly controlled single-dataset conditions, frozen VGG16 feature extraction establishes a statistically robust and reproducible baseline that demonstrates significant superiority over end-to-end training of a lightweight CNN (mean test accuracy 94.4% ± 0.4% vs. 58.8% ± 25.0%; paired t test p = 0.032; Cohen’s d = 1.45). External multicenter validation on diverse scanners and populations, together with quantitative interpretability analyses, remain essential prerequisites for clinical translation.