Scholarlink

<p>Brain cancer represents a significant global health challenge with increasing incidence and mortality rates. Magnetic Resonance Imaging (MRI) plays a pivotal role in early detection and treatment planning. This study adopts a systematic approach across four phases: (1) Optimal Model Selection using the Adam optimizer, emphasizing accuracy metrics, weight computation, early stopping, and ReduceLROnPlateau techniques. (2) Real-world Scenario Simulation through synthetic perturbed datasets created by applying noise, blur (to simulate various magnetic field strengths: 1T, 1.5T, 3T), and patient motion artifacts (mimicking MRI scanning motion effects) to the testing data from the BT-MRI dataset, an online published brain tumor MRI dataset. (3) Optimization involving a range of optimizers (Adam, Adagrad, Nadam, RMSprop, SGD) and online augmentation techniques (AutoMix, CutMix, LGCOAMix, PatchUp). (4) Solution Exploration integrating Gaussian Noise and Blur as augmentation strategies during training to enhance model generalization under diverse conditions. Initial evaluations achieved strong performance, consistently reaching 99.45% accuracy on the BT-MRI dataset. However, testing against synthetic perturbed datasets mimicking real-world conditions revealed challenges in maintaining robust model performance. Despite employing diverse optimization methods and advanced augmentation techniques, this study identifies persistent challenges in ensuring model robustness with synthetic perturbed datasets. Notably, the integration of Gaussian Noise and Blur during training significantly improved model resilience. This research underscores the critical role of methodological rigor and innovative augmentation strategies in advancing deep learning applications for precise brain cancer diagnosis using MRI.</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

Enhancing Generalization and Mitigating Overfitting in Deep Learning for Brain Cancer Diagnosis from MRI

  • 期刊论文

  • 发表日期：

    2025年1月3日

查看全文
  • Mohamad Abou Ali,
  • Jinan Charafeddine,
  • Fadi Dornaika,
  • Ignacio Arganda-Carreras

摘要

Brain cancer represents a significant global health challenge with increasing incidence and mortality rates. Magnetic Resonance Imaging (MRI) plays a pivotal role in early detection and treatment planning. This study adopts a systematic approach across four phases: (1) Optimal Model Selection using the Adam optimizer, emphasizing accuracy metrics, weight computation, early stopping, and ReduceLROnPlateau techniques. (2) Real-world Scenario Simulation through synthetic perturbed datasets created by applying noise, blur (to simulate various magnetic field strengths: 1T, 1.5T, 3T), and patient motion artifacts (mimicking MRI scanning motion effects) to the testing data from the BT-MRI dataset, an online published brain tumor MRI dataset. (3) Optimization involving a range of optimizers (Adam, Adagrad, Nadam, RMSprop, SGD) and online augmentation techniques (AutoMix, CutMix, LGCOAMix, PatchUp). (4) Solution Exploration integrating Gaussian Noise and Blur as augmentation strategies during training to enhance model generalization under diverse conditions. Initial evaluations achieved strong performance, consistently reaching 99.45% accuracy on the BT-MRI dataset. However, testing against synthetic perturbed datasets mimicking real-world conditions revealed challenges in maintaining robust model performance. Despite employing diverse optimization methods and advanced augmentation techniques, this study identifies persistent challenges in ensuring model robustness with synthetic perturbed datasets. Notably, the integration of Gaussian Noise and Blur during training significantly improved model resilience. This research underscores the critical role of methodological rigor and innovative augmentation strategies in advancing deep learning applications for precise brain cancer diagnosis using MRI.