Enhancing brain tumor detection in MRI images through explainable AI using Grad-CAM with Resnet 50

BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)

Published: May 11, 2024

Abstract This study addresses the critical challenge of detecting brain tumors using MRI images, a pivotal task in medical diagnostics that demands high accuracy and interpretability. While deep learning has shown remarkable success image analysis, there remains substantial need for models are not only accurate but also interpretable to healthcare professionals. The existing methodologies, predominantly learning-based, often act as black boxes, providing little insight into their decision-making process. research introduces an integrated approach ResNet50, model, combined with Gradient-weighted Class Activation Mapping (Grad-CAM) offer transparent explainable framework tumor detection. We employed dataset enhanced through data augmentation, train validate our model. results demonstrate significant improvement model performance, testing 98.52% precision-recall metrics exceeding 98%, showcasing model’s effectiveness distinguishing presence. application Grad-CAM provides insightful visual explanations, illustrating focus areas making predictions. fusion explainability holds profound implications diagnostics, offering pathway towards more reliable detection tools.

Language: Английский

---

Brain Tumor Segmentation and Detection Utilizing Deep Learning Convolutional Neural Networks

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 25, 2025

Brain tumor division presents a principal challenge in neuro-oncology, essentially affecting determination, treatment arranging, and persistent results. Machine learning strategies, counting directed, unsupervised, profound approaches, have revolutionized neuroimaging investigation by robotizing upgrading the of brain tumors over imaging modalities like MRI CT. Profound learning, especially convolutional Neural Systems (CNNs), empowers exact outline boundaries, distinguishing proof districts intrigued, extraction neurotic highlights, tending to restrictions conventional manual strategies. In spite significant progressions, challenges stay optimizing algorithmic execution, guaranteeing clinical significance, moral contemplations. The integration strong calculations into workflows requires intrigue collaborations improve adequacy reliability. Future inquire about bearings emphasize creating progressed models, leveraging data-driven joining frameworks hone, keeping up compliance, cultivating collaborative advancement environments, locks partners. This consider highlights transformative affect CNN-based strategies on progressing demonstrative precision, results, healthcare development, supporting personalized pharmaceutical approaches around world.

Language: Английский

---

Explainable AI in medical imaging: an interpretable and collaborative federated learning model for brain tumor classification

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: Feb. 27, 2025

A brain tumor is a collection of abnormal cells in the that can become life-threatening due to its ability spread. Therefore, prompt and meticulous classification an essential element healthcare care. Magnetic Resonance Imaging (MRI) central resource for producing high-quality images soft tissue considered principal technology diagnosing tumors. Recently, computer vision techniques such as deep learning (DL) have played important role tumors, most which use traditional centralized models, face significant challenges insufficient availability diverse representative datasets exacerbate difficulties obtaining transparent model. This study proposes collaborative federated model (CFLM) with explainable artificial intelligence (XAI) mitigate existing problems using state-of-the-art methods. The proposed method addresses four class identify glioma, meningioma, no tumor, pituitary We integrated GoogLeNet (FL) framework facilitate on multiple devices maintain privacy sensitive information locally. Moreover, this also focuses interpretability make Gradient-weighted activation mapping (Grad-CAM) saliency map visualizations. In total, 10 clients were selected 50 communication rounds, each decentralized local training. approach achieves 94% accuracy. we incorporate Grad-CAM heat maps offer meaningful graphical interpretations specialists. outlines efficient interpretable by introducing technique FL architecture. has great potential improve them more reliable clinical use.

Language: Английский

---

Advanced Brain Tumor Classification in MR Images Using Transfer Learning and Pre-Trained Deep CNN Models

Cancers, Journal Year: 2025, Volume and Issue: 17(1), P. 121 - 121

Published: Jan. 2, 2025

Background/Objectives: Brain tumor classification is a crucial task in medical diagnostics, as early and accurate detection can significantly improve patient outcomes. This study investigates the effectiveness of pre-trained deep learning models classifying brain MRI images into four categories: Glioma, Meningioma, Pituitary, No Tumor, aiming to enhance diagnostic process through automation. Methods: A publicly available Tumor dataset containing 7023 was used this research. The employs state-of-the-art models, including Xception, MobileNetV2, InceptionV3, ResNet50, VGG16, DenseNet121, which are fine-tuned using transfer learning, combination with advanced preprocessing data augmentation techniques. Transfer applied fine-tune optimize accuracy while minimizing computational requirements, ensuring efficiency real-world applications. Results: Among tested Xception emerged top performer, achieving weighted 98.73% F1 score 95.29%, demonstrating exceptional generalization capabilities. These proved particularly effective addressing class imbalances delivering consistent performance across various evaluation metrics, thus their suitability for clinical adoption. However, challenges persist improving recall Glioma Meningioma categories, black-box nature requires further attention interpretability trust settings. Conclusions: findings underscore transformative potential imaging, offering pathway toward more reliable, scalable, efficient tools. Future research will focus on expanding diversity, model explainability, validating settings support widespread adoption AI-driven systems healthcare ensure integration workflows.

Language: Английский

---

Explainable artificial intelligence with UNet based segmentation and Bayesian machine learning for classification of brain tumors using MRI images

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 3, 2025

Detecting brain tumours (BT) early improves treatment possibilities and increases patient survival rates. Magnetic resonance imaging (MRI) scanning offers more comprehensive information, such as better contrast clarity, than any alternative process. Manually separating BTs from several MRI images gathered in medical practice for cancer analysis is challenging time-consuming. Tumours scans of the are exposed utilizing methods machine learning technologies, simplifying process doctors. can sometimes appear normal even when a has tumour or malignancy. Deep approaches have recently depended on deep convolutional neural networks to analyze with promising outcomes. It supports saving lives faster rectifying some errors. With this motivation, article presents new explainable artificial intelligence semantic segmentation Bayesian tumors (XAISS-BMLBT) technique. The presented XAISS-BMLBT technique mainly concentrates classification BT images. approach initially involves bilateral filtering-based image pre-processing eliminate noise. Next, performs MEDU-Net+ define impacted regions. For feature extraction process, ResNet50 model utilized. Furthermore, regularized network (BRANN) used identify presence BTs. Finally, an improved radial movement optimization employed hyperparameter tuning BRANN To highlight performance technique, series simulations were accomplished by benchmark database. experimental validation portrayed superior accuracy value 97.75% over existing models.

Language: Английский

---

Accessible AI Diagnostics and Lightweight Brain Tumor Detection on Medical Edge Devices

Bioengineering, Journal Year: 2025, Volume and Issue: 12(1), P. 62 - 62

Published: Jan. 13, 2025

The timely and accurate detection of brain tumors is crucial for effective medical intervention, especially in resource-constrained settings. This study proposes a lightweight efficient RetinaNet variant tailored edge device deployment. model reduces computational overhead while maintaining high accuracy by replacing the computationally intensive ResNet backbone with MobileNet leveraging depthwise separable convolutions. modified achieves an average precision (AP) 32.1, surpassing state-of-the-art models small tumor (APS: 14.3) large localization (APL: 49.7). Furthermore, significantly costs, making real-time analysis feasible on low-power hardware. Clinical relevance key focus this work. proposed addresses diagnostic challenges small, variable-sized often overlooked existing methods. Its architecture enables portable devices, bridging gap accessibility underserved regions. Extensive experiments BRATS dataset demonstrate robustness across sizes configurations, confidence scores consistently exceeding 81%. advancement holds potential improving early detection, particularly remote areas lacking advanced infrastructure, thereby contributing to better patient outcomes broader AI-driven tools.

Language: Английский

---

Detection of brain tumors using a transfer learning-based optimized ResNet152 model in MR images

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 188, P. 109790 - 109790

Published: Feb. 13, 2025

Language: Английский

---

Brain tumor classification: a novel approach integrating GLCM, LBP and composite features

Frontiers in Oncology, Journal Year: 2024, Volume and Issue: 13

Published: Jan. 30, 2024

Identifying and classifying tumors are critical in-patient care treatment planning within the medical domain. Nevertheless, conventional approach of manually examining tumor images is characterized by its lengthy duration subjective nature. In response to this challenge, a novel method proposed that integrates capabilities Gray-Level Co-Occurrence Matrix (GLCM) features Local Binary Pattern (LBP) conduct quantitative analysis (Glioma, Meningioma, Pituitary Tumor). The key contribution study pertains development interaction features, which obtained through outer product GLCM LBP feature vectors. utilization greatly enhances discriminative capability extracted features. Furthermore, methodology incorporates aggregated, statistical, non-linear in addition vectors utilized compute these values, encompassing range statistical characteristics effectively modifying space. effectiveness has been demonstrated on image datasets include tumors. Integrating (Gray-Level Co-occurrence Matrix) (Local Patterns) offers comprehensive representation texture characteristics, enhancing detection classification precision. introduced distinctive element methodology, provide enhanced capability, resulting improved performance. Incorporating enables more precise crucial characteristics. When with linear support vector machine classifier, showcases better accuracy rate 99.84%, highlighting efficacy promising prospects. improvement extraction techniques for brain potential enhance precision processing significantly. exhibits substantial facilitating clinicians accurate diagnoses treatments forthcoming times.

Language: Английский

---

Enhanced MRI-based brain tumor classification with a novel Pix2pix generative adversarial network augmentation framework

Brain Communications, Journal Year: 2024, Volume and Issue: 6(6)

Published: Jan. 1, 2024

Abstract The scarcity of medical imaging datasets and privacy concerns pose significant challenges in artificial intelligence-based disease prediction. This poses major to patient confidentiality as there are now tools capable extracting information by merely analysing patient’s data. To address this, we propose the use synthetic data generated generative adversarial networks a solution. Our study pioneers utilisation novel Pix2Pix network model, specifically ‘image-to-image translation with conditional networks,’ generate for brain tumour classification. We focus on classifying four types: glioma, meningioma, pituitary healthy. introduce deep convolutional neural architecture, developed from architectures, process pre-processed original obtained Kaggle repository. evaluation metrics demonstrate model's high performance images, achieving an accuracy 86%. Comparative analysis state-of-the-art models such Residual Network50, Visual Geometry Group 16, 19 InceptionV3 highlights superior our model detection, diagnosis findings underscore efficacy augmentation technique creating accurate classification, offering promising avenue improved prediction treatment planning.

Language: Английский

---

AI‐Enhanced Detection of Clinically Relevant Structural and Functional Anomalies in MRI: Traversing the Landscape of Conventional to Explainable Approaches

Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 19, 2024

Anomaly detection in medical imaging, particularly within the realm of magnetic resonance imaging (MRI), stands as a vital area research with far‐reaching implications across various fields. This review meticulously examines integration artificial intelligence (AI) anomaly for MR images, spotlighting its transformative impact on diagnostics. We delve into forefront AI applications MRI, exploring advanced machine learning (ML) and deep (DL) methodologies that are pivotal enhancing precision diagnostic processes. The provides detailed analysis preprocessing, feature extraction, classification, segmentation techniques, alongside comprehensive evaluation commonly used metrics. Further, this paper explores latest developments ensemble methods explainable AI, offering insights future directions potential breakthroughs. synthesizes current insights, valuable guide researchers, clinicians, experts. It highlights AI's crucial role improving speed detecting key structural functional irregularities MRI. Our exploration innovative techniques trends furthers MRI technology development, aiming to refine diagnostics, tailor treatments, elevate patient care outcomes. Level Evidence 5 Technical Efficacy Stage 1.

Language: Английский

---