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

BMC Medical Imaging, Год журнала: 2024, Номер 24(1)

Опубликована: Май 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.

Язык: Английский

---

Addressing Class Imbalance Problem in Health Data Classification: Practical Application From an Oversampling Viewpoint

Applied Computational Intelligence and Soft Computing, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

While analyzing health data is important for improving outcomes, class imbalance in datasets poses major challenges to machine learning classification models. This work, therefore, considers the problem stroke prediction using models such as K‐nearest neighbors, support vector machine, logistic regression, random forest, and decision tree. work balances dataset, thereby enhancing model performance, through various oversampling strategies: (RO), ADASYN, SMOTE, SMOTE–Tomek. Compared results of imbalanced all applied techniques enhanced correct events by ML model. Among these, RO–SVM with RBF kernel was best terms sensitivity, specificity, G‐mean, F1‐score, accuracy values, offering highest respective values 89.87%, 94.91%, 92.36%, 89.64%, 89.87%. After applying techniques, classifications were good enough classify status, especially minority class. study has highlighted importance issues datasets. Precise detection instances classes can be considerably employing implementation hybrid strategies effectively solve issues, which, turn, will help improve healthcare outcomes. Further research integrating more advanced deep into other imbalances encouraged further validate or refine approaches, effective handling substantially promote predictive performance analysis healthcare.

Язык: Английский

---

A robust transfer learning approach with histopathological images for lung and colon cancer detection using EfficientNetB3

Healthcare Analytics, Год журнала: 2025, Номер unknown, С. 100391 - 100391

Опубликована: Апрель 1, 2025

Язык: Английский

---

Detection of Marchiafava Bignami disease using distinct deep learning techniques in medical diagnostics

BMC Medical Imaging, Год журнала: 2024, Номер 24(1)

Опубликована: Апрель 29, 2024

Abstract Purpose To detect the Marchiafava Bignami Disease (MBD) using a distinct deep learning technique. Background Advanced methods are becoming more crucial in contemporary medical diagnostics, particularly for detecting intricate and uncommon neurological illnesses such as MBD. This rare neurodegenerative disorder, sometimes associated with persistent alcoholism, is characterized by loss of myelin or tissue death corpus callosum. It poses significant diagnostic difficulties owing to its infrequency subtle signs it exhibits first stages, both clinically on radiological scans. Methods The novel method Variational Autoencoders (VAEs) conjunction attention mechanisms used identify MBD peculiar diseases accurately. VAEs well-known their proficiency unsupervised anomaly detection. They excel at analyzing extensive brain imaging datasets uncover patterns abnormalities that traditional approaches may overlook, especially those related specific diseases. use enhances this technique, enabling model concentrate most elements data, similar discerning observation skilled radiologist. Thus, we utilized VAE study Such combination enables prompt identification assists formulating customized efficient treatment strategies. Results A breakthrough field creation equipped mechanisms, which has shown outstanding performance achieving accuracy rates over 90% accurately differentiating from other disorders. Conclusion model, underwent training diverse range MRI images, notable level sensitivity specificity, significantly minimizing frequency false positive results strengthening confidence dependability these sophisticated automated tools.

Язык: Английский

---

An Adaptive Xception Model for Classification of Brain Tumors

International Journal of Pattern Recognition and Artificial Intelligence, Год журнала: 2024, Номер 38(08)

Опубликована: Май 10, 2024

Classification of different brain tumors is challenging due to unpredictable variations in intra-inter-classes. Unlike existing methods which are not effective for images complex backgrounds, the proposed work aims at accurate classification diverse types such that an appropriate model can be used disease identification. This study considers glioma, meningioma, no tumor, and pituitary classification. To achieve classification, we explore Xception architecture layer, involves flattening, dropout, dense layer operations. The extracts features based on shapes, spatial relationships, structure image, discriminating between tumor images. evaluated a dataset 7023 MRI results large comparative with show method better than state art terms rate. Specifically, our achieves more 90% average rate, art. noisy blurred datasets robust noise blur.

Язык: Английский

---

Explainable lung cancer classification with ensemble transfer learning of VGG16, Resnet50 and InceptionV3 using grad-cam

BMC Medical Imaging, Год журнала: 2024, Номер 24(1)

Опубликована: Июль 19, 2024

Medical imaging stands as a critical component in diagnosing various diseases, where traditional methods often rely on manual interpretation and conventional machine learning techniques. These approaches, while effective, come with inherent limitations such subjectivity constraints handling complex image features. This research paper proposes an integrated deep approach utilizing pre-trained models-VGG16, ResNet50, InceptionV3-combined within unified framework to improve diagnostic accuracy medical imaging. The method focuses lung cancer detection using images resized converted uniform format optimize performance ensure consistency across datasets. Our proposed model leverages the strengths of each network, achieving high degree feature extraction robustness by freezing early convolutional layers fine-tuning deeper layers. Additionally, techniques like SMOTE Gaussian Blur are applied address class imbalance, enhancing training underrepresented classes. model's was validated IQ-OTH/NCCD dataset, which collected from Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases over period three months fall 2019. achieved 98.18%, precision recall rates notably all improvement highlights potential systems diagnostics, providing more accurate, reliable, efficient means disease detection.

Язык: Английский

---

An XAI-Enhanced EfficientNetB0 Framework for Precision Brain Tumor Detection in MRI Imaging

Journal of Neuroscience Methods, Год журнала: 2024, Номер 410, С. 110227 - 110227

Опубликована: Июль 20, 2024

Язык: Английский

---

Enhancing Diagnostic Precision in Breast Cancer Classification Through EfficientNetB7 Using Advanced Image Augmentation and Interpretation Techniques

International Journal of Imaging Systems and Technology, Год журнала: 2024, Номер 35(1)

Опубликована: Дек. 8, 2024

ABSTRACT The precise classification of breast ultrasound images into benign, malignant, and normal categories represents a critical challenge in medical diagnostics, exacerbated by subtle interclass variations the variable quality clinical imaging. State‐of‐the‐art approaches largely capitalize on advanced capabilities deep convolutional neural networks (CNNs), with significant emphasis exploiting architectures like EfficientNet that are pre‐trained extensive datasets. While these methods demonstrate potential, they frequently suffer from overfitting, reduced resilience to image distortions such as noise artifacts, presence pronounced class imbalances training data. To address issues, this study introduces an optimized framework using EfficientNetB7 architecture, enhanced targeted augmentation strategy. This strategy employs aggressive random rotations, color jittering, horizontal flipping specifically bolster representation minority classes, thereby improving model robustness generalizability. Additionally, approach integrates adaptive learning rate scheduler implements strategic early stopping refine process prevent overfitting. demonstrates substantial improvement diagnostic accuracy, achieving 98.29% accuracy meticulously assembled test dataset. performance significantly surpasses existing benchmarks field, highlighting model's ability navigate intricacies analysis. high positions it invaluable tool detection informed management cancer, potentially transforming current paradigms oncological care.

Язык: Английский

---

Revolutionizing breast ultrasound diagnostics with EfficientNet-B7 and Explainable AI

BMC Medical Imaging, Год журнала: 2024, Номер 24(1)

Опубликована: Сен. 2, 2024

Breast cancer is a leading cause of mortality among women globally, necessitating precise classification breast ultrasound images for early diagnosis and treatment. Traditional methods using CNN architectures such as VGG, ResNet, DenseNet, though somewhat effective, often struggle with class imbalances subtle texture variations, to reduced accuracy minority classes malignant tumors. To address these issues, we propose methodology that leverages EfficientNet-B7, scalable architecture, combined advanced data augmentation techniques enhance representation improve model robustness. Our approach involves fine-tuning EfficientNet-B7 on the BUSI dataset, implementing RandomHorizontalFlip, RandomRotation, ColorJitter balance dataset The training process includes stopping prevent overfitting optimize performance metrics. Additionally, integrate Explainable AI (XAI) techniques, Grad-CAM, interpretability transparency model's predictions, providing visual quantitative insights into features regions influencing outcomes. achieves 99.14%, significantly outperforming existing CNN-based approaches in image classification. incorporation XAI enhances our understanding decision-making process, thereby increasing its reliability facilitating clinical adoption. This comprehensive framework offers robust interpretable tool detection cancer, advancing capabilities automated diagnostic systems supporting processes.

Язык: Английский

---

Optimizing Deep Learning Based Approach for Brain Tumor Segmentation in Magnetic Resonance Imaging(MRI) Scans

Опубликована: Апрель 3, 2024

Язык: Английский

---