Machine learning for medical image classification

Academia Medicine, Год журнала: 2024, Номер 1(4)

Опубликована: Дек. 23, 2024

This review article focuses on the application of machine learning (ML) algorithms in medical image classification. It highlights intricate process involved selecting most suitable ML algorithm for predicting specific conditions, emphasizing critical role real-world data testing and validation. navigates through various methods utilized healthcare, including Supervised Learning, Unsupervised Self-Supervised Deep Neural Networks, Reinforcement Ensemble Methods. The challenge lies not just selection an but identifying appropriate one a task as well, given vast array options available. Each unique dataset requires comparative analysis to determine best-performing algorithm. However, all available is impractical. examines performance recent studies, focusing their applications across different imaging modalities diagnosing conditions. provides summary these offering starting point those seeking select conditions modalities.

Язык: Английский

---

Integrating Deep Learning and Imaging Techniques for High-Precision Brain Tumor Analysis

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 53 - 67

Опубликована: Янв. 1, 2025

Язык: Английский

---

A Novel Self‐Attention Transfer Adaptive Learning Approach for Brain Tumor Categorization

International Journal of Intelligent Systems, Год журнала: 2024, Номер 2024(1)

Опубликована: Янв. 1, 2024

Brain tumors cause death to a lot of people globally. tumor disease is seen as one the most lethal diseases since its mortality rate high. Nevertheless, this can be diminished if identified and treated early. Recently, healthcare providers have relied on computed tomography (CT) scans magnetic resonance imaging (MRI) in their diagnosis. Currently, various artificial intelligence (AI)‐based solutions been implemented diagnose early prepare suitable treatment plans. In article, we propose novel self‐attention transfer adaptive learning approach (SATALA) identify brain tumors. This an automated AI‐based model that contains two deep‐learning technologies determine existence addition, proposed categorizes into groups, which are benign malignant. The developed method incorporates technologies: convolutional neural network (CNN), VGG‐19, new UNET architecture. trained evaluated six public datasets attained exquisite results. It achieved average 95% accuracy F 1‐score 96.61%. was compared with other state‐of‐the‐art models were reported related work. conducted experiments show generates outputs exceeds works some scenarios. conclusion, infer provides trustworthy identifications cancer applied facilities.

Язык: Английский

---

Revolutionizing MRI-Based Brain Tumor Classification with BrainMRI-NetX for Superior Accuracy and Reliability

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 28, 2024

This study aims to enhance and ensure reliable MRI-based brain tumor classification through the development of an innovative BrainMRI-NetX model, incorporating advanced techniques such as Depthwise Separable Convolutions, Residual Blocks, Squeeze-and-Excite Self-Attention Layers. For feature extraction, we utilized a hybrid VGG19 LSTM model. Our primary goal is develop evaluate CNN model that outperforms state-of-the-art models in terms F-score, recall, accuracy, precision.The proposed was trained using cutting-edge optimization on large dataset FigShare MRI images, significantly enhancing its performance. We thoroughly evaluated model's critical performance indicators: precision. When benchmarked against popular ResNet-152, DenseNet121, VGG16, our demonstrated superior performance, achieving F-score 0.96, precision all at 0.99. In comparison, DenseNet121 showed accuracy 0.85, 0.89, recall 0.90, 0.88. ResNet-152 VGG16 exhibited lower metrics, with 0.86, 0.84, 0.87. The exceptional highlights potential for advancing medical diagnostics, particularly classification.

Язык: Английский

---

Variable Kernel Feature Fusion and Transfer Learning for Pap Smear Image-Based Cervical Cancer Classification

International Journal of Electronics and Communication Engineering, Год журнала: 2024, Номер 11(11), С. 228 - 243

Опубликована: Ноя. 30, 2024

Cervical cancer, a malignant tumour that forms in the cervix, significantly contributes to cancer-related mortality among women globally, making early diagnosis crucial for effective treatment. Pap smear images, which are microscopic images of cervical cells, commonly used detection abnormal cells may lead cancer. This study introduces novel classification approach, Variable Kernel Feature Fusion-CNN (VKFF-CNN), improves performance by fusing multi-scale features using convolutional layers with 3x3, 4x4, and 5x5 kernels. architecture captures diverse set features, enhancing ability model accurately classify cells. With an average accuracy 98.03%, precision 97.83%, recall 97.11%, F1 score 98.23%, VKFF-CNN exhibited outstanding outcomes on Herlev Smear dataset. These results demonstrate outperforms traditional machine learning models. The model's confusion matrix indicated fewer misclassifications, underscoring its robustness effectiveness. Including batch normalization softmax activation function further enhanced stability accurate classification. Overall, presents promising advancement automated cancer screening, providing highly reliable detection.

Язык: Английский

---