A Survey on Liver Cancer Detection Using Hyperfusion of CNN and SVM in Machine Learning

International Journal of Preventive Medicine and Health, Journal Year: 2025, Volume and Issue: 5(2), P. 20 - 23

Published: Jan. 25, 2025

Since liver cancer ranks among of the most aggressive renditions disease, improving patient outcomes requires early identification. We propose an inventive tactic to detection by integrating CNN and SVM. CNNs, known for their powerful feature extraction capabilities, are particularly effective in analysing complex medical images. SVMs, on other hand, efficient classifiers that can separate data points high-dimensional spaces with accuracy. By merging strength classification efficiency SVM, proposed model aims enhance accuracy robustness. The experimental results reveal fused CNN-SVM significantly surpasses performance standalone SVM models, achieving a high 95.2%. This hybrid method offers promising direction precision computer-aided diagnosis systems, contributing more reliable methods assist healthcare professionals making timely decisions.

Language: Английский

---

Explainable and Robust Deep Learning for Liver Segmentation Through U-Net Network

Diagnostics, Journal Year: 2025, Volume and Issue: 15(7), P. 878 - 878

Published: March 31, 2025

Background/Objectives: Clinical imaging techniques, such as magnetic resonance and computed tomography, play a vital role in supporting clinicians by aiding disease diagnosis facilitating the planning of appropriate interventions. This is particularly important malignant conditions like hepatocellular carcinoma, where accurate image segmentation, delineating liver tumor, critical initial step optimizing diagnosis, staging, treatment planning, including interventions transplantation, surgical resection, radiotherapy, portal vein embolization, other procedures. Therefore, effective segmentation methods can significantly influence both diagnostic accuracy outcomes. Method: In this paper, we propose deep learning-based approach aimed at accurately segmenting medical images, thus addressing need hepatic planning. We consider U-Net architecture with residual connections to capture fine-grained anatomical details. also take into account prediction explainability, aiming highlight, under analysis, areas that are symptomatic for certain segmentation. detail, exploiting architecture, two different models trained annotated datasets tomography resulting four experiments. Results: improve robustness generalization across diverse patient populations conditions. Experimental results demonstrate proposed method obtains interesting performances, an ranging from 0.81 0.93. Conclusions: show provide reliable efficient solution automated promising significant advancements clinical workflows precision medicine.

Language: Английский

---

The current status and future directions of artificial intelligence in the prediction, diagnosis, and treatment of liver diseases

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: April 1, 2025

Early detection, accurate diagnosis, and effective treatment of liver diseases are paramount importance for improving patient survival rates. However, traditional methods frequently influenced by subjective factors technical limitations. With the rapid progress artificial intelligence (AI) technology, its applications in medical field, particularly prediction, diseases, have drawn increasing attention. This article offers a comprehensive review current AI hepatology. It elaborates on how is utilized to predict progression diagnose various conditions, assist formulating personalized plans. The emphasizes key advancements, including application machine learning deep algorithms. Simultaneously, it addresses challenges limitations within this domain. Moreover, pinpoints future research directions. underscores necessity large-scale datasets, robust algorithms, ethical considerations clinical practice, which crucial facilitating integration technology enhancing diagnostic therapeutic capabilities diseases.

Language: Английский

---