EUVIMEDEUVIMED entdecken
Crossref

An Optimized Deep Learning Framework for Liver Tumor Detection from Ultrasound Images Using Hybrid CNN and Adaptive Image Enhancement

SD. Abid Hussain, Ms. M. Madhulika, D.V. Harshini Gayathri, Ch. Sravanthi, D. Jagan Mohan Reddy, J. Sowmya

INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 11.04.2026 · 10 (04) · 1-9

DOI: 10.55041/ijsrem59148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 11.04.2026. Verfasst von SD. Abid Hussain und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Liver cancer is a major global health concern due to its high mortality rate and challenges in early diagnosis. Ultrasound imaging is widely used for liver examination; however, the presence of noise, low contrast, and complex tissue structures makes accurate tumor detection difficult. This paper presents an optimized hybrid deep learning framework for liver tumor detection using ultrasound images. The proposed system integrates preprocessing techniques, including resizing, grayscale conversion, and median filtering, followed by adaptive contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE). K-means clustering is employed for segmentation to extract Regions of Interest (ROI), enabling focused analysis of tumor-prone regions. The segmented images are then classified using a Hybrid Convolutional Neural Network (CNN) architecture. The model is trained using Stochastic Gradient Descent with Momentum (SGDM) and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results indicate that the proposed model achieved an accuracy of 98.6%, demonstrating improved performance in detecting small and low-contrast tumors. The proposed system provides an efficient and reliable tool for computer-aided diagnosis and can assist radiologists in the early detection of liver cancer. KEYWORDS: Liver tumor detection, Ultrasound imaging, Hybrid CNN, K-means clustering, CLAHE, Deep learning

Zitieren

APA

Hussain, S. A., Madhulika, M. M., Gayathri, D. H., Sravanthi, C., Reddy, D. J. M., & Sowmya, J. (2026). An Optimized Deep Learning Framework for Liver Tumor Detection from Ultrasound Images Using Hybrid CNN and Adaptive Image Enhancement. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem59148

Vancouver

Hussain SA, Madhulika MM, Gayathri DH, Sravanthi C, Reddy DJM, Sowmya J. An Optimized Deep Learning Framework for Liver Tumor Detection from Ultrasound Images Using Hybrid CNN and Adaptive Image Enhancement. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem59148

BibTeX
@article{Hussain2026,
  author = {Hussain, SD. Abid and Madhulika, Ms. M. and Gayathri, D.V. Harshini and Sravanthi, Ch. and Reddy, D. Jagan Mohan and Sowmya, J.},
  title = {An Optimized Deep Learning Framework for Liver Tumor Detection from Ultrasound Images Using Hybrid CNN and Adaptive Image Enhancement},
  journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  volume = {10},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsrem59148}
}
Kostenlos starten →