Fuzzy C-Means Segmentation and Hybrid DarkNet-SVM Model for Tumor Detection in Homo Sapiens Through CT Images

The accurate detection of lung tumors is crucial due to their potential to metastasize to other body parts, posing severe risks including fatality. Computed Tomography (CT) scans are commonly used by medical professionals to obtain precise images of lung tissues. To address existing limitations, we...

Full description

Saved in:
Bibliographic Details
Published in:Journal of electrical engineering & technology 2024, 19(4), , pp.2683-2691
Main Authors: Priyadharsini, S. Indira, Raghuraman, G., SaiRamesh, L.
Format: Article
Language:English
Subjects:
Electrical Engineering
Electrical Machines and Networks
Electronics and Microelectronics
Engineering
Instrumentation
Original Article
Power Electronics
전기공학
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The accurate detection of lung tumors is crucial due to their potential to metastasize to other body parts, posing severe risks including fatality. Computed Tomography (CT) scans are commonly used by medical professionals to obtain precise images of lung tissues. To address existing limitations, we propose two advanced deep learning methods: DarkNet-19 and a hybrid DarkNet-SVM approach. These methods aim to enhance tumor detection accuracy. Additionally, we employ Fuzzy C-Means for precise nodule segmentation within the lungs. Following segmentation, our proposed deep learning techniques extract nodule features and categorize them as Malignant or Non-Malignant. Our framework is evaluated utilizing the lung image database consortium (LIDC) dataset. Our findings reveal that the DarkNet-SVM model achieves a testing accuracy of 91.07%, surpassing the DarkNet-19 model by a 2% margin.
ISSN:1975-0102
2093-7423
DOI:10.1007/s42835-023-01750-2