Evolutionary U-Net for lung cancer segmentation on medical images
Article type: Research Article
Authors: Sahapudeen, Farjana Farvina; * | Krishna Mohan, S.b
Affiliations: [a] Department of Computer Science and Engineering, Anjalai Ammal Mahalingam Engineering College, Kovilvenni, Tamil Nadu, India | [b] Department of Mechanical Engineering, E.G.S. Pillay Engineering College, Nagapattinam, Tamil Nadu, India
Correspondence: [*] Corresponding author. Farjana Farvin Sahapudeen, E-mail: [email protected].
Abstract: Patients with lung cancer can only be diagnosed and treated surgically. Early detection of lung cancer through medical imaging could save numerous lives. Adding advanced techniques to conventional tests that offer high accuracy in diagnosing lung cancer is essential. U-Net has excelled in diversified tasks involving the segmentation of medical image datasets. A significant challenge remains in determining the ideal combination of hyper parameters for designing an optimized U-Net for detailed image segmentation. In our work, we suggested a technique for automatically generating evolutionary U-Nets to detect and segregate lung cancer anomalies. We used three distinct datasets, namely the LIDC-IRDC Dataset, Luna 16 Dataset, and Kaggle Dataset, for training the proposed work on lung images. Our results, examined with six distinct evaluation criteria used for medical image segmentation, consistently demonstrated the highest performance. More specifically, the GA-UNet outperforms conventional approaches in terms of an impressive accuracy rate of 97.5% and a Dice similarity coefficient (DSC) of 92.3%.
Keywords: Genetic programming, deep learning, attention blocks, residual network, UNets, optimized U-Net
DOI: 10.3233/JIFS-233006
Journal: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 2, pp. 3963-3974, 2024
Evolutionary U-Net for lung cancer segmentation on medical images
What is it about?
Patients with lung cancer can only be diagnosed and treated surgically. Early detection of lung cancer through medical imaging could save numerous lives. Adding advanced techniques to conventional tests that offer high accuracy in diagnosing lung cancer is essential. U-Net has excelled in diversified tasks involving the segmentation of medical image datasets. A significant challenge remains in determining the ideal combination of hyper parameters for designing an optimized U-Net for detailed image segmentation. In our work, we suggested a technique for automatically generating evolutionary U-Nets to detect and segregate lung cancer anomalies. We used three distinct datasets, namely the LIDC-IRDC Dataset, Luna 16 Dataset, and Kaggle Dataset, for training the proposed work on lung images. Our results, examined with six distinct evaluation criteria used for medical image segmentation, consistently demonstrated the highest performance.
Why is it important?
Evolutionary U-Net is an effective method of classifying and detecting lung tumors using deep learning.Three datasets, the LIDC-IRDC Dataset, the Luna 16 Dataset, and the Kaggle Dataset, were used for the evaluations in GA-UNet for CT medical images. The Evolutionary U-Net outperforms other cutting-edge methods in comparison, with an accuracy of 97.5% and a dice coefficient of 92.3%
Resources
-
Url
Deep Learning Approaches for IoMT
Deep Learning algorithms play an inevitable role in assessing the patient data maintained in IoMT servers and forecasting the existence of deadly illnesses. DL not only can diagnose major problems like tumors, heart disorders, skin diseases, COVID-19, etc.,