Zobraziť v EDS

A Dynamic Optimization and Deep Learning Technique for Detection of Lung Cancer in CT Images and Data Access Through Internet of Things.

Uložené v:
Podrobná bibliografia
Názov: A Dynamic Optimization and Deep Learning Technique for Detection of Lung Cancer in CT Images and Data Access Through Internet of Things.
Autori: Venkatesh, C., Bojja, Polaiah
Zdroj: Wireless Personal Communications; Aug2022, Vol. 125 Issue 3, p2621-2646, 26p
Predmety: LUNG cancer, COMPUTED tomography, INTERNET access, DEEP learning, IMAGE analysis, INTERNET of things, IMAGE processing
Abstrakt: Now-a-days the most common pretentious disease is the lung cancer, which has become more prevalent in the world that primarily infects the pulmonary nodules of the lungs. At present the most propitious way to increase survival rate in cancer patients is by early detection. Commonly the lung cancer is diagnosed by radiologists with an inclusive analysis of CT images, which proceeds comprehensively a longer time. The analysis of lung cancer in imaging modalities like CT images is crucial. Image processing itself act as a progressive diagnostic tool for analysis of medical imaging modalities. The existing procedures for detection of lung cancer like PSO with morphological yields poor accuracy. In this work the novelty is established by considering cuckoo-search optimization algorithm along with ostu threshold for segmentation, CNN as classifier and LBP as feature extraction procedure on CT images for detection of lung cancer. In addition, IoT technology is carried out using raspberry PI processor to establish a network to share the details among the medical professionals to exchange opinions for final treatment. Finally, various parameters were calculated and compared with existing procedures especially accuracy is around 98% and MSE within 1.5 is obtained. Thus, the proposed method gives an optimal solution on comparison with respect to all the parameters. [ABSTRACT FROM AUTHOR]
Copyright of Wireless Personal Communications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
Popis
Abstrakt:Now-a-days the most common pretentious disease is the lung cancer, which has become more prevalent in the world that primarily infects the pulmonary nodules of the lungs. At present the most propitious way to increase survival rate in cancer patients is by early detection. Commonly the lung cancer is diagnosed by radiologists with an inclusive analysis of CT images, which proceeds comprehensively a longer time. The analysis of lung cancer in imaging modalities like CT images is crucial. Image processing itself act as a progressive diagnostic tool for analysis of medical imaging modalities. The existing procedures for detection of lung cancer like PSO with morphological yields poor accuracy. In this work the novelty is established by considering cuckoo-search optimization algorithm along with ostu threshold for segmentation, CNN as classifier and LBP as feature extraction procedure on CT images for detection of lung cancer. In addition, IoT technology is carried out using raspberry PI processor to establish a network to share the details among the medical professionals to exchange opinions for final treatment. Finally, various parameters were calculated and compared with existing procedures especially accuracy is around 98% and MSE within 1.5 is obtained. Thus, the proposed method gives an optimal solution on comparison with respect to all the parameters. [ABSTRACT FROM AUTHOR]
ISSN:09296212
DOI:10.1007/s11277-022-09676-0