Detection of Lung Cancers From CT Images Using a Deep CNN Architecture in Layers Through ML

Detection of Lung Cancers From CT Images Using a Deep CNN Architecture in Layers Through ML

Khushwant Singh, Yudhvir Singh, Dheerdhwaj Barak, Mohit Yadav
Copyright: © 2023 |Pages: 11
DOI: 10.4018/979-8-3693-0876-9.ch006
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Lung inflammation is caused by the development of cancer cells. As the frequency of cancer rises, men and women are dying at a higher rate. With malignancy, cancerous cells multiply uncontrollably in the lobes. It is impossible to prevent lung cancer, but we can lower its associated risks. Early detection of lung cancer can considerably improve a patient's chances of survival. Patients with lung disease are more likely to be chain smokers. Several classification methods were applied to assess lung cancer prediction, such as the deep CNN algorithm and deep CNN, with the final layer as machine learning. The first deep CNN model defined this accuracy.
Chapter Preview
Top

2. Literature Survey

According to Hexuan et al. (2020), DenseNet and the hybrid attention mechanism module are combined to produce its network model. When it comes to identifying lung cancer in photographs, the parallel deep learning system that used a hybrid attention mechanism achieved an accuracy of 94.61%. The aggregate results of the tests led to these conclusions. To address the complete slide cancer image classification with low annotation effort, Wang et al. (2019) proposed a semi-supervised learning approach. Before generating SUCC, the most fine-grained lung cancer WSI dataset ever assembled, the author conducted preliminary research on a TCGA open lung disease WSIs dataset. Jiang et al. (2018), proposed two distinct neural network models to distinguish lung tumors from CT images by fusing several residual channels of various quality. Results show advancement in classification methods across many datasets.

Complete Chapter List

Search this Book:
Reset