Early Lung Cancer Detection using Deep Learning Optimization

This paper proposes a Computer Aided Detection (CADe) system for early detection of lung nodules from low dose computed tomography (LDCT) images. The proposed system initially pre-process the raw data to improve the contrast of the low dose images. Compact deep learning features are then extracted by investigating different deep learning architectures, including Alex, VGG16, and VGG19 networks. To optimize the extracted set of features, a genetic algorithm (GA) is trained to select the most relevant features for early detection. Finally, different types of classifiers are tested in order to accurately detect the lung nodules. The system is tested on 320 LDCT images from 50 different subjects, using an online public lung database, i.e., the International Early Lung Cancer Action Project, I-ELCAP. The proposed system, using VGG19 architecture and SVM classifier, achieves the best detection accuracy of 96.25%, sensitivity of 97.5%, and specificity of 95%. Compared to other state-of-the-art methods, the proposed system shows a promising results.

Download Full-text

Computer-Aided Detection (CADe) System for Detection of Malignant Lung Nodules in CT Slices - a Key for Early Lung Cancer Detection

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405613666170614083951 ◽

2018 ◽

Vol 14 (3) ◽

pp. 422-429

Author(s):

Usama Ijaz Bajwa ◽

Abdullah Ali Shah ◽

Muhammad Waqas Anwar ◽

Ghulam Gilanie ◽

Asma Ejaz Bajwa

Keyword(s):

Lung Cancer ◽

Cancer Detection ◽

Lung Nodules ◽

Computer Aided Detection ◽

Early Lung Cancer ◽

Computer Aided ◽

Cade System ◽

Lung Cancer Detection ◽

Ct Slices

Download Full-text

Application of Deep Learning in Lung Cancer Imaging Diagnosis

Journal of Healthcare Engineering ◽

10.1155/2022/6107940 ◽

2022 ◽

Vol 2022 ◽

pp. 1-12

Author(s):

Wenfa Jiang ◽

Ganhua Zeng ◽

Shuo Wang ◽

Xiaofeng Wu ◽

Chenyang Xu

Keyword(s):

Lung Cancer ◽

Computer Vision ◽

Deep Learning ◽

Malignant Tumors ◽

Lung Nodule ◽

Ct Images ◽

Lung Nodules ◽

X Rays ◽

Imaging Diagnosis ◽

Risk Of Cancer

Lung cancer is one of the malignant tumors with the highest fatality rate and nearest to our lives. It poses a great threat to human health and it mainly occurs in smokers. In our country, with the acceleration of industrialization, environmental pollution, and population aging, the cancer burden of lung cancer is increasing day by day. In the diagnosis of lung cancer, Computed Tomography (CT) images are a fairly common visualization tool. CT images visualize all tissues based on the absorption of X-rays. The diseased parts of the lung are collectively referred to as pulmonary nodules, the shape of nodules is different, and the risk of cancer will vary with the shape of nodules. Computer-aided diagnosis (CAD) is a very suitable method to solve this problem because the computer vision model can quickly scan every part of the CT image of the same quality for analysis and will not be affected by fatigue and emotion. The latest advances in deep learning enable computer vision models to help doctors diagnose various diseases, and in some cases, models have shown greater competitiveness than doctors. Based on the opportunity of technological development, the application of computer vision in medical imaging diagnosis of diseases has important research significance and value. In this paper, we have used a deep learning-based model on CT images of lung cancer and verified its effectiveness in the timely and accurate prediction of lungs disease. The proposed model has three parts: (i) detection of lung nodules, (ii) False Positive Reduction of the detected nodules to filter out “false nodules,” and (iii) classification of benign and malignant lung nodules. Furthermore, different network structures and loss functions were designed and realized at different stages. Additionally, to fine-tune the proposed deep learning-based mode and improve its accuracy in the detection Lung Nodule Detection, Noudule-Net, which is a detection network structure that combines U-Net and RPN, is proposed. Experimental observations have verified that the proposed scheme has exceptionally improved the expected accuracy and precision ratio of the underlined disease.

Download Full-text

Diagnostic Value of Imaging Combined With Tumor Markers in Early Detection of Lung Cancer

Frontiers in Surgery ◽

10.3389/fsurg.2021.694210 ◽

2021 ◽

Vol 8 ◽

Author(s):

Su-Ju Wei ◽

Li-Ping Wang ◽

Jun-Yan Wang ◽

Jing-Xu Ma ◽

Feng-Bin Chuan ◽

...

Keyword(s):

Lung Cancer ◽

Early Detection ◽

Tumor Markers ◽

Cancer Diagnosis ◽

Diagnostic Value ◽

Diagnostic Methods ◽

Lung Cancer Diagnosis ◽

Early Lung Cancer ◽

Group A ◽

Group B

Objective: The objective of this research is to explore the diagnostic value of imaging plus tumor markers in the early detection of lung cancer.Methods: Sixty patients with lung cancer treated in our hospital from January 2018 to January 2019 were selected as group A. They were matched with 60 patients with benign lung disease as group B and 60 healthy subjects examined in our hospital as group C. The carcino-embryonic antigen (CEA), CYFRA21-1, and neuron-specific enolase (NSE) were assessed, and the diagnostic value of tumor markers plus imaging in lung cancer diagnosis was explored.Results: The CEA, CYFRA21-1, and NSE in group A were evidently superior to those in groups B and C, and those in group B were superior to those in group C (all P < 0.001). CEA had the highest sensitivity (56.7%), and NSE had the highest specificity (93.3%). The tumor markers plus imaging had the highest sensitivity for different types of lung cancer, and the sensitivity to early lung cancer (90%) was superior to other diagnostic methods (P < 0.05).Conclusion: The tumor markers plus imaging is of great significance in early lung cancer diagnosis and provides a reference for judging the pathological classification.

Download Full-text