scholarly journals Lung Cancer Diagnosis using Transfer Learning

2021 ◽  
Vol 9 (11) ◽  
pp. 621-634
Author(s):  
Aashka Mohite
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Transfer Learning ◽  
Cancer Diagnosis ◽  
Chronic Condition ◽  
Death Rate ◽  
Ct Scans ◽  
Lung Cancer Diagnosis ◽  
Learning Architectures ◽  
Lung Ct

Lung cancer is unquestionably a lung-influencing chronic condition that significantly hampers the respiratory system. It is the second most dangerous disease which causes increase in death rate. To resolve this issue, we had planned to create a very Convolutional Neural Network using Transfer learning to specifically classify the lungs CT scans as normal, malignant, or benign in a subtle way. A dataset of 1100 lung CT scans is used for this purpose. For the most part, five Transfer Learning architectures are compared extensively in this classification such as MobileNet, VGG16, VGG19, DenseNet-201 and ResNet-101. Out of which, DenseNet-201 performed the best. The proposed strategy achieved a mean accuracy of 53 percent in the trials and 43% of  mean F1-score, mean precision and mean recall.

scholarly journals AUTOMATED CLASSIFICATION OF SOLITARY PULMONARY NODULES USING CONVOLUTIONAL NEURAL NETWORK BASED ON TRANSFER LEARNING STRATEGY

2021 ◽  
pp. 2140002
Author(s):  
SHIWEI LI ◽  
DANDAN LIU
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Transfer Learning ◽  
Pulmonary Nodule ◽  
Learning Strategy ◽  
Solitary Pulmonary Nodule ◽  
Ct Images ◽  
Ct Image ◽  
Nodule Classification ◽  
Lung Ct

This study aimed to propose an effective malignant solitary pulmonary nodule classification method based on improved Faster R-CNN and transfer learning strategy. In practice, the existing solitary pulmonary nodule classification methods divide the lung cancer images into two categories only: normal and cancerous. This study proposed the deep convolution neural network to classify the computed tomography (CT) images of lung cancer into four categories: lung adenocarcinoma, lung squamous cell carcinoma, metastatic lung cancer, and normal types of lung cancer. Some high-resolution lung CT images have unnecessary characters such as a large number of high-density continuity features, small-size lung nodule targets, CT image background complexity, and so forth. In this study, the CT image sub-block preprocessing strategy was used to extract nodule features for enhancement and alleviate the aforementioned problems. The experimental results showed that the proposed system was effective in resolving issues such as high false-positive rate and long classification time cost based on the original Faster R-CNN detection method. Meanwhile, the transfer learning strategy was used to improve the classification efficiency so as to avoid the overfitting problem caused by a few labeled samples of lung cancer datasets. The classification results were integrated using the majority vote algorithm. The classification results of the lung CT imaging showed that the proposed method had an average detection accuracy of 89.7% and reduced the rate of misdiagnosis to meet the clinical needs.

scholarly journals Lung cancer diagnosis with quantitative DIC microscopy and a deep convolutional neural network

2019 ◽  
Vol 10 (5) ◽  
pp. 2446 ◽  
Author(s):  
Longfei Zheng ◽  
Kangyuan Yu ◽  
Shuangshuang Cai ◽  
Yu Wang ◽  
Bixin Zeng ◽  
...  
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Convolutional Neural Network ◽  
Cancer Diagnosis ◽  
Deep Convolutional Neural Network ◽  
Lung Cancer Diagnosis ◽  
Dic Microscopy
Sign in / Sign up

Export Citation Format

Share Document