Abstract
Lung cancer late diagnosis has a large impact on the mortality rate numbers, leading to a very low five-year survival rate of 5%. This issue emphasises the importance of developing systems to support a diagnostic at earlier stages. Clinicians use Computed Tomography (CT) scans to assess the nodules and the likelihood of malignancy. Automatic solutions can help to make a faster and more accurate diagnosis, which is crucial for the early detection of lung cancer. Convolutional neural networks (CNN) based approaches have shown to provide a reliable feature extraction ability to detect the malignancy risk associated with pulmonary nodules. This type of approach requires a massive amount of data to model training, which usually represents a limitation in the biomedical field due to medical data privacy and security issues. Transfer learning (TL) methods have been widely explored in medical imaging applications, offering a solution to overcome problems related to the lack of training data publicly available. For the clinical annotations experts with a deep understanding of the complex physiological phenomena represented in the data are required, which represents a huge investment. In this direction, this work explored a TL method based on unsupervised learning achieved when training a Convolutional Autoencoder (CAE) using images in the same domain. For this, lung nodules from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) were extracted and used to train a CAE. Then, the encoder part was transferred, and the malignancy risk was assessed in a binary classification—benign and malignant lung nodules, achieving an Area Under the Curve (AUC) value of 0.936. To evaluate the reliability of this TL approach, the same architecture was trained from scratch and achieved an AUC value of 0.928. The results reported in this comparison suggested that the feature learning achieved when reconstructing the input with an encoder-decoder based architecture can be considered an useful knowledge that might allow overcoming labelling constraints.
Highlights
Lung cancer is on the top of cancer-related mortality numbers worldwide [1,2]
The work presented in this paper addressed a binary lung nodule malignancy classification by a Transfer learning (TL) approach based on a trained Convolutional Autoencoder (CAE), using the LIDC-IDRI dataset
We proposed a deep structured algorithm to automatically extract features based on a convolutional autoencoder and an end-to-end learning classification network to predict the malignancy risk of nodules in Computed Tomography (CT) images using TL techniques
Summary
16% of lung cancer cases are diagnosed as local stage tumors. In these cases, patients have a five-year survival rate of more than 50%; when diagnosed in an advanced stage, the chances of a five-year survival decrease to 5%. As a non-invasive method, computed tomography (CT) images have shown the ability to provide valuable information on tumor status, rising opportunities to the development of computer-aided diagnoses (CAD) systems able to provide an automatic assessment of lung nodules malignancy risk to help the clinical decision. Considering the use of qualitative data, factors like the high interobserver variability associated with the visual assessment of relevant characteristics, and the amount of radiological data to be analyzed makes the development of completely automatic systems a more attractive approach
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.