Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks

• Published in: BioMed research international Vol. 2017; no. 2017; pp. 1 - 6
• Main Authors: Fujita, Hiroshi, Kiriyama, Yuka, Tsukamoto, Tetsuya, Teramoto, Atsushi
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2017; Hindawi; John Wiley & Sons, Inc
• Subjects: Adenocarcinoma; Adenocarcinoma - classification; Adenocarcinoma - diagnosis; Adenocarcinoma - diagnostic imaging; Adenocarcinoma - pathology; Adenocarcinoma of Lung; Algorithms; Artificial neural networks; Automation; Brain cancer; Breast cancer; Cancer; Cancer therapies; Carcinoma, Squamous Cell - classification; Carcinoma, Squamous Cell - diagnosis; Carcinoma, Squamous Cell - diagnostic imaging; Carcinoma, Squamous Cell - pathology; Cellular biology; Classification; Cytodiagnosis - methods; Databases, Factual; Diagnosis; Diagnosis, Differential; Diagnostic imaging; Differential diagnosis; Filtration; Health physics; Humans; Image classification; Image Processing, Computer-Assisted; Lung cancer; Lung Neoplasms - classification; Lung Neoplasms - diagnosis; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Machine learning; Medical imaging; Methods; Microscopy; Neural networks; Neural Networks (Computer); Pathology; Small Cell Lung Carcinoma - classification; Small Cell Lung Carcinoma - diagnosis; Small Cell Lung Carcinoma - diagnostic imaging; Small Cell Lung Carcinoma - pathology; Squamous cell carcinoma; Japan
• ISSN: 2314-6133; 2314-6141; 2314-6141
• DOI: 10.1155/2017/4067832

Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.