Multi-view convolutional recurrent neural networks for lung cancer nodule identification

Naeem Abid, Mian Muhammad, Zia, Tehseen, Ghafoor, Mubeen and Windridge, David ORCID: https://orcid.org/0000-0001-5507-8516 (2021) Multi-view convolutional recurrent neural networks for lung cancer nodule identification. Neurocomputing . ISSN 0925-2312 [Article] (Published online first) (doi:10.1016/j.neucom.2020.06.144)

PDF - Final accepted version (with author's formatting) Restricted to Repository staff and depositor only until 23 January 2022. Available under License Creative Commons Attribution-NoDerivatives. Download (16MB) | Request a copy

Abstract

Screening via low-dose Computer Tomography (CT) has been shown to reduce lung cancer mortality rates by at least 20%. However, the assessment of large numbers of CT scans by radiologists is cost intensive, and potentially produces varying and inconsistent results for differing radiologists (and also for temporally-separated assessments by the same radiologist). To overcome these challenges, computer aided diagnosis systems based on deep learning methods have proved an effective in automatic detection and classification of lung cancer.

Latterly, interest has focused on the full utilization of the 3D information in CT scans using 3D-CNNs and related approaches. However, such approaches do not intrinsically correlate size and shape information between slices. In this work, an innovative approach to Multi-view Convolutional Recurrent Neural Networks (MV-CRecNet) is proposed that exploits shape, size and cross-slice variations while learning to identify lung cancer nodules from CT scans. The multiple-views that are passed to the model ensure better generalization and the learning of robust features.

We evaluate the proposed MV-CRecNet model on the reference Lung Image Database Consortium and Image Database Resource Initiative and Early Lung Cancer Action Program datasets; six evaluation metrics are applied to eleven comparison models for testing. Results demonstrate that proposed methodology outperforms all of the models against all of the evaluation metrics.

Actions (login required)

View Item