Automatic Sequence-Based Network for Lung Diseases Detection in Chest CT

Hao, Jinkui, Xie, Jianyang ORCID: 0000-0002-4565-5807, Liu, Ri, Hao, Huaying, Ma, Yuhui, Yan, Kun, Liu, Ruirui, Zheng, Yalin ORCID: 0000-0002-7873-0922, Zheng, Jianjun, Liu, Jiang
et al (show 2 more authors) (2021) Automatic Sequence-Based Network for Lung Diseases Detection in Chest CT. FRONTIERS IN ONCOLOGY, 11. 781798-.

Access the full-text of this item by clicking on the Open Access link.


<h4>Objective</h4>To develop an accurate and rapid computed tomography (CT)-based interpretable AI system for the diagnosis of lung diseases.<h4>Background</h4>Most existing AI systems only focus on viral pneumonia (e.g., COVID-19), specifically, ignoring other similar lung diseases: e.g., bacterial pneumonia (BP), which should also be detected during CT screening. In this paper, we propose a unified sequence-based pneumonia classification network, called SLP-Net, which utilizes consecutiveness information for the differential diagnosis of viral pneumonia (VP), BP, and normal control cases from chest CT volumes.<h4>Methods</h4>Considering consecutive images of a CT volume as a time sequence input, compared with previous 2D slice-based or 3D volume-based methods, our SLP-Net can effectively use the spatial information and does not need a large amount of training data to avoid overfitting. Specifically, sequential convolutional neural networks (CNNs) with multi-scale receptive fields are first utilized to extract a set of higher-level representations, which are then fed into a convolutional long short-term memory (ConvLSTM) module to construct axial dimensional feature maps. A novel adaptive-weighted cross-entropy loss (ACE) is introduced to optimize the output of the SLP-Net with a view to ensuring that as many valid features from the previous images as possible are encoded into the later CT image. In addition, we employ sequence attention maps for auxiliary classification to enhance the confidence level of the results and produce a case-level prediction.<h4>Results</h4>For evaluation, we constructed a dataset of 258 chest CT volumes with 153 VP, 42 BP, and 63 normal control cases, for a total of 43,421 slices. We implemented a comprehensive comparison between our SLP-Net and several state-of-the-art methods across the dataset. Our proposed method obtained significant performance without a large amount of data, outperformed other slice-based and volume-based approaches. The superior evaluation performance achieved in the classification experiments demonstrated the ability of our model in the differential diagnosis of VP, BP and normal cases.

Item Type: Article
Uncontrolled Keywords: deep learning, CT, CNN, ConvLSTM, lung diseases
Divisions: Faculty of Health and Life Sciences
Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences
Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 25 Apr 2022 08:00
Last Modified: 18 Jan 2023 21:04
DOI: 10.3389/fonc.2021.781798
Open Access URL:
Related URLs: