AUTHOR=Hao Jinkui , Xie Jianyang , Liu Ri , Hao Huaying , Ma Yuhui , Yan Kun , Liu Ruirui , Zheng Yalin , Zheng Jianjun , Liu Jiang , Zhang Jingfeng , Zhao Yitian 

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

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.781798

DOI=10.3389/fonc.2021.781798

ISSN=2234-943X

ABSTRACT=Developing an accurate and rapid AI system for the diagnosis of pneumonia could play a vital role in enabling timely quarantine and medical treatment.
However, 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.
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 do 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. 
%Given the fact that the final diagnosis conclusion needs to be made for each patient, case-based prediction rather than a slice- or sequence-based prediction are more valuable,
In addition, we employ sequence attention maps for auxiliary classification to enhance the confidence level of the results and produce a case-level prediction.
For evaluation, we construct 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 implement a comprehensive comparison between our SLP-Net and several state-of-the-art methods across the dataset. Our proposed method obtains significant performance without a large amount of data, outperforms other slice-based and volume-based approaches.
The superior evaluation performance achieved in the classification experiments demonstrate the ability of our model in the differential diagnosis of VP, BP and normal cases.