Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window
Not on the map. Why?
Abstract (arXiv)
Since the pandemic of COVID-19, several deep learning methods were proposed to analyze the chest Computed Tomography (CT) for diagnosis. In the current situation, the disease course classification is significant for medical personnel to decide the treatment. Most previous deep-learning-based methods extract features observed from the lung window. However, it has been proved that some appearances related to diagnosis can be observed better from the mediastinal window rather than the lung window, e.g., the pulmonary consolidation happens more in severe symptoms. In this paper, we propose a novel Dual Window RCNN Network (DWRNet), which mainly learns the distinctive features from the successive mediastinal window. Regarding the features extracted from the lung window, we introduce the Lung Window Attention Block (LWA Block) to pay additional attention to them for enhancing the mediastinal-window features. Moreover, instead of picking up specific slices from the whole CT slices, we use a Recurrent CNN and analyze successive slices as videos. Experimental results show that the fused and representative features improve the predictions of disease course by reaching the accuracy of 90.57%, against the baseline with an accuracy of 84.86%. Ablation studies demonstrate that combined dual window features are more efficient than lung-window features alone, while paying attention to lung-window features can improve the model's stability.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 8 Jun 2022.
Builds on
18 of 40 references.
References · 18
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
- 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
- 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
- 2016Image Captioning with Semantic Attentioncited by 260
- 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
- 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
- 2015DRAW: A Recurrent Neural Network For Image Generationcited by 190
- 2020Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Imagescited by 184
- 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
- 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
6 more
- 2020Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networkscited by 70
- 2020Deep Learning COVID-19 Features on CXR using Limited Training Data Setscited by 68
- 2020Normalized and Geometry-Aware Self-Attention Network for Image Captioningcited by 63
- 2019HA-CCN: Hierarchical Attention-based Crowd Counting Networkcited by 32
- 2020Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumoniacited by 26
- 2020Diagnosis of Coronavirus Disease 2019 (COVID-19) with Structured Latent Multi-View Representation Learningcited by 15
Built on by
Citing papers per year: 2025: 2.
2 papers.