# A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images

arXiv: https://arxiv.org/abs/2106.14403 · HTML: https://mlsanity.com/paper/2106.14403/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 28 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Deep Transparent Prediction through Latent Representation Analysis](https://mlsanity.com/paper/2009.07044/) (2020)
- [MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysis](https://mlsanity.com/paper/2106.07524/) (2021)
- [COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images](https://mlsanity.com/paper/2009.05383/) (2020)
- [COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning](https://mlsanity.com/paper/2101.07433/) (2021)
- [Towards Good Practices for Very Deep Two-Stream ConvNets](https://mlsanity.com/paper/1507.02159/) (2015)
- [COVID-FACT: A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans](https://mlsanity.com/paper/2010.16041/) (2020)
- [Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans](https://mlsanity.com/paper/2101.05442/) (2021)
- [Detecting COVID-19 and Community Acquired Pneumonia using Chest CT scan images with Deep Learning](https://mlsanity.com/paper/2104.05121/) (2021)
- [CT-CAPS: Feature Extraction-based Automated Framework for COVID-19 Disease Identification from Chest CT Scans using Capsule Networks](https://mlsanity.com/paper/2010.16043/) (2020)

## Built on by (most cited first, 6 of 6)

- [COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings](https://mlsanity.com/paper/2206.15073/) (2022)
- [Data Augmentation and CNN Classification For Automatic COVID-19 Diagnosis From CT-Scan Images On Small Dataset](https://mlsanity.com/paper/2108.07148/) (2021)
- [CardioSyntax: end-to-end SYNTAX score prediction -- dataset, benchmark and method](https://mlsanity.com/paper/2407.19894/) (2024)
- [Deep Learning Based Automated COVID-19 Classification from Computed Tomography Images](https://mlsanity.com/paper/2111.11191/) (2021)
- [Two-Stage COVID19 Classification Using BERT Features](https://mlsanity.com/paper/2206.14861/) (2022)
- [Res-Dense Net for 3D Covid Chest CT-scan classification](https://mlsanity.com/paper/2208.04613/) (2022)

## Abstract (arXiv)

We present an automatic COVID1-19 diagnosis framework from lung CT-scan slice images. In this framework, the slice images of a CT-scan volume are first proprocessed using segmentation techniques to filter out images of closed lung, and to remove the useless background. Then a resampling method is used to select one or multiple sets of a fixed number of slice images for training and validation. A 3D CNN network with BERT is used to classify this set of selected slice images. In this network, an embedding feature is also extracted. In cases where there are more than one set of slice images in a volume, the features of all sets are extracted and pooled into a global feature vector for the whole CT-scan volume. A simple multiple-layer perceptron (MLP) network is used to further classify the aggregated feature vector. The models are trained and evaluated on the provided training and validation datasets. On the validation dataset, the accuracy is 0.9278 and the F1 score is 0.9261.