MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray

Abstract

Background COVID-19 has caused 3.34m deaths till 13/May/2021. It is now still causing confirmed cases and ongoing deaths every day. Method This study investigated whether fusing chest CT with chest X-ray can help improve the AI's diagnosis performance. Data harmonization is employed to make a homogeneous dataset. We create an end-to-end multiple-input deep convolutional attention network (MIDCAN) by using the convolutional block attention module (CBAM). One input of our model receives 3D chest CT image, and other input receives 2D X-ray image. Besides, multiple-way data augmentation is used to generate fake data on training set. Grad-CAM is used to give explainable heatmap. Results The proposed MIDCAN achieves a sensitivity of 98.10±1.88%, a specificity of 97.95±2.26%, and an accuracy of 98.02±1.35%. Conclusion Our MIDCAN method provides better results than 8 state-of-the-art approaches. We demonstrate the using multiple modalities can achieve better results than individual modality. Also, we demonstrate that CBAM can help improve the diagnosis performance.

RETRACTED: PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

“…The multiple-way data augmentation (MDA) method is used to help create fake training images so as to make our AI model avoid overfitting (22). Compared to traditional data augmentation (DA), MDA can provide more diverse images than DA.…”

KL-MOB: automated COVID-19 recognition using a novel approach based on image enhancement and a modified MobileNet CNN

“…There is definitely still room for improvement through: (a) the other preprocesses such as increasing the number of images, implementing another preprocessing technique, i.e ., data augmentation, utilizing different noise filters, and enhancement techniques. (b) design a model that deals with multiple inputs simultaneously, where utilizing multiple modalities may achieve superior outcomes than the individual modality ( Zhang et al, 2021 ).…”

“…However, the most prevalent studies have focused only on some of these types of noise ( e.g ., Gaussian and Poisson). In particular, among many other techniques, histogram equalization (HE) ( Civit-Masot et al, 2020 ; Tartaglione et al, 2020 , Rezaul Karim et al, 2020 ), contrast limited adaptive histogram equalization (CLAHE) ( El-bana, Al-Kabbany & Sharkas, 2020 ; Saiz & Barandiaran, 2020 ; Maguolo & Nanni, 2021 ; Ramadhan et al, 2020 ), adaptive total variation method (ATV) ( Punn & Agarwal, 2021 ), white balance followed by CLAHE ( Siddhartha & Santra, 2020 ), intensity normalization followed by CLAHE (N-CLAHE) ( Horry et al, 2020 ; El Asnaoui & Chawki, 2020 ), Perona-Malik filter (PMF), unsharp masking (UM) ( Rezaul Karim et al, 2020 ), Bi-histogram equalization with adaptive sigmoid function (BEASF) ( Haghanifar et al, 2020 ), the gamma correction (GC) ( Rahman et al, 2021b ), histogram stretching (HS) ( Wang et al, 2021 ; Zhang et al, 2021 ), Moment Exchange algorithm (MoEx), CLAHE ( Lv et al, 2021 ), local phase enhancement (LPE) ( Qi et al, 2021 ), image contrast enhancement algorithm (ICEA) ( Canayaz, 2021 ), and Gaussian filter ( Medhi, Jamil & Hussain, 2020 ) are, as far as we are aware, the only adopted techniques in COVID-19 recognition to date. An overview of these works is listed in Table 1 .…”

A complete framework for accurate recognition and prognosis of COVID-19 patients based on deep transfer learning and feature classification approach

“…They are just examples of the massive work concerning the application of deep learning on the detection of COVID-19 (Zhang et al. 2021a , b ; Sharma 2021 ; Mukherjee et al. 2021 ; Abdulkareem et al.…”