Determining and Measuring the Amount of Region Having COVID-19 on Lung Images

Tuncer, Seda Arslan; Çınar, Ahmet; Tuncer, Taner; Çolak, Fatih

doi:10.2478/acss-2021-0023

Abstract

It is important to know how much the lungs are affected in the course of the disease in patients with COVID-19. Detecting infected tissues on CT lung images not only helps diagnose the disease but also helps measure the severity of the disease. In this paper, using the hybrid artificial intelligence-based segmentation method, which we call TA-Segnet, it has been revealed how the region with COVID-19 affects the lung on 2D CT images. A hybrid convolutional neural network-based segmentation method (TA-Segnet) has been developed for this process. We use “COVID-19 CT Lung and Infection Segmentation Dataset” and “COVID-19 CT Segmentation Dataset” to evaluate TA-SegNET. At first, the tissues with COVID-19 on each lung image are determined, then the measurements obtained are evaluated according to the parameters of Accuracy, Dice, Jaccard, Mean Square Error, Mutual Information and Cross-correlation. Accuracy, Dice, Jaccard, Mean Square Error, Mutual Information and Cross-correlation values for data set-1 are 98.63 %, 0.95, 0.919, 0.139, 0.51, and 0.904, respectively. For data set-2, these parameters are 98.57 %, 0.958, 0.992, 0.0088, 0.565 and 0.8995, respectively. Second, the ratio of COVID-19 regions relative to the lung region on CT images is determined. This ratio is compared with the values in the original data set. The results obtained show that such an artificial intelligence-based method during the pandemic period will help prioritize and automate the diagnosis of COVID-19 patients.

References

[1] S. Roy et al., “Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2676–2687, Aug. 2020. https://doi.org/10.1109/TMI.2020.299445910.1109/TMI.2020.299445932406829
Search in Google Scholar Back to article
[2] J. Born et. al., “POCOVID-Net: Automatic detection of COVID-19 from a new lung ultrasound imaging dataset (POCUS),” ArXiv, Art no. 2004.12084, 2020.
Search in Google Scholar Back to article
[3] Q Hao et al., “DenseCapsNet: Detection of COVID-19 from X-ray images using a capsule neural network,” Computers in Biology and Medicine, vol. 133, Art no. 104399, June 2021. https://doi.org/10.1016/j.compbiomed.2021.10439910.1016/j.compbiomed.2021.104399804919033892307
Search in Google Scholar Back to article
[4] T. Ozturk et al., “Automated detection of COVID-19 cases using deep neural networks with X-ray images,” Computers in Biology and Medicine, vol. 121, Art no. 103792, June 2020. https://doi.org/10.1016/j.compbiomed.2020.10379210.1016/j.compbiomed.2020.103792718788232568675
Search in Google Scholar Back to article
[5] M. Z. Alom et.al., “COVID_MTNet: COVID-19 detection with multi-task deep learning approaches,” ArXiv, Art no. 2004.03747, 2020.
Search in Google Scholar Back to article
[6] A. Altan and S. Karasu, “Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique,” Chaos, Solitons & Fractals, vol. 140, Art no. 110071, pp. 1–10, Nov. 2020. https://doi.org/10.1016/j.chaos.2020.11007110.1016/j.chaos.2020.110071733296032834627
Search in Google Scholar Back to article
[7] A. Voulodimos et al., “Deep learning models for COVID-19 infected area segmentation in CT images,” medRxiv, May 2020. https://doi.org/10.1101/2020.05.08.2009466410.1101/2020.05.08.20094664
Search in Google Scholar Back to article
[8] T. Yan et al., “Automatic distinction between COVID-19 and common pneumonia using multi-scale convolutional neural network on chest CT scans”, Chaos, Solutions & Fractals, Art no. 110153, Nov. 2020. https://doi.org/10.1016/j.chaos.2020.11015310.1016/j.chaos.2020.110153738189532834641
Search in Google Scholar Back to article
[9] A. Abbas et al., “Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network,” ArXiv, Art no. 2003.13815, 2020.10.1101/2020.03.30.20047456
Search in Google Scholar Back to article
[10] H. Panwar et al., “Application of deep learning for fast detection of COVID-19 in X-rays using nCOVnet,” Chaos, Solitons & Fractals, Art no. 109944, 2020.10.1016/j.chaos.2020.109944
Search in Google Scholar Back to article
[11] P. Hambarde et al., “Prostate lesion segmentation in MR images using radiomics based deeply supervised U-Net,” Biocybernetics and Biomedical Engineering, vol. 40, no. 4, pp. 1421–1435, 2020. https://doi.org/10.1016/j.bbe.2020.07.01110.1016/j.bbe.2020.07.011
Search in Google Scholar Back to article
[12] B. Wu et al., “Left ventricle automatic segmentation in cardiac MRI using a combined CNN and U-net approach,” Computerized Medical Imaging and Graphics, vol.82, Art no. 101719, June 2020. https://doi.org/10.1016/j.compmedimag.2020.10171910.1016/j.compmedimag.2020.10171932325284
Search in Google Scholar Back to article
[13] M. Byra et al., “Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network,” Biomedical Signal Processing and Control, vol. 61, Art no. 102027, Aug. 2020. https://doi.org/10.1016/j.bspc.2020.10202710.1016/j.bspc.2020.102027854527534703489
Search in Google Scholar Back to article
[14] R. M. Rad et al., “Trophectoderm segmentation in human embryo images via inceptioned U-Net,” Medical Image Analysis, vol. 62, Art no. 101612, May 2020. https://doi.org/10.1016/j.media.2019.10161210.1016/j.media.2019.10161232120267
Search in Google Scholar Back to article
[15] A. Khanna et al., “A deep Residual U-Net convolutional neural network for automated lung segmentation in computed tomography images,” Biocybernetics and Biomedical Engineering, vol. 40, no. 3, pp.1314–1327, 2020. https://doi.org/10.1016/j.bbe.2020.07.00710.1016/j.bbe.2020.07.007
Search in Google Scholar Back to article
[16] S. Li, et al., “Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation”, Expert Systems with Applications, vol. 145, 2020, 113131.10.1016/j.eswa.2019.113131
Search in Google Scholar Back to article
[17] N. Sambyal et al., “Modified U-Net architecture for semantic segmentation of diabetic retinopathy images,” Biocybernetics and Biomedical Engineering, vol. 40, no. 3, pp.1094–1109, 2020. https://doi.org/10.1016/j.bbe.2020.05.00610.1016/j.bbe.2020.05.006
Search in Google Scholar Back to article
[18] M. Dash et al., “PsLSNet: Automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network,” Biomedical Signal Processing and Control, vol. 52, pp. 226–237, Jul. 2019. https://doi.org/10.1016/j.bspc.2019.04.00210.1016/j.bspc.2019.04.002
Search in Google Scholar Back to article
[19] D. Lin et al., “RefineU-Net: Improved U-Net with progressive global feedbacks and residual attention guided local refinement for medical image segmentation,” Pattern Recognition Letters, vol. 138, pp. 267–275, Oct. 2020. https://doi.org/10.1016/j.patrec.2020.07.01310.1016/j.patrec.2020.07.013
Search in Google Scholar Back to article
[20] M. S. Hossain, “Microc alcification segmentation using modified U-Net segmentation network from mammogram images”, Journal of King Saud University - Computer and Information Sciences, Nov. 2019. https://doi.org/10.1016/j.jksuci.2019.10.01410.1016/j.jksuci.2019.10.014
Search in Google Scholar Back to article
[21] Z. Liu et al., “Liver CT sequence segmentation based with improved UNet and graph cut,” Expert Systems with Applications, vol. 126, pp. 54–63, Jul. 2019. https://doi.org/10.1016/j.eswa.2019.01.05510.1016/j.eswa.2019.01.055
Search in Google Scholar Back to article
[22] G. Tong et al., “Improved U-NET network for pulmonary nodules segmentation,” Optik, vol. 174, pp. 460–469, Dec. 2018. https://doi.org/10.1016/j.ijleo.2018.08.08610.1016/j.ijleo.2018.08.086
Search in Google Scholar Back to article
[23] C. Zheng et al., “Deep learning-based detection for COVID-19 from chest CT using weak label,” medRxiv, 2020. https://doi.org/10.1101/2020.03.12.2002718510.1101/2020.03.12.20027185
Search in Google Scholar Back to article
[24] Y. Cao et al., “Longitudinal assessment of COVID-19 using a deep learning–based quantitative CT pipeline: Illustration of two cases,” Radiology: Cardiothoracic Imaging, vol. 2, no. 2, 2020. https://doi.org/10.1148/ryct.202020008210.1148/ryct.2020200082723343233778563
Search in Google Scholar Back to article
[25] J. Chen et al., “Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography: A prospective study,” medRxiv, Mar. 2020. https://doi.org/10.1101/2020.02.25.2002156810.1101/2020.02.25.20021568
Search in Google Scholar Back to article
[26] S. Jin et al., “AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system in four weeks,” medRxiv, Mar. 2020. https://doi.org/10.1101/2020.03.19.2003935410.1101/2020.03.19.20039354
Search in Google Scholar Back to article
[27] D. P. Fan et al., “Inf-Net: automatic COVID-19 lung infection segmentation from CT images,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, Aug. 2020. https://doi.org/10.1109/TMI.2020.299664510.1109/TMI.2020.299664532730213
Search in Google Scholar Back to article
[28] S. Narges et al., “COVID TV-UNet: Segmenting COVID-19 chest CT images using connectivity imposed U-Net,” ArXiv, Art no. 2007.12303, Jul. 2020.
Search in Google Scholar Back to article
[29] “COVID-19 CT lung and infection segmentation dataset”, Zenodo, 2020. [Online]. Available: https://zenodo.org/record/3757476#.Ybh16WhBzIU. Accessed on: Feb. 02, 2020.
Search in Google Scholar Back to article
[30] “COVID-19 CT segmentation dataset”, 2020. [Online]. Available: http://medicalsegmentation.com/covid19/. Accessed on: Feb. 02, 2020.
Search in Google Scholar Back to article
[31] O. Ronneberger et al., “U-Net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, vol. 9351, Nov. 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_2810.1007/978-3-319-24574-4_28
Search in Google Scholar Back to article
[32] A. Alkan et al., “Comparative MR image analysis for thyroid nodule detection and quantification,” Measurement, vol. 47, pp. 861–868, Jan. 2014. https://doi.org/10.1016/j.measurement.2013.10.00910.1016/j.measurement.2013.10.009
Search in Google Scholar Back to article
[33] J. Bertels et al., “Optimizing the Dice score and Jaccard index for medical image segmentation: Theory and practice,” in Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, vol 11765, Cham, Switzerland: Springer, pp. 92–100, Oct. 2019. https://doi.org/10.1007/978-3-030-32245-8_1110.1007/978-3-030-32245-8_11
Search in Google Scholar Back to article
[34] M. E. Khalifa et al., “Medical image registration using mutual information similarity measure,” in 13th International Conference on Biomedical Engineering, vol. 23, 2009, pp. 151–155. https://doi.org/10.1007/978-3-540-92841-6_3710.1007/978-3-540-92841-6_37
Search in Google Scholar Back to article
[35] B. Stoyanov, “B. BOOST: Medical image steganography using nuclear spin generator,” Entropy, vol. 22, no. 5, Art no. 501, Apr. 2020. https://doi.org/10.3390/e2205050110.3390/e22050501751698733286274
Search in Google Scholar Back to article
[36] Z. Wang et al., “Image quality assessment: From error measurement to structural similarity,” IEEE Transactions Image Processing, vol. 13, no. 4, pp. 600–612, Apr. 2004. https://doi.org/10.1109/TIP.2003.81986110.1109/TIP.2003.819861
Search in Google Scholar Back to article
[37] T. Zhou et al., “An automatic COVID-19 CT segmentation based on UNet with attention mechanism,” ArXiv, Art no. 2004.06673, Apr. 2020. [Online]. Available: https://arxiv.org/abs/2004.06673.
Search in Google Scholar Back to article
[38] A. Amyar et al., “Multi-task deep learning based CT imaging analysis for COVID-19: Classification and segmentation,” MedRxiv, Apr. 2020. https://doi.org/10.1101/2020.04.16.2006470910.1101/2020.04.16.20064709
Search in Google Scholar Back to article

Determining and Measuring the Amount of Region Having COVID-19 on Lung Images

Abstract

Paradigm

My account