Mini-COVIDNet: Mobile friendly point-of-care detection of COVID19 using Ultrasound Images

We (Medical Imaging Group (MIG), CDS, IISc Bangalore and ACPS Group, ICT, UiA Campus Grimstad) have developed a Mobile-friendly deep learning model for point-of-care detection of COVID19 using Ultrasound Images for better triaging of patients. This manuscript is accepted for publication in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (Special issue on Ultrasound in COVID-19 and Lung Diagnostics).

Navchetan Awasthi, Aveen Dayal, Linga R. Cenkeramaddi, and Phaneendra K. Yalavarthy, “Mini-COVIDNet : Efficient Light Weight Deep Neural Network for Ultrasound based Point-of-Care Detection of COVID-19,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (Special issue on Ultrasound in COVID-19 and Lung Diagnostics) 2021 (in press). [Reprint is available at: http://cds.iisc.ac.in/faculty/yalavarthy/Publications.html]
Project Repository: https://github.com/navchetan-awasthi/Mini-COVIDNet

Keywords: COVID-19, Lung, Ultrasonic imaging, Computed, tomography, Imaging, Diseases, X-ray imaging

Abstract: Lung ultrasound imaging has the potential to be an effective point-of-care test for detection of COVID-19, due to its ease of operation with minimal personal protection equipment along with easy disinfection. The current state-of-the-art deep learning models for detection of COVID-19 are heavy models that may not be easy to deploy in commonly utilized mobile platforms in point-of-care testing. In this work, we developed a lightweight mobile-friendly efficient deep learning model for the detection of COVID-19 using lung ultrasound images. The developed method was shown to be sensitive to the damage to the pleural surface of the lung, which has been proven to have prognostic value, commonly observed in intensive care unit–admitted and deceased patients. The developed model has utility in the context of a massive COVID-19 pandemic, where it can better triage patients with pulmonary symptoms (suspected of infection).

More details:DOI: 10.1109/TUFFC.2021.3068190


The article, “Anam-Net : Anamorphic Depth Embedding based Light-Weight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images” by Paluru, Naveen; Dayal, Aveen; Jenssen, Havard ; Sakinis, Tomas; Cenkeramaddi, Linga Reddy; Prakash, Jaya; Yalavarthy, Phaneendra, has been accepted for publication as a [Fast Track: COVID-19 Focused Papers] in the IEEE Transactions on Neural Networks and Learning Systems.

Naveen Paluru, Aveen Dayal, Havard B. Jenssen, Tomas Sakinis, Linga R. Cenkeramaddi, Jaya Prakash, and Phaneendra K. Yalavarthy, “Anam-Net : Anamorphic Depth Embedding based Light-Weight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images,” IEEE Transactions on Neural Networks and Learning Systems (Fast Track: COVID-19 Focused Papers) 2021 (in press).

Keywords: COVID-19, Coronavirus, Deep Learning, Segmentation, and Abnormalities.

Abstract: Chest computed tomography (CT) imaging has become indispensable for staging and managing of COVID-19, and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding based light-weight CNN, called Anam-Net, to segment anomalies in COVID-19 Chest CT images. The proposed Anam-Net has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it light-weight capable of providing inferences in mobile or resource constraint (point-of-care) platforms. The results from chest CT images (test cases) across different experiments showed that the proposed method could provide good Dice similarity scores for abnormal as well as normal regions in the lung. We have benchmarked Anam-Net with other state-of-the-art architectures like ENet, LEDNet, UNet++, SegNet, Attention UNet and DeepLabV3+. The proposed AnamNet was also deployed on embedded systems like Raspberry Pi 4, NVIDIA Jetson Xavier, and mobile based Android application (CovSeg) embedded with Anam-Net to demonstrate its suitability for point-of-care platforms. The generated codes, models, and the mobile application are available for enthusiastic users at https://github.com/NaveenPaluru/Segmentation-COVID-19.