Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System

Demetris Gerogiannis, Anastasios Arsenos, Dimitrios Kollias, Dimitris Nikitopoulos, Stefanos Kollias

TL;DR

This paper showcases the integration and reliable and fast deployment of a state-of-the-art AI system designed to automatically analyze CT images, offering infection probability for the swift detection of COVID-19.

Abstract

Computer-aided diagnosis (CAD) systems stand out as potent aids for physicians in identifying the novel Coronavirus Disease 2019 (COVID-19) through medical imaging modalities. In this paper, we showcase the integration and reliable and fast deployment of a state-of-the-art AI system designed to automatically analyze CT images, offering infection probability for the swift detection of COVID-19. The suggested system, comprising both classification and segmentation components, is anticipated to reduce physicians' detection time and enhance the overall efficiency of COVID-19 detection. We successfully surmounted various challenges, such as data discrepancy and anonymisation, testing the time-effectiveness of the model, and data security, enabling reliable and scalable deployment of the system on both cloud and edge environments. Additionally, our AI system assigns a probability of infection to each 3D CT scan and enhances explainability through anchor set similarity, facilitating timely confirmation and segregation of infected patients by physicians.

COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System

TL;DR

This paper showcases the integration and reliable and fast deployment of a state-of-the-art AI system designed to automatically analyze CT images, offering infection probability for the swift detection of COVID-19.

Abstract

Computer-aided diagnosis (CAD) systems stand out as potent aids for physicians in identifying the novel Coronavirus Disease 2019 (COVID-19) through medical imaging modalities. In this paper, we showcase the integration and reliable and fast deployment of a state-of-the-art AI system designed to automatically analyze CT images, offering infection probability for the swift detection of COVID-19. The suggested system, comprising both classification and segmentation components, is anticipated to reduce physicians' detection time and enhance the overall efficiency of COVID-19 detection. We successfully surmounted various challenges, such as data discrepancy and anonymisation, testing the time-effectiveness of the model, and data security, enabling reliable and scalable deployment of the system on both cloud and edge environments. Additionally, our AI system assigns a probability of infection to each 3D CT scan and enhances explainability through anchor set similarity, facilitating timely confirmation and segregation of infected patients by physicians.
Paper Structure (8 sections, 4 figures)

This paper contains 8 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Materials and Model
  3. Dataset
  4. Deep learning model
  5. MLOps Orchestration
  6. Compliance with ethical standards
  7. Conclusion and Future Work
  8. Acknowledgments

Figures (4)

  • Figure 1: RACNet architecture
  • Figure 2: A complete diagram that explains the MLPod™ architecture and how the information flows between the various modules. Each module represents an individual service, while the rows visualize the flow of information. Please note that all communications are protected via encryption. The whole deployment of the MLPod™ platform can be considered as an MLOps sandbox.
  • Figure 3: A screenshot from an execution of the RACNet based Covid19 detection app. Note the visualization of the underlying pipeline steps. The LogicPod orchestrator automatically handles the communication of the required data in each step.
  • Figure 4: An instance of the final response of the RACNet model based diagnosis app. Once the underlying models’ execution is completed, LogicPod module automatically renders the models’ inference and provides a visual report about the patient’s condition, i.e., if the patient is Covid19 positive/negative along with a short text explanation and representative images associated with his/her medical condition.