AlexNet for Image-Based COVID-19 Diagnosis

Min Tang, Yibin Peng, Shuihua Wang, Shuwen Chen*, Yudong Zhang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

The medical community is working harder to develop quick and accurate methods of diagnosing the virus in response to the COVID-19 pandemic. The speed and efficiency of image-based COVID-19 diagnosis are its benefits, but it also carries a risk of error and necessitates the involvement of numerous skilled radiologists. In this paper, a novel convolutional neural network architecture called AlexNet is presented. It has the capacity to automatically learn features in a hierarchy and recognize complex patterns and improves the model’s recognition of disease-related features. In addition, AlexNet’s adaptability and generalization capabilities contribute to its effectiveness in processing various imaging datasets. AlexNet therefore has great potential to identify complex patterns associated with COVID-19-related lung abnormalities. Nevertheless, it also has certain limitations, including the need for a large amount of processing power, the possibility of overfitting, the lack of sufficient interpretability, and the need for further development in order to make it more applicable to particular diagnostic tasks. In summary, collaborative efforts between the AI research community and healthcare professionals will continue to seek accurate, efficient, and ethical solutions for image-based COVID-19 diagnosis.

Original languageEnglish
Title of host publicationProceedings of 2023 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2023) - Medical Imaging and Computer-Aided Diagnosis
EditorsRuidan Su, Yu-Dong Zhang, Alejandro F. Frangi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages166-176
Number of pages11
ISBN (Print)9789819713349
DOIs
Publication statusPublished - 2024
EventInternational Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2023 - Cambridge, United Kingdom
Duration: 9 Dec 202310 Dec 2023

Publication series

NameLecture Notes in Electrical Engineering
Volume1166 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2023
Country/TerritoryUnited Kingdom
CityCambridge
Period9/12/2310/12/23

Keywords

  • AlexNet
  • COVID-19
  • X-rays and CT scans

Fingerprint

Dive into the research topics of 'AlexNet for Image-Based COVID-19 Diagnosis'. Together they form a unique fingerprint.

Cite this