Deep Convolutional Neural Networks in Medical Image Analysis: A Review

Ibomoiye Domor Mienye; Theo G. Swart; George Obaido; Matt Jordan; Philip Ilono

doi:10.3390/info16030195

Deep Convolutional Neural Networks in Medical Image Analysis: A Review

Ibomoiye Domor Mienye, Theo G. Swart, George Obaido, Matt Jordan, Philip Ilono

Electrical and Electronic Engineering Science

Research output: Contribution to journal › Review article › peer-review

Abstract

Deep convolutional neural networks (CNNs) have revolutionized medical image analysis by enabling the automated learning of hierarchical features from complex medical imaging datasets. This review provides a focused analysis of CNN evolution and architectures as applied to medical image analysis, highlighting their application and performance in different medical fields, including oncology, neurology, cardiology, pulmonology, ophthalmology, dermatology, and orthopedics. The paper also explores challenges specific to medical imaging and outlines trends and future research directions. This review aims to serve as a valuable resource for researchers and practitioners in healthcare and artificial intelligence.

Original language	English
Article number	195
Journal	Information (Switzerland)
Volume	16
Issue number	3
DOIs	https://doi.org/10.3390/info16030195
Publication status	Published - Mar 2025

Keywords

CNN
deep learning
image recognition
machine learning
medical imaging
segmentation

ASJC Scopus subject areas

Information Systems

Access to Document

10.3390/info16030195

Cite this

@article{009c11d99fae4c6691b1804ba79851b4,

title = "Deep Convolutional Neural Networks in Medical Image Analysis: A Review",

abstract = "Deep convolutional neural networks (CNNs) have revolutionized medical image analysis by enabling the automated learning of hierarchical features from complex medical imaging datasets. This review provides a focused analysis of CNN evolution and architectures as applied to medical image analysis, highlighting their application and performance in different medical fields, including oncology, neurology, cardiology, pulmonology, ophthalmology, dermatology, and orthopedics. The paper also explores challenges specific to medical imaging and outlines trends and future research directions. This review aims to serve as a valuable resource for researchers and practitioners in healthcare and artificial intelligence.",

keywords = "CNN, deep learning, image recognition, machine learning, medical imaging, segmentation",

author = "Mienye, {Ibomoiye Domor} and Swart, {Theo G.} and George Obaido and Matt Jordan and Philip Ilono",

note = "Publisher Copyright: {\textcopyright} 2025 by the authors.",

year = "2025",

month = mar,

doi = "10.3390/info16030195",

language = "English",

volume = "16",

journal = "Information (Switzerland)",

issn = "2078-2489",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "3",

}

TY - JOUR

T1 - Deep Convolutional Neural Networks in Medical Image Analysis

T2 - A Review

AU - Mienye, Ibomoiye Domor

AU - Swart, Theo G.

AU - Obaido, George

AU - Jordan, Matt

AU - Ilono, Philip

PY - 2025/3

Y1 - 2025/3

N2 - Deep convolutional neural networks (CNNs) have revolutionized medical image analysis by enabling the automated learning of hierarchical features from complex medical imaging datasets. This review provides a focused analysis of CNN evolution and architectures as applied to medical image analysis, highlighting their application and performance in different medical fields, including oncology, neurology, cardiology, pulmonology, ophthalmology, dermatology, and orthopedics. The paper also explores challenges specific to medical imaging and outlines trends and future research directions. This review aims to serve as a valuable resource for researchers and practitioners in healthcare and artificial intelligence.

AB - Deep convolutional neural networks (CNNs) have revolutionized medical image analysis by enabling the automated learning of hierarchical features from complex medical imaging datasets. This review provides a focused analysis of CNN evolution and architectures as applied to medical image analysis, highlighting their application and performance in different medical fields, including oncology, neurology, cardiology, pulmonology, ophthalmology, dermatology, and orthopedics. The paper also explores challenges specific to medical imaging and outlines trends and future research directions. This review aims to serve as a valuable resource for researchers and practitioners in healthcare and artificial intelligence.

KW - CNN

KW - deep learning

KW - image recognition

KW - machine learning

KW - medical imaging

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=105001033294&partnerID=8YFLogxK

U2 - 10.3390/info16030195

DO - 10.3390/info16030195

M3 - Review article

AN - SCOPUS:105001033294

SN - 2078-2489

VL - 16

JO - Information (Switzerland)

JF - Information (Switzerland)

IS - 3

M1 - 195

ER -

Deep Convolutional Neural Networks in Medical Image Analysis: A Review

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Research from University of Johannesburg Yields New Data on Information Technology (Deep Convolutional Neural Networks in Medical Image Analysis: A Review)

Cite this

Deep Convolutional Neural Networks in Medical Image Analysis: A Review

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Press/Media

Research from University of Johannesburg Yields New Data on Information Technology (Deep Convolutional Neural Networks in Medical Image Analysis: A Review)

Cite this