Page 1 of 9
ISSN: 2692-5389 DOI: 10.33552/GJFSM.2024.02.000538
Global Journal of
Forensic Science & Medicine
Review Article Copyright © All rights are reserved by ala Ibor Oboma
The imperative of integrating digital image analysis
in evaluation of tumor tissue: A Review of African
Contemporary Landscape
Bassey Okon Ekpenyong
1
, Yibala Ibor Oboma
2
*, Elvis Tams Godams
3
, Salma Osman Mohammed
4
1
Department of Histopathology and Cytology, Faculty of medical laboratory science, Rivers State University Nkpolo - Oroworukwo, Port Harcourt River State.
2
Department of Medical Laboratory Sciences, School of Allied Health Sciences, Kampala International University Western Campus Uganda.
3
Department of Human Anatomy Rivers State University Nkpolo Oroworukwo Port Harcourt. Rivers State.
4
Department of Medical Laboratory Sciences, School of Allied Health Sciences, Kampala International University Western Campus Uganda.
*Corresponding author: Yibala Ibor Obama, Department of Medical Laboratory
Sciences, School of Allied Health Sciences, Kampala International University
Western Campus Uganda.
Received Date: November 23, 2024
Published Date: December 19, 2024
Abstract
Digital Image Analysis (DIA) has emerged as a transformative technology in the evaluation of tumor tissue. This offers significant improvements
in accuracy, reproducibility, and efficiency of diagnosis. Traditional histopathological methods rely on manual interpretation and often suffer from
variability and subjectivity with limited turnaround time. Leveraging advanced algorithms and machine learning (ML) techniques provides objective
and standardized assessments that enhance diagnostic precision and consistency. Technological advancements, particularly the development of
Whole Slide Imaging (WSI) and sophisticated WSI scanners, have been pivotal in advancing DIA. These tools facilitate the acquisition of high-
resolution, detailed images of the entire tissue sections, enabling comprehensive analysis. The integration of powerful software tools and AI
algorithms further enhances the diagnostic process by automating routine tasks and providing precise quantitative analyses of histopathology
and cytopathology. Machine learning, specifically deep learning, plays a crucial role in DIA. Deep learning models, trained on vast datasets of
histopathological images, can identify complex patterns and correlations, aiding in detecting and classifying tumors. These AI-driven tools offer
the potential for real-time analysis and predictive modeling, significantly impacting clinical decision-making and personalized patient care. Despite
its numerous advantages, DIA faces challenges including technical issues related to image quality and data management, as well as the need for
rigorous validation and standardization of algorithms. Additionally, the cost and accessibility of DIA technology pose barriers to its widespread
adoption, particularly in resource-limited settings. The future of DIA is promising, with ongoing advancements in imaging technologies, multi-omics
integration, and AI. These developments are expected to enhance the capabilities of DIA further, making it a standard practice in pathology and
improving patient outcomes. As DIA continues to evolve, it holds the potential to revolutionize the histochemical evaluation of tumor tissue, offering
new opportunities for innovation in diagnostics and personalized medicine in the African landscape.
Keywords: Integrating; digital; image; analysis
This work is licensed under Creative Commons Attribution 4.0 License GJFSM.MS.ID.000538.
Background
Evaluation of tumor (new growth) tissue involves the
examination of tissue samples using various techniques to identify
cellular and molecular features characteristic of the cancer
environment. Traditional methods rely heavily on the expertise
of pathologists to visually inspect and interpret stained (mostly
hematoxylin and eosin) tissue sections under a microscope,