Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 43 min ago
Peer-reviewedCC BYArchives of Computational Methods in Engineering

A Comprehensive Review Tracing the Evolution of Volumetric Medical Imaging Analysis from Classic CNNs to Emerging AI-Agents

  • Muhammad Owais1
  • Muhammad Zubair2
  • Daniya Najiha Abdul Kareem3
  • Sana Akhtar Naseer4
  • Mehbub Alam5
  • Mubashir Ahmad6
  • Irfan Hussain1
6 affiliations
  1. 1Khalifa University Center for Autonomous Robotic Systems (KU-CARS), Khalifa University, Abu Dhabi, 127788, United Arab Emirates
  2. 2School of Computer Science, University of Galway, Galway, H91 TK33, Ireland
  3. 3Autonomous Robotics Research Center (ARRC), Technology Innovation Institute (TII), Abu Dhabi, 127788, United Arab Emirates
  4. 4School of Artificial Intelligence, University of Management and Technology, Lahore, Pakistan
  5. 5Department of Computer Science and Engineering, Indian Institute of Information Technology Raichur, Raichur, Karnataka, 584102, India
  6. 6IRC for Finance and Digital Economy, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia
Open at sourcePDFDOICite

Abstract

Volumetric medical imaging has redefined modern healthcare, enabling precise diagnosis, prognosis, and treatment planning. During the past decade, the field has undergone a paradigm shift from classical deep learning architectures to multimodal, agent-driven AI systems capable of uncovering rich volumetric biomarkers and utilizing heterogeneous data for predictive and generative modeling. Existing surveys are fragmented, focusing on specific models or tasks instead of offering a unified view of volumetric learning evolution. This study traces the evolution from classical models (Convolutional Neural Networks, Recurrent Neural Networks, and transformers) to generative approaches (Variational Autoencoders, Generative Adversarial Networks, and diffusion models) and finally to foundation models and AI-agents that enable advanced reasoning and adaptive clinical workflows. As the reported performance varies substantially across datasets, imaging modalities, and evaluation protocols, this review emphasizes methodological evolution, representative innovations, and practical implications rather than direct numerical ranking of competing architectures. For each paradigm, we critically assess methodological innovations, strengths, limitations, and comparative performance in segmentation, classification, detection, reconstruction, and report generation. Beyond synthesizing progress, we identify persistent challenges, including data scarcity, generalization between institutions, and clinical trustworthiness, and outline emerging frontiers in multimodal fusion, explainable AI, and human–AI collaboration. This review provides a unified framework for understanding the evolution of volumetric medical imaging and offers actionable insights for researchers, clinicians, and industry practitioners, contributing to the development of reliable, interpretable, and clinically deployable next-generation medical AI systems. To support further research, we provide a GitHub repository that includes popular 3D medical imaging datasets with recent 3D models in our shared GitHub repository (https://github.com/Owais-CodeHub/3D-Medical-Imaging-Review).

Related

  1. Editorial: Tracing the evolution of infection control for STIs: from historical roots to future directions
    Fausto Ciccacci, Fernanda Khouri Barreto, Fifonsi Adjidossi Gbeasor-Komlanvi
    Frontiers in Public HealthPeer-reviewedCC BY 4.0Epidemiology & public healthCrossref
  2. Tracing the Evolution of Research on Breaking Bad News: A Global Analysis of Publications
    S. Mujeeb, L. Ponnuchamy, G. Majhi +4
    medRxivPreprintCC BY-NCFull textGeneral medicinemedRxiv
  3. The emerging discipline has emerged: cardio-oncology as a medical specialty
    Yohannes T. Ghebre, Derek R. Shyr, Pius S. Fasinu
    Frontiers in Cardiovascular MedicinePeer-reviewedCC BY 4.0Full textCardiovascular medicineCrossref
  4. Emerging Therapeutic Strategies for Neurodegenerative Diseases: A Comprehensive Review of Recent Advances and Future Directions
    Masood Sepehrimanesh, Sarah Victoria Melen, Fatima Yeasmin +5
    CellsPeer-reviewedCC BY11 citedNeurosciencePhysiologyOpenAlex
  5. Curcumin, Resveratrol and Berberine as Emerging Therapeutic Agents in Treatment of Gliomas: A Comprehensive Review
    Dominika Kunachowicz, Julia Kostrzewa, Paulina Tomecka +8
    MoleculesPeer-reviewedCC BY 4.0Human geneticsCrossref

Cite

BibTeXRIS
BibTeX
@article{owais2026comprehensive,
  title = {{A Comprehensive Review Tracing the Evolution of Volumetric Medical Imaging Analysis from Classic CNNs to Emerging AI-Agents}},
  author = {Muhammad Owais and Muhammad Zubair and Daniya Najiha Abdul Kareem and Sana Akhtar Naseer and Mehbub Alam and Mubashir Ahmad and Irfan Hussain},
  journal = {Archives of Computational Methods in Engineering},
  year = {2026},
  month = aug,
  doi = {10.1007/s11831-026-10738-w},
  url = {https://doi.org/10.1007/s11831-026-10738-w},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - A Comprehensive Review Tracing the Evolution of Volumetric Medical Imaging Analysis from Classic CNNs to Emerging AI-Agents
AU  - Muhammad Owais
AU  - Muhammad Zubair
AU  - Daniya Najiha Abdul Kareem
AU  - Sana Akhtar Naseer
AU  - Mehbub Alam
AU  - Mubashir Ahmad
AU  - Irfan Hussain
PY  - 2026
DA  - 2026/08/05
JO  - Archives of Computational Methods in Engineering
DO  - 10.1007/s11831-026-10738-w
UR  - https://doi.org/10.1007/s11831-026-10738-w
AB  - Volumetric medical imaging has redefined modern healthcare, enabling precise diagnosis, prognosis, and treatment planning. During the past decade, the field has undergone a paradigm shift from classical deep learning architectures to multimodal, agent-driven AI systems capable of uncovering rich volumetric biomarkers and utilizing heterogeneous data for predictive and generative modeling. Existing surveys are fragmented, focusing on specific models or tasks instead of offering a unified view of volumetric learning evolution. This study traces the evolution from classical models (Convolutional Neural Networks, Recurrent Neural Networks, and transformers) to generative approaches (Variational Autoencoders, Generative Adversarial Networks, and diffusion models) and finally to foundation models and AI-agents that enable advanced reasoning and adaptive clinical workflows. As the reported performance varies substantially across datasets, imaging modalities, and evaluation protocols, this review emphasizes methodological evolution, representative innovations, and practical implications rather than direct numerical ranking of competing architectures. For each paradigm, we critically assess methodological innovations, strengths, limitations, and comparative performance in segmentation, classification, detection, reconstruction, and report generation. Beyond synthesizing progress, we identify persistent challenges, including data scarcity, generalization between institutions, and clinical trustworthiness, and outline emerging frontiers in multimodal fusion, explainable AI, and human–AI collaboration. This review provides a unified framework for understanding the evolution of volumetric medical imaging and offers actionable insights for researchers, clinicians, and industry practitioners, contributing to the development of reliable, interpretable, and clinically deployable next-generation medical AI systems. To support further research, we provide a GitHub repository that includes popular 3D medical imaging datasets with recent 3D models in our shared GitHub repository (https://github.com/Owais-CodeHub/3D-Medical-Imaging-Review).
SN  - 1134-3060
SN  - 1886-1784
ER  -