A systematic review on colon cancer classification by convolutional neural networks: Architecture, accuracy, and research directions - Takeaways - MDSpire

A systematic review on colon cancer classification by convolutional neural networks: Architecture, accuracy, and research directions

  • By

  • Jie Li

  • Weiwei Goh

  • N. Z. Jhanjhi

  • Ting Li

  • July 9, 2026

  • 0 min

Share

  • 1

    Colon cancer is a significant global health issue, with convolutional neural networks (CNNs) enhancing diagnostic accuracy in histopathological image processing.

  • 2

    CNNs have shown superior performance in bi-classification and multi-classification tasks for colon cancer compared to traditional machine learning methods.

  • 3

    A systematic review of CNN applications in colon cancer classification has not been previously conducted, highlighting a gap in the literature.

  • 4

    The study employs the PRISMA method and PICOS framework to systematically select and evaluate relevant publications from 2020 to 2025.

  • 5

    Inclusion criteria for the review focus on peer-reviewed studies using CNNs for histopathological whole slide images with an accuracy of at least 85%.

Original Source(s)

A systematic review on colon cancer classification by convolutional neural networks: Architecture, accuracy, and research directions

  • by Jie Li, Weiwei Goh, N. Z. Jhanjhi, Ting Li

  • July 9, 2026

Related Content

Eight-year disease-free survival in clear cell adenocarcinoma of the urethra with surgery alone: a case report and literature review

Global burden and temporal trends of kidney cancer among children from 1990 to 2021: an analysis with projections to 2036

Single-cell sequencing uncovers clonal dynamics profiles and therapeutic resistance biomarkers in relapsed and refractory peripheral T-cell lymphoma