The current landscape of artificial intelligence in computational histopathology for cancer diagnosis

Aaditya Tiwari; Aruni Ghose; Maryam Hasanova; Sara Socorro Faria; Srishti Mohapatra; Sola Adeleke; Stergios Boussios

doi:10.1007/s12672-025-02212-z

The current landscape of artificial intelligence in computational histopathology for cancer diagnosis

Aaditya Tiwari
, Aruni Ghose
, Maryam Hasanova
, Sara Socorro Faria
, Srishti Mohapatra
, Sola Adeleke
, Stergios Boussios

Research output: Contribution to journal › Article › peer-review

Abstract

Artificial intelligence (AI) marks a frontier in histopathologic analysis shift towards the clinic, becoming a mainstream choice to interpret histological images. Surveying studies assessing AI applications in histopathology from 2013 to 2024, we review key methods (including supervised, unsupervised, weakly supervised and transfer learning) in deep learning-based pattern recognition in computational histopathology for diagnostic and prognostic purposes. Deep learning methods also showed utility in identifying a wide range of genetic mutations and standard pathology biomarkers from routine histology. This survey of 41 primary studies also encompasses key regions of AI applicability in histopathology in a multi-cancer review while marking prospects to introduce AI into the clinical setting with key examples including Swarm Learning and Data Fusion. [Abstract copyright: © 2025. The Author(s).]

Original language	English
Pages (from-to)	438
Journal	Hormones and Cancer
Volume	16
Issue number	1
DOIs	https://doi.org/10.1007/s12672-025-02212-z
Publication status	Published - 1 Apr 2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Artificial intelligence
Cancer
Computational
Deep learning
Histopathology
Machine learning

Access to Document

10.1007/s12672-025-02212-zLicence: CC BY-NC-ND

s12672-025-02212-z.pdfFinal published version, 1.98 MBLicence: CC BY-NC-ND

Cite this

@article{c475c7fa7008474fa483bbe2c91f2357,

title = "The current landscape of artificial intelligence in computational histopathology for cancer diagnosis",

abstract = "Artificial intelligence (AI) marks a frontier in histopathologic analysis shift towards the clinic, becoming a mainstream choice to interpret histological images. Surveying studies assessing AI applications in histopathology from 2013 to 2024, we review key methods (including supervised, unsupervised, weakly supervised and transfer learning) in deep learning-based pattern recognition in computational histopathology for diagnostic and prognostic purposes. Deep learning methods also showed utility in identifying a wide range of genetic mutations and standard pathology biomarkers from routine histology. This survey of 41 primary studies also encompasses key regions of AI applicability in histopathology in a multi-cancer review while marking prospects to introduce AI into the clinical setting with key examples including Swarm Learning and Data Fusion. [Abstract copyright: {\textcopyright} 2025. The Author(s).]",

keywords = "Artificial intelligence, Cancer, Computational, Deep learning, Histopathology, Machine learning",

author = "Aaditya Tiwari and Aruni Ghose and Maryam Hasanova and Faria, \{Sara Socorro\} and Srishti Mohapatra and Sola Adeleke and Stergios Boussios",

year = "2025",

month = apr,

day = "1",

doi = "10.1007/s12672-025-02212-z",

language = "English",

volume = "16",

pages = "438",

journal = "Hormones and Cancer",

issn = "1868-8497",

publisher = "Springer",

number = "1",

}

TY - JOUR

T1 - The current landscape of artificial intelligence in computational histopathology for cancer diagnosis

AU - Tiwari, Aaditya

AU - Ghose, Aruni

AU - Hasanova, Maryam

AU - Faria, Sara Socorro

AU - Mohapatra, Srishti

AU - Adeleke, Sola

AU - Boussios, Stergios

PY - 2025/4/1

Y1 - 2025/4/1

N2 - Artificial intelligence (AI) marks a frontier in histopathologic analysis shift towards the clinic, becoming a mainstream choice to interpret histological images. Surveying studies assessing AI applications in histopathology from 2013 to 2024, we review key methods (including supervised, unsupervised, weakly supervised and transfer learning) in deep learning-based pattern recognition in computational histopathology for diagnostic and prognostic purposes. Deep learning methods also showed utility in identifying a wide range of genetic mutations and standard pathology biomarkers from routine histology. This survey of 41 primary studies also encompasses key regions of AI applicability in histopathology in a multi-cancer review while marking prospects to introduce AI into the clinical setting with key examples including Swarm Learning and Data Fusion. [Abstract copyright: © 2025. The Author(s).]

AB - Artificial intelligence (AI) marks a frontier in histopathologic analysis shift towards the clinic, becoming a mainstream choice to interpret histological images. Surveying studies assessing AI applications in histopathology from 2013 to 2024, we review key methods (including supervised, unsupervised, weakly supervised and transfer learning) in deep learning-based pattern recognition in computational histopathology for diagnostic and prognostic purposes. Deep learning methods also showed utility in identifying a wide range of genetic mutations and standard pathology biomarkers from routine histology. This survey of 41 primary studies also encompasses key regions of AI applicability in histopathology in a multi-cancer review while marking prospects to introduce AI into the clinical setting with key examples including Swarm Learning and Data Fusion. [Abstract copyright: © 2025. The Author(s).]

KW - Artificial intelligence

KW - Cancer

KW - Computational

KW - Deep learning

KW - Histopathology

KW - Machine learning

U2 - 10.1007/s12672-025-02212-z

DO - 10.1007/s12672-025-02212-z

M3 - Article

SN - 1868-8497

VL - 16

SP - 438

JO - Hormones and Cancer

JF - Hormones and Cancer

IS - 1

ER -

The current landscape of artificial intelligence in computational histopathology for cancer diagnosis

Abstract

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this