# Machine Learning in Biomarker-Driven Precision Oncology: Automated Immunohistochemistry Scoring and Emerging Directions in Genitourinary Cancers

## TL;DR

This paper reviews how machine learning improves the consistency of immunohistochemistry scoring in cancer diagnosis and explores its potential in genitourinary cancers.

## Contribution

The paper highlights the application of machine learning to emerging biomarkers in genitourinary cancers, supporting precision oncology.

## Key findings

- Machine learning improves consistency and scalability in scoring established biomarkers like ER/PR and PD-L1.
- ML algorithms show early success in quantifying emerging biomarkers in genitourinary cancers, linking them to clinical outcomes.
- Challenges include limited training data and variability in staining protocols.

## Abstract

Immunohistochemistry (IHC) is a common test used by pathologists to detect cancer biomarkers, which can help with diagnosis, prognosis, and treatment selection. However, IHC results can vary between laboratories and between observers. New digital pathology tools and artificial intelligence (AI), particularly machine learning (ML) techniques, can analyse stained tissue more consistently. This review gives an overview of how ML is being used to automate IHC scoring, first in well-studied biomarkers and then emerging biomarkers. This review then explores how these innovations can apply to genitourinary (GU) oncology, including prostate, renal, and bladder tumours, for which researchers have begun applying ML to new biomarkers that may predict outcomes or treatment response. ML use in IHC scoring is promising but requires more validation.

Immunohistochemistry (IHC) is essential for diagnostic, prognostic, and predictive biomarker assessment in oncology, but manual interpretation is limited by subjectivity and inter-observer variability. Machine learning (ML), a computational subset of AI that allows algorithms to recognise patterns and learn from annotated datasets to make predictions or decisions, has led to advancements in digital pathology by supporting automated quantification of biomarker expression on whole-slide images (WSIs). This review evaluates the role of ML-assisted IHC scoring in the transition from validated biomarkers to the discovery of emerging prognostic and predictive IHC biomarkers for genitourinary (GU) tumours. Current applications include ML-based scoring of routinely used biomarkers such as ER/PR, HER2, mismatch repair (MMR) proteins, PD-L1, and Ki-67, demonstrating improved consistency and scalability. Emerging studies in GU cancers show that algorithms can quantify markers including androgen receptor (AR), PTEN, cytokeratins, Uroplakin II, Nectin-4 and immune checkpoint proteins, with early evidence indicating associations between ML-derived metrics and clinical outcomes. Important limitations remain, including limited availability of training datasets, variability in staining protocols, and regulatory challenges. Overall, ML-assisted IHC scoring is a reproducible and evolving approach that may support biomarker discovery and enhance precision GU oncology.