# Integration of histopathological images and immunological analysis to predict M2 macrophage infiltration and prognosis in patients with serous ovarian cancer

## TL;DR

This study combines histopathological images and immunological data to predict M2 macrophage infiltration and prognosis in serous ovarian cancer patients, aiming to improve personalized treatment strategies.

## Contribution

A novel deep learning model using histopathological imaging features to predict M2 macrophage infiltration and prognosis in serous ovarian cancer.

## Key findings

- Higher M2 macrophage infiltration is significantly associated with poor prognosis in serous ovarian cancer patients.
- A deep learning model using histopathological images effectively predicted M2 macrophage infiltration with reasonable accuracy metrics.
- The Mean Probability Method was identified as the most effective strategy for predicting M2 macrophage infiltration from histopathological images.

## Abstract

Investigating the effect of M2 macrophage infiltration on overall survival and to use histopathological imaging features (HIF) to predict M2 macrophage infiltration in patients with serous ovarian cancer (SOC) is important for improving prognostic accuracy, identifying new therapeutic targets, and advancing personalized treatment approaches.

We downloaded data from 86 patients with SOC from The Cancer Genome Atlas (TCGA) and divided these patients into a training set and a validation set with a ratio of 8:2. In addition, tissue microarrays from 106 patients with SOC patients were included as an external validation set. HIF were recognized by deep multiple instance learning (MIL) to predict M2 macrophage infiltration via theResNet18 network in the training set. The final model was evaluated using the internal and external validation set.

Using data acquired from the TCGA database, we applied univariate Cox analysis and determined that higher levels of M2 macrophage infiltration were associated with a poor prognosis (hazard ratio [HR]=6.8; 95% CI [confidence interval]: 1.6–28, P=0.0083). External validation revealed that M2 macrophage infiltration was an independent risk factor for the prognosis of patients with SOC (HR=3.986; 95% CI: 2.436–6.522; P<0.001). Next, we constructed four MIL strategies (Mean probability, Top-10 Mean, Top-100 Mean, and Maximum probability) to identify histopathological images that could predict M2 macrophage infiltration. The Mean Probability Method was the most suitable and was used to generate a HIF model with an AUC, recall rate, precision and F1 score of 0.7500, 0.6932, 0.600, 0.600, and 0.600, respectively.

Collectively, our findings indicated that M2 macrophage infiltration may increase prognostic prediction for SOC patients. Machine deep learning of pathological immunohistochemical images exhibited good potential for the direct prediction of M2 macrophage infiltration.