# Integrating computed tomography and biopsy images to predict chemotherapy response in gastric cancer

## TL;DR

This study combines CT scans and biopsy images to better predict how gastric cancer patients will respond to chemotherapy.

## Contribution

The novel approach integrates radiomic and pathomic features to improve chemotherapy response prediction in gastric cancer.

## Key findings

- The multimodal model achieved an AUC of 0.814, outperforming unimodal radiomic and pathomic models.
- Combining CT and biopsy features provides better predictive accuracy than using either modality alone.

## Abstract

To predict pathological complete response to neoadjuvant chemotherapy in advanced gastric cancer by integrating multimodal radiomic and pathomic data.

Eligible patients with advanced gastric cancer underwent neoadjuvant chemotherapy followed by radical gastrectomy. We collected pre-treatment venous-phase computed tomography (CT) scans and whole-slide H&E-stained gastroscopic biopsy sections for feature extraction. Three models were constructed: a unimodal radiomic model, a unimodal pathomic model, and a multimodal model combining both feature types. Model performance was evaluated using the area under the curve (AUC).

Our study included 295 AGC patients who received NAC and radical surgery between February 2013 and September 2022 (236 in the training cohort, 59 in the validation cohort). A total of 42 patients (14.2%) achieved pCR. We extracted 615 radiomic and 548 pathomic features. The unimodal radiomic model (10 selected features) achieved an AUC of 0.672, while the pathomic model (13 selected features) achieved an AUC of 0.806. The multimodal model, constructed with 22 features (12 radiomic, 10 pathomic), achieved the highest AUC of 0.814. Decision curve analysis confirmed the multimodal model’s superior predictive efficacy compared to the unimodal models, highlighting the synergistic potential of combining radiomic and pathomic features.

By integrating pathological images and CT features, we can maximize the utilization of pre-treatment information and enhance the accuracy of NAC prediction in AGC.