# Infrared Imaging Combined with Machine Learning for Detection of the (Pre)Invasive Pancreatic Neoplasia

## TL;DR

This paper introduces an automated method using infrared imaging and machine learning to detect early signs of pancreatic cancer in tissue samples, improving early diagnosis and treatment timing.

## Contribution

The novel combination of stain-free FT-IR imaging and machine learning for automated detection of pancreatic neoplasia in a mouse model.

## Key findings

- The model accurately distinguishes normal, benign, and malignant pancreatic tissues at the cellular level.
- A streamlined version of the model rapidly identifies pathologically altered regions, including PanINs.
- The approach mirrors human PDAC progression using a reliable mouse model with mutant Kras and Trp53 genes.

## Abstract

With the challenge of limited early stage detection and
a resulting
five-year survival rate of only 13%, pancreatic ductal adenocarcinoma
(PDAC) remains one of the most lethal cancers. Replacing the high-cost
and time-consuming grading of pancreatic samples by pathologists with
automated diagnostic approaches can revolutionize PDAC detection and
thus accelerate patient admission into the clinical setting for treatment.
To address this unmet diagnostic need and facilitate the shift of
tissue screening toward automated systems, we combined stain-free
histologyspecifically, Fourier-transform infrared (FT-IR)
imagingwith machine learning. The obtained stain-free model
was trained to distinguish between normal, benign, and malignant areas
in analyzed specimens using hematoxylin and eosin stained pancreatic
tissues isolated from KC (KrasG12D/+; Pdx1-Cre) or KPC
mice (KrasG12D/+; Trp53R172H/+; Pdx1-Cre). Due
to the pancreas-specific mosaic expression of the mutant Kras and Trp53 genes, changes in pancreatic tissues
of this mouse model of PDAC closely mirror the gradual transformation
of normal pancreatic epithelia into (pre)­malignant structures. Thus,
this mouse model provides a reliable representation of human disease
progression, which we tracked in our study with a Random Forest classifier
to achieve accurate detection at the cellular level. This approach
yielded a comprehensive model that distinguishes normal pancreatic
tissues from pathological features such as pancreatic intraepithelial
neoplasia (PanIN), cancerous regions, hemorrhages, and collagen fibers,
as well as a streamlined model designed to rapidly identify normal
tissues versus pathologically altered regions, including PanINs. These
models offer highly accurate diagnostic tools for the early detection
of pancreatic malignancies, thus significantly improving the chance
for timely therapeutic intervention against PDAC.