Fast cancer imaging in pancreatic biopsies using infrared imaging.

Pancreatic cancer, particularly Pancreatic ductal adenocarcinoma, remains a highly lethal form of cancer with limited early diagnosis and treatment options. Infrared (IR) spectroscopy, combined with machine learning, has demonstrated great potential in detecting various cancers. This study explores the translation of a diagnostic model from Fourier Transform Infrared to Quantum Cascade Laser (QCL) microscopy for pancreatic cancer classification. Furthermore, QCL microscopy offers faster measurements with selected frequencies, improving clinical feasibility. Thus, the goals of the study include establishing a QCL-based model for pancreatic cancer classification and creating a fast surgical margin detection model using reduced spectral information. The research involves preprocessing QCL data, training Random Forest (RF) classifiers, and optimizing the selection of spectral features for the models. Results demonstrate successful translation of the diagnostic model to QCL microscopy, achieving high predictive power (AUC = 98%) in detecting cancerous tissues. Moreover, a model for rapid surgical margin recognition, based on only a few spectral frequencies, is developed with promising differentiation between benign and cancerous regions. The findings highlight the potential of QCL microscopy for efficient pancreatic cancer diagnosis and surgical margin detection within clinical timeframes of minutes per surgical resection tissue.

Pancreatic intraepithelial neoplasia detection and duct pathology grading using FT-IR imaging and machine learning.

Pancreatic intraepithelial neoplasia (PanIN) is manifested by noninvasive lesions in the epithelium of smaller pancreatic ducts. Generally, cancer development risk from low-grade PanIN is minor, whereas, invasive pancreatic ductal adenocarcinoma (PDAC) development is highly related to high-grade PanINs. Therefore, in the case of high-grade PanIN detection, additional surgical resection may be recommended. However, even the low-grade PanINs can indicate possible progression to PDAC. The definition of PanIN is constantly changing and there is a need for new tools to better characterize and understand its behavior. We have recently developed a comprehensive pancreatic cancer classification model with biopsies collected from over 600 biopsies from 250 patients. Here, we take the next step and employ Infrared (IR) spectroscopy to build the first classification model for PanINs detection. Furthermore, we created a Partial Least Squares Regression (PLSR) model to characterize ducts from benign to cancerous. This model was then used to predict and grade PanINs accordingly to their malignancy level.