Abstract 159P
Background
The stromal component constitutes as much as 90% of pancreatic cancer specimens, dynamically interacting with the tumor and adapting into a pro-survival environment. This poses a clinical challenge, as biopsies often miss cancer by only sampling stroma. By leveraging AI and image analysis, we aim to extract informative cues from stromal interactions for novel cancer biomarker identification. This approach offers the potential for enhanced diagnostic precision and a deeper understanding of pancreatic cancer biology.
Methods
Anonymized digital scans of pancreatic cancer and chronic pancreatitis were sourced from the Centre Hospitalier de l’Université de Montréal. QuPath 0.4.3 aided slide annotation, with subsequent TIF annotation export. Staining normalization was performed via the Mitkovetta technique in Python. Our process involved deep-learning stromal segmentation, prioritizing >95% stromal tiles using Ilastik. Feature extraction was executed utilizing computer vision techniques (Haralick features), alongside the pre-trained and class-trained ImageNet deep-neural network, VGG16.
Results
Our annotated, normalized, automated, and 95% stroma-probability method generated for the training cohort 9829 cancer and 1638 mass-forming pancreatitis tiles, and 10776 cancer and 1211 pancreatitis tiles for the testing set. The table highlights the performance of the classical computer vision approach (Haralicks features extraction in RGB). Furthermore, transferring the ImageNet VGG-16 pre-trained model to our dataset managed to predict the presence of adjacent cancer at 86.6% accuracy. Table: 159P
Training | Validation | |||
Haralicks features | Cancer (N=9829) vs None (N=1638) | P | Cancer (N=10776) vs None (N=1211) | P |
RGB-F2 | +66% | 7.52 X 10-308 | +8.2% | 1.37 X 10-9 |
RGB-F15 | +54% | 3.28 X 10-272 | +8.5% | 8.57 X 10-11 |
RGB F37 | +9.6% | 2.35 X 10-294 | +2.7% | 5.02 X 10-36 |
Conclusions
We demonstrate that normalized stromal tiles could predict the presence of cancer accurately just by their morphological features at HE staining. This highlights the importance of stroma for diagnostic purposes and can serve as the basis for future studies through multiplex imaging and spatial transcriptomics.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Vincent Quoc-Huy Trinh.
Funding
Fonds de Recherche Québec Santé.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
153P - IMbrave150: Exploratory analyses for investigating associations between overall survival (OS) and depth of response (DpR) or duration of response (DoR) in patients (pts) with unresectable hepatocellular carcinoma (HCC)
Presenter: Masatoshi Kudo
Session: Poster Display
Resources:
Abstract
154P - Adverse events (AEs) as potential predictive factors of activity in patients with advanced hepatocellular carcinoma (HCC) treated with atezolizumab plus bevacizumab (AB)
Presenter: Mara Persano
Session: Poster Display
Resources:
Abstract
155P - Penpulimab combined with anlotinib and nab-paclitaxel plus gemcitabine (PAAG) as first-line treatment for advanced metastatic pancreatic cancer: A prospective, multicenter, single-arm, phase II study
Presenter: Juan Du
Session: Poster Display
Resources:
Abstract
156P - Phase II trial of second-line regorafenib in patients with unresectable hepatocellular carcinoma after progression on first-line atezolizumab plus bevacizumab: REGONEXT trial
Presenter: Jaekyung Cheon
Session: Poster Display
Resources:
Abstract
157P - T/N ratio and radiation dose delivered do not correlate with the development of Radioembolization-Induced Liver Disease (REILD) in Hepatocellular Carcinoma (HCC) following Y90 selective internal radiation therapy (Y90-SIRT): A retrospective, single tertiary centre cohort study
Presenter: Daniel Yang Yao Peh
Session: Poster Display
Resources:
Abstract
158P - Single-cell RNA sequencing via Endoscopic Ultrasoundguided Fine-Needle Biopsy (EUS-FNB) Pancreatic Biopsies uncovered an aggressive subclone with a poor prognosis
Presenter: Yung-yeh Su
Session: Poster Display
Resources:
Abstract
160P - Interim analysis of the NAPOLEON-2 study: Safety evaluation of nano-liposomal irinotecan with fluorouracil and folinic acid for advanced pancreatic cancer
Presenter: Wataru Kusano
Session: Poster Display
Resources:
Abstract
161P - Screening and COnsensus based on Practices and Evidence (SCOPE): Real-world survey on Japanese and rest-of-world practice patterns in resectable pancreatic cancer
Presenter: Elizabeth Smyth
Session: Poster Display
Resources:
Abstract
162P - Recurrence pattern of hepatocellular carcinoma patients receiving curative surgery of RFA: An update
Presenter: Long Chan
Session: Poster Display
Resources:
Abstract
163P - Chemotherapy versus palliative radiotherapy in advanced inoperable gall bladder cancer
Presenter: Vimal Sekar
Session: Poster Display
Resources:
Abstract