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
426P - Characterization of a novel comprehensive genomic profiling test with better detection of heterozygous deletions and gene fusions
Presenter: ryouta kakuta
Session: Poster Display
Resources:
Abstract
427P - Real-world performance of a comprehensive next-generation sequencing (NGS) panel for patients (pts) with solid tumors from Asia and the Middle East (AME)
Presenter: Nitesh Rohatgi
Session: Poster Display
Resources:
Abstract
428P - What do women want to see in a personalized breast cancer risk report? A qualitative study of Asian women of two countries
Presenter: Faustina Audrey Agatha
Session: Poster Display
Resources:
Abstract
429P - Clinical utility and outcomes of liquid biopsy-based next generation sequencing in identification of actionable genomic mutations in solid malignancy: A single center retrospective study in the Philippines
Presenter: Omar Maaño
Session: Poster Display
Resources:
Abstract
436P - Chemotherapy-induced hand-foot syndrome, comparative efficacy and safety of pharmacological prophylaxis: Systematic review and network meta-analysis
Presenter: Anand Srinivasan
Session: Poster Display
Resources:
Abstract
437P - A randomized single blinded phase II trial comparing efficacy and quality of life of topical aloe vera gel plus urea cream versus urea cream alone for prevention of hand-foot syndrome in cancer patients receiving capecitabine
Presenter: Lucksika Wanichtanom
Session: Poster Display
Resources:
Abstract
438P - A novel treatment for immune checkpoint inhibitor-related myocarditis
Presenter: Takahiro Niimura
Session: Poster Display
Resources:
Abstract
439P - Randomized controlled trial evaluating efficacy of topical urea-based cream for capecitabine-associated hand-foot syndrome prevention
Presenter: Concord Wongkraisri
Session: Poster Display
Resources:
Abstract
440P - Real-world adverse events of targeted therapy reported by pharmacist in oncology clinic
Presenter: TIKUMPORN PORNWISETSIRIKUL
Session: Poster Display
Resources:
Abstract
441P - The prophylactic efficacy of telpegfilgrastim, a Y-shape branched pegylated G-CSF in patient with chemotherapy-induced neutropenia: A multicenter, randomized phase III study
Presenter: Xinshuai Wang
Session: Poster Display
Resources:
Abstract