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
561P - Mechanisms of osimertinib resistance using circulating tumor DNA analyses for EGFR-mutated non-small cell lung cancer, results from ELUCIDATOR: A prospective observational multicenter study
Presenter: Daijiro Harada
Session: Poster Display
Resources:
Abstract
562P - First-line (1L) osimertinib (osi) ± platinum-pemetrexed in patients (pts) with EGFRm advanced NSCLC: FLAURA2 China cohort
Presenter: Yan Yu
Session: Poster Display
Resources:
Abstract
563P - Real-world effectiveness and safety of first-line osimertinib for EGFR-mutated advanced NSCLC in China (FLOURISH study)
Presenter: Jianya Zhou
Session: Poster Display
Resources:
Abstract
564P - Co-occurring EGFR p.E709X mutation affects the treatment response to the third-generation EGFR-TKIs in EGFR p.G719X-mutant patients with advanced NSCLC
Presenter: Wen Feng Fang
Session: Poster Display
Resources:
Abstract
565P - Genome-guided targeted therapy combination improves survival in patients with advanced EGFR mutation positive NSCLC failing osimertinib
Presenter: Molly Li
Session: Poster Display
Resources:
Abstract
566P - Safety of tepotinib + osimertinib in EGFR-mutant NSCLC with MET amplification after first-line osimertinib
Presenter: Chong Kin Liam
Session: Poster Display
Resources:
Abstract
567P - Furmonertinib in combination with bevacizumab and intrathecal chemotherapy as later-line re-challenge treatment in EGFR –mutated NSCLC patients with leptomeningeal metastasis after third-generation EGFR-TKIs treatment failure
Presenter: Fang Cun
Session: Poster Display
Resources:
Abstract
568P - First-line (1L) osimertinib + platinum-pemetrexed in EGFR-mutated (EGFRm) advanced NSCLC: Updated FLAURA2 safety run-in (SRI) results
Presenter: David Planchard
Session: Poster Display
Resources:
Abstract
569P - Whole-transcriptome sequencing of transformed small-cell lung cancer from EGFR-mutated lung adenocarcinoma reveals LUAD–like and SCLC–like subsets
Presenter: Chan-Yuan Zhang
Session: Poster Display
Resources:
Abstract
570P - First-line osimertinib for patients with advanced NSCLC harboring EGFR mutations: A real-world study
Presenter: Wenxiang Ji
Session: Poster Display
Resources:
Abstract