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
62P - Combination of chemotherapy with endocrinal therapy as upfront treatment of metastatic breast cancer in hormone receptor- positive, HER2 -negative disease: A phase II randomised clinical trial
Presenter: Mariam Saleh
Session: Poster Display
Resources:
Abstract
63P - Efficacy and safety of eribulin plus carboplatin combination for HER2-negative metastatic breast cancer
Presenter: Mengqian Ni
Session: Poster Display
Resources:
Abstract
64P - Unmet needs following metastatic breast cancer in a middle-income Asian country
Presenter: Nirmala Bhoo-Pathy
Session: Poster Display
Resources:
Abstract
66P - Utidelone-based therapy in metastatic solid tumors after failure of standard therapies: A prospective, multicenter, single-arm trial
Presenter: Jianjun Zhang
Session: Poster Display
Resources:
Abstract
67P - Efficacy and safety of trastuzumab biosimilar in HER2+ve metastatic breast cancer: A multicenter phase III study
Presenter: krishna Mohan
Session: Poster Display
Resources:
Abstract
68P - Neratinib in combination with fulvestrant and or palbociclib can overcome endocrine resistance in HER2-low/ ER+ breast cancer
Presenter: Maryam Arshad
Session: Poster Display
Resources:
Abstract
69P - A multicenter, retrospective, real-world study of inetetamab combined with pyrotinib and vinorelbine as treatment for HER2-positive metastatic breast cancer
Presenter: Nan Jin
Session: Poster Display
Resources:
Abstract
70P - Overall survival of eribulin, trastuzumab, and pertuzumab as first-line therapy for patients with HER2-positive metastatic breast cancer: A phase II, single-arm clinical trial
Presenter: Kenichi Inoue
Session: Poster Display
Resources:
Abstract
71P - Efficacy and safety of disitamab vedotin after trastuzumab for HER2 -positive breast cancer: A real-world data of retrospective study
Presenter: Chao Li
Session: Poster Display
Resources:
Abstract
72P - Real-world data on the efficacy of T-DM1 biosimilar for the treatment of HER2-positive metastatic breast cancer patients: Outcomes from a single center retrospective study in India
Presenter: Kaushal Patel
Session: Poster Display
Resources:
Abstract