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
49P - Survival outcomes of HER2-positive breast cancer patients treated with neoadjuvant therapy at a single cancer centre in India
Presenter: Minit Shah
Session: Poster Display
Resources:
Abstract
50P - A nationwide retrospective cohort study of the response to neoadjuvant chemotherapy between HER-2 low and HER-2 negative non-metastatic breast cancer in Qatar: A real-world analysis
Presenter: Ahmed Kardousha
Session: Poster Display
Resources:
Abstract
51P - Four-year outcomes of hypofractionated postmastectomy radiation therapy of 39 Gy in 13 fractionations
Presenter: Sevinj Gahramanova
Session: Poster Display
Resources:
Abstract
52P - A comparative study to assess volumetric and dosimetric profile of heart and lung in patients undergoing left sided post mastectomy radiotherapy: Continuous positive airway pressure (CPAP) versus free breathing (FB) techniques
Presenter: Pritanjali Singh
Session: Poster Display
Resources:
Abstract
29P - HUWE1 inhibition has tumor suppressive effect in triple-negative breast cancer cell lines by modulating glycolytic and immune modulatory markers
Presenter: Shruti Kahol
Session: Poster Display
Resources:
Abstract
53P - Radiotherapy utilization rate for breast cancer in Indonesia: A call for empowering cancer care
Presenter: Donald Manuain
Session: Poster Display
Resources:
Abstract
58P - Safety and pharmacokinetics (PK) of vepdegestrant in Japanese patients with estrogen receptor (ER)+/human epidermal growth factor receptor 2 (HER2)- advanced breast cancer: Results from a Japanese phase I study
Presenter: Hiroji Iwata
Session: Poster Display
Resources:
Abstract
59P - Comprehensive genomic profiling (CGP) unravels druggable targets in breast carcinoma (BC): A single institutional experience
Presenter: Gautam Balaram
Session: Poster Display
Resources:
Abstract
60P - A study of gene alterations in Asian patients with late stage and recurrent breast cancer
Presenter: Po-Sheng Yang
Session: Poster Display
Resources:
Abstract
61P - Tumor cell-released autophagosomes (TRAPs) remodel the breast tumor microenvironment by inducing the formation of inflammatory cancer-associated fibroblasts (CAFs)
Presenter: Chengdong Wu
Session: Poster Display
Resources:
Abstract