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
26P - Subcutaneous trastuzumab versus intravenous trastuzumab for treatment of patients with HER2-positive breast cancer: A time, motion and cost-benefit assessment in a day care oncology unit in China
Presenter: Bei Sun
Session: Poster Display
Resources:
Abstract
27P - The biological characteristics of HER2-low in TNBC using mRNA profiling and molecular subtypes
Presenter: Asako Tsuruga
Session: Poster Display
Resources:
Abstract
28P - One-week ultra-hypofractionated partial breast RT in early breast cancer: 3DCRT vs IMRT
Presenter: Nurilla Zaynutdinov
Session: Poster Display
Resources:
Abstract
30P - Stereotactic body radiotherapy using cyberknife versus interstitial brachytherapy in accelerated partial breast irradiation on left-sided breast: A comparison of preliminary clinical result and dosimetric characteristics
Presenter: Ting-Na Wei
Session: Poster Display
Resources:
Abstract
31P - Prognostic implication of breast edema on preoperative breast MRI in breast cancer
Presenter: Ki-tae Hwang
Session: Poster Display
Resources:
Abstract
32P - Efficacy of olanzapine in the prophylaxis of delayed chemotherapy-induced nausea and vomiting in breast cancer patients receiving dose-dense AC with a steroid-sparing regimen: A single-center pilot study
Presenter: Manami Tada
Session: Poster Display
Resources:
Abstract
34P - Social support as the mediator of the association between unmet needs and happiness among women with early breast cancer
Presenter: Nithiya Sinarajoo
Session: Poster Display
Resources:
Abstract
35P - Prospective study assessing the efficacy and safety of a scalp cooling device for the prevention of alopecia in breast cancer patients undergoing (neo)adjuvant chemotherapy
Presenter: Winnie Yeo
Session: Poster Display
Resources:
Abstract
37P - To excise or not to excise: Preventive management of early breast cancer in atypical ductal hyperplasia patients
Presenter: Clarisse Hing
Session: Poster Display
Resources:
Abstract
38P - Exploring prognostic factors in patients achieving PCR after neoadjuvant therapy for triple-negative breast cancer: A retrospective study based on SEER data
Presenter: Lv Wenjie
Session: Poster Display
Resources:
Abstract