Abstract 1220P
Background
Determination of programmed death-ligand (PD-L1) status in triple-negative breast cancer (BC) by immunohistochemical (IHC) assay represents has prognostic significance in association with immune checkpoint inhibitor (ICI) therapies. However, the evaluation of PD-L1 SP142 remains challenging for pathologists since the associated tumor microenvironment complicates the immune cell (IC) scoring. Moreover, PD-L1 distribution in tumor could also lead to a risk of inaccurate patient allocation for ICI. To accurately diagnose PD-L1 status as IC score, a computer-aided artificial intelligence (AI) system is required to precisely quantify PD-L1 expression in two-dimensional and three-dimensional (3D) pathological images.
Methods
In this study, we proposed a computer-aided AI system for digital images of IHC and 3D immunofluorescence (IF) assays. This system consisted of machine learning algorithms for tumor/IC recognition, infiltration identification, and PD-L1 expression detection. Tissue clearing technology with IF and confocal microscopy were utilized to detect the spatial distribution of PD-L1 in BC specimens.
Results
The designed computer-aided AI system was based on a tumor segmentation model with a >80% accuracy and an IC recognition model with a 90% accuracy. For the IHC digital pathology, the computer-aided AI system achieved a concordance rate of 83% in comparison with PD-L1 IC interpretation by experienced pathologists. For 3D digital images, the system achieved a concordance rate of 90% with traditional pathological diagnosis. This system could serve as an integrated plugin onto existing open-source platforms. Appling the system for 3D analysis, the spatial distribution of PD-L1 showed heterogeneity across different layers. Notably, 30% cases crossed the 1% cutoff along the 3D layers, which is related to admission of immunotherapy.
Conclusions
The computer-aided AI system could improve the PD-L1 diagnosis from IHC to 3D digital images, which provides accurate prognostic significance for precision medicine.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
1785P - Changes in bone mineral density, trabecular bone score and body composition in metastatic hormone-sensitive prostate cancer (mHSPC) patients randomized to receive androgen deprivation + enzalutamide plus/minus zoledronic acid: The BonEnza study
Presenter: Alberto Dalla Volta
Session: Poster session 14
1787P - Prostate specific membrane antigen positron emission tomography (PSMA PET)-directed clinical outcomes in metastatic hormone-sensitive prostate cancer (mHSPC): Implications for the STAMPEDE2 trial design
Presenter: Hoda Abdel-Aty
Session: Poster session 14
1789P - Low- and high-volume disease in mHSPC: From CHAARTED to PSMA PET
Presenter: Lena Unterrainer
Session: Poster session 14
1790P - Utilisation rates of treatment intensification for metastatic hormone sensitive prostate cancer (mHSPC) in England, UK
Presenter: Joanna Dodkins
Session: Poster session 14
1791P - Molecular profiling and prognostic relevance of low PTEN expression in metastatic hormone-sensitive prostate cancer patients
Presenter: Marta Garcia De Herreros
Session: Poster session 14
1792P - Effects of enzalutamide on overall survival +/- early docetaxel in participants aged less than 70 yrs versus greater than or equal to 70 yrs in ENZAMET (ANZUP 1304)
Presenter: Lisa Horvath
Session: Poster session 14
1793P - PPROSTRATEGY: A SOGUG randomized trial of androgen deprivation therapy (ADT) plus docetaxel (dct) +/- nivolumab (nivo) or ipilimumab-nivolumab (ipi-nivo) in high-volume metastatic hormone-sensitive prostate cancer (hvHSPCa) - Safety and toxicity profiles from the pilot phase
Presenter: Jose Arranz Arija
Session: Poster session 14