Quibim Unveils Four Oncology Imaging Publications at ASCO 2025
May 23, 2025, Valencia, Spain/ New York, US/ Cambridge, UK – Quibim, a global leader in quantitative medical imaging solutions, today announced the publication of four scientific contributions at the 2025 American Society of Clinical Oncology (ASCO) Annual Meeting. These publications showcase Quibim’s latest advances in imaging biomarkers, artificial intelligence (AI), and non-invasive companion diagnostics to drive personalized oncology care.
Key Publications at ASCO 2025
- Predicting Immunotherapy Response in Advanced Solid Tumours Using Quantitative Imaging Features from CD8 PET/CT
- An Automatic AI Model for Tumoral Burden Detection and Segmentation on Whole-Body MRI: The DIPCAN Study
- Non-Invasive PD-L1 Prediction in NSCLC Patients Using 3D Self-Supervised Deep Learning and Radiomics
- DIPCAN, a multidimensional approach to precision oncology: Harnessing genomic, clinical, pathological and radiographic data to advance personalized cancer treatment.
At this year’s meeting, Quibim will present data demonstrating how imaging analytics and AI can refine patient stratification, streamline diagnostic workflows, and non-invasively infer critical molecular markers.
Predicting Immunotherapy Response in Advanced Solid Tumours Using Quantitative Imaging Features from CD8 PET/CT
In collaboration with ImaginAb, Quibim researchers extracted radiomic features from CD8-targeted PET/CT scans to identify biomarkers predictive of immunotherapy response in patients with advanced solid tumours. Analysis focused on the peritumoral ring, where specific texture and intensity signatures correlated strongly with treatment outcomes. The findings emphasize the potential for CD8 PET/CT radiomics to guide personalized monitoring and early adaptation of immunotherapy regimens.
An Automatic AI Model for Tumoral Burden Detection and Segmentation on Whole-Body MRI: The DIPCAN Study
Led by Carmen Prieto-de-la-Lastra et al., the DIPCAN study introduces an AI-driven model trained using diffusion-weighted MRI sequences to automatically detect and segment both primary and metastatic lesions across whole-body scans. The model achieved superior accuracy and consistency compared to current semi-automated methods, promising to reduce radiologist workload, minimize inter-reader variability, and unlock quantitative lesion metrics at scale.
Non-Invasive PD-L1 Prediction in NSCLC Patients Using 3D Self-Supervised Deep Learning and Radiomics
Xavier Rafael-Palou et al. present a novel, non-invasive approach to predict PD-L1 expression in non-small cell lung cancer (NSCLC) patients using routine CT exams. By integrating handcrafted radiomic features with a 3D self-supervised deep-learning framework, the method achieved high predictive performance across a heterogeneous, real-world NSCLC cohort—offering a biopsy-free tool for treatment decision support and patient stratification.
DIPCAN, a multidimensional approach to precision oncology: Harnessing genomic, clinical, pathological and radiographic data to advance personalized cancer treatment.
DIPCAN is a national project in Spain focused on the digitalization and comprehensive management of personalized medicine in cancer. The main objective of DIPCAN is to categorize the metastatic cancer patient through the development of an artificial intelligence algorithm that helps evolve the understanding, diagnosis and treatment choice of cancer patients. Therefore, this study aims to simplify the decision making during the disease management of each patient, and offers a guide in healthcare policies for good practices.
“These four ASCO contributions highlight Quibim’s commitment to advancing precision oncology,” said Dr. Ángel Alberich-Bayarri, Founder and CEO of Quibim. “Our partnerships with innovators like ImaginAb, combined with our in-house AI expertise, are opening new pathways to non-invasive biomarkers and automated image analysis that will ultimately improve outcomes for cancer patients worldwide.”