en.Wedoany.com Reported - On June 5, 2026, Classiq, a quantum software engineering developer, and Pontificia Universidad Católica de Chile (UC Chile) jointly launched a 12-month research initiative aimed at developing hybrid quantum-classical machine learning algorithms for advanced biomedical image analysis. Funded through the Avanza UC 2025 competition under the title "Enhancing Pathology through Quantum Computing," the project establishes Latin America's first computational pathology consortium.
The project integrates Classiq's automated circuit synthesis platform with NVIDIA's CUDA-Q hybrid infrastructure and leverages curated histopathology datasets from Brazilian research institutions, including Fundação Oswaldo Cruz (FIOCRUZ) and Universidade Federal da Bahia (UFBA). The co-design roadmap addresses the high dimensionality and feature complexity of whole-slide tissue images, which strain classical computer vision architectures in pixel-level segmentation tasks. Rather than relying entirely on deep classical neural networks, the research team developed a hybrid Quantum Machine Learning (QML) pipeline optimized for renal pathology, using Classiq's abstract functional modeling environment to automatically synthesize and optimize specialized quantum network topologies, bypassing the limitations of manual gate-level programming.
The joint computational pathology workflow focuses on three clinical analysis objectives. Quantum Convolutional Neural Networks (QCNNs) adjust quantum convolutional layers to compress high-resolution structural features, optimizing automated glomerular segmentation in complex tissue samples. Variational Quantum Classifiers (VQCs) apply parameterized variational quantum logic states to perform multi-class renal lesion classification models. Quantum Kernel Methods leverage high-dimensional quantum state spaces for semantic pattern searches, isolating subtle diagnostic anomalies within dense histological sections.
The compiled software stack executes through a unified runtime environment. Hybrid algorithms are compiled using the NVIDIA CUDA-Q platform, enabling low-latency coprocessor data routing. This framework allows the team to run high-fidelity algorithm simulations on classical NVIDIA AI supercomputing infrastructure, then deploy optimized, hardware-ready circuits to IonQ's trapped-ion Quantum Processing Units (QPUs) for physical benchmarking.
This partnership establishes an operational anchor for advanced computing applications in South America's medical technology sector, directly aligning with Chile's National Quantum Technology Strategy 2025-2035. The project is directed by Dr. Dardo Goyeneche of the Faculty of Physics at Pontificia Universidad Católica de Chile—who also leads the QuDIT research group and the QuAntü project for building a general-purpose quantum computer in Chile—and is supported by Dr. Daniel Uzcátegui of Universidad Católica de la Santísima Concepción (UCSC). By embedding Classiq's hardware-agnostic coding layer into regional healthcare pipelines, the initiative creates a validated framework for bringing emerging quantum advantages directly into active public health diagnostic tools.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
