"Quantum-Enhanced Medical Imaging Paper Published in BioMedInformatics"

Using the cross-homology Hodge–Laplacian on cross-simplicial complexes, to lift the construction to cell complexes and build layered higher-order representations. For hands-on introduction to simplicial complexes: https://lnkd.in/g9KFTj2g #SimplicialComplex #CellComplex #HodgeLaplacian #CrossLaplacian

“Human cell computation on silicon chips and vice versa’’ may ahead to revolutionary technology in bio-computing research. An instinct of cell anatomy integration with silicon chips may help to save millions of people, but still needs broader research in the multidisciplinary field of biology and computer science. #Biocomputing #Human brain interface #Future technology #Researching in bioscience and computer science

I’m excited to share my open dataset of 218 paired noisy/ground-truth high-resolution STEM images, covering crystalline materials and epitaxial thin films, acquired on a JEOL GrandARM with probe corrector. The dataset is designed to support researchers and engineers in developing and benchmarking deep learning denoising algorithms for electron microscopy and related imaging fields. 🔗 Dataset (Zenodo DOI): https://lnkd.in/eFk5d3qj. 💻 Example of denoising pipeline: https://lnkd.in/eScv-mKs 👉 If you work in computational imaging, ML for materials, microscopy R&D, or scientific software, I’d love to connect and hear your feedback. I also encourage the community to contribute additional images from other microscopes, building toward a rich benchmark resource for high-resolution electron microscopy. #ElectronMicroscopy #DeepLearning #STEM #OpenScience #Denoising #MaterialsScience #JEOL

The National Institutes of Health Quantum Computing Challenge moves to stage 2! Ten teams have been selected as winners of Stage 1 of the NIH quantum computing challenge, part of the QuBIT program. Their innovative proposals explore how quantum approaches could transform biomedical research, from accelerating drug discovery to advancing medical imaging. Winners are now invited to participate in stage 2, where ideas will be further developed and refined. Learn more: https://brnw.ch/21wVbsM #QuantumComputing #BiomedicalInnovation #TranslationalResearch #QuBIT #HealthTech #MedicalResearch #VisionResearch #VisionNews #ResearchNews

Excited to share that our paper “Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction” has been accepted as a 🌟Spotlight Oral (<3.5%) at IEEE ICIP 2025 in Anchorage, Alaska! 📄 https://lnkd.in/g38aWsHT Check it out to see how we introduce a sparsity-driven consistency term that enhances self-supervised physics-driven deep learning models for fast MRI reconstruction, leading to more reliable and artifact-free images at very high acceleration rates. Our approach outperforms state-of-the-art self-supervised methods on the fastMRI knee and brain datasets.

Yasar Utku Alcalar, a PhD student in my lab, is giving a Spotlight Oral (<3.5%) presentation at IEEE ICIP, on a new self-supervised learning approach for MRI reconstruction. Paper is linked in his post below.

Excited to share that our paper “Chalcogenide-Based Brain-Inspired Photo-Synapses for Neuromorphic Vision Sensor: An Experimental and Theoretical Study” has been accepted for publication in Small. In this work, we explore 2D chalcogenide memristors, focusing on SnS₂ as a multifunctional vdW material to replicate biological visual systems. Our combined experimental and simulation work reveals that SnS₂ memristors enable wavelength-sensitive pattern recognition and memory, achieving 98.51% accuracy on MNIST datasets. https://lnkd.in/g9UmwutW #NeuromorphicComputing #2DMaterials #MachineVision #ArtificialIntelligence #BrainInspired

Students’ image tool offers sharper signs, earlier detection in the lab or from space. UBC Okanagan research tech gets the most from medical and environmental imaging. https://lnkd.in/gYek2Ad6 #CdnPSE The University of British Columbia UBC Okanagan

Hard disagree. Human in the loop is poop only when either the human is poop (1st week in MRI posting) or the AI is poop (trained on US data trying to be pushed into reporting in an Indian primary healthcare centre) or both are poop (quacks using llama 3 to diagnose cause of shortness of breath in a village). And when you encounter a poop in your system, be it human or AI, it’s your responsibility to pick it up and throw it out of the loop. Unfortunately, that is not possible always. So we are forced to choose our poop and that’s often confusing to most administrators and regulators. Till we figure out a way to evaluate which is a better poop, the human is going to stay in the loop.

🏛️ Can deep learning and EEG reveal how we emotionally respond to architectural spaces—before we even realize it? In this study, our Enobio (https://lnkd.in/dFS8ugFy) was used to record a 32-channel EEG while participants viewed images of architectural environments. Forty participants were shown multiple architectural space images while a real-time EEG was recorded. Event-related potential analysis (N100, N200, P300, LPP) revealed consistent differences between preferred and non-preferred stimuli. Two CNN-LSTM models trained on EEG data showed that emotional preferences could be predicted with high recall or precision, depending on the features used. These findings support integrating EEG into early design stages to create emotionally adaptive, user-centric spaces. 👏 Congratulations to Ju Eun Cho, Se Yeon Kang, Yi Yeon Hong, and Han Jong Jun for this exciting work in architectural neuroscience!   #EEG #Neuroarchitecture #AffectiveDesign #SmartBuildings #DeepLearning