Hassan Abbas, PhD’s Post

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.

Building the Future of Flow Cytometry: At SpikoCyte we’re rethinking what a cytometer can be. Our mission is to design a compact, intelligent system that combines cutting-edge technologies to unlock faster, more sensitive, and label-free cell analysis. Here’s what we’re integrating into our platform: - Microfluidics → to precisely handle and control cells in flow - Advanced Optics → to capture rich scattering signals - Neuromorphic Event-Based Cameras (DVS) → for real-time, high-speed vision without redundant data - Spiking Neural Networks → trained to classify cells efficiently, mimicking how the brain processes information By bringing these components together, we’re creating a new generation of cytometers that are smarter, faster, and more efficient—pushing the boundaries of biomedical research and diagnostics. #SpikoCyte #FlowCytometry #Microfluidics #Optics #Neuromorphic #EventBasedVision #SpikingNeuralNetworks #BiotechInnovation

This is a recent paper from our ongoing collaboration between the Radiology Department at UNMC and Electrical & Computer Engineering at UNL! In this project, we apply AI and deep learning tools to advance in vivo molecular imaging, aiming for greater robustness and efficiency. Our first study demonstrates that CEST MRI can be accelerated by up to 10× while maintaining high-quality data in a normal mouse model. Next, we are evaluating the robustness of the method to handle disease mouse models. This is a nice project. Grateful to be part of this team! https://lnkd.in/dmD-CQNb https://lnkd.in/d7D4qNpR

I am pleased to announce that our article, “A Benchmark Study of Deep Super-Resolution Models for Digital Holography: Quantitative Phase and Intensity Evaluation”, has been published in Optics Express. This research was carried out in collaboration with my esteemed co-authors Berkay Abdioğlu, Yağmur IŞIK, İbrahim Cem Balcı, Gökhan Bora Esmer, Huseyin Uvet and Ali Anil DEMIRCALI. I am grateful for their contributions throughout the project. The article presents a comprehensive benchmark of deep learning-based super-resolution models applied to off-axis digital holography, with a particular focus on preserving both structural detail and quantitative phase accuracy. We evaluated multiple architectures across 2×, 3×, and 4× downsampling levels, explored generalization to biological cell holograms, and proposed a unified, scale-aware model that performs effectively across varying magnifications. Key contributions include: • Quantitative evaluation of SR models (RCAN, SwinIR, diffusion-based) for both intensity and phase reconstructions • Accurate recovery of phase-derived depth maps for label-free biomedical imaging • Demonstrated generalization to unseen biological samples despite training on microbeads • A unified multi-scale SR framework capable of adapting to different magnification levels • Clear performance advantage over conventional interpolation methods The article is available open access: https://lnkd.in/d7FGv4iw #digitalholography #superresolution #deepLearning #quantitativephaseimaging #phaseimaging #biomedicalimaging #imageprocessing #computervision #RCAN #SwinIR #diffusionmodels #transformermodels #residuallearning #scaleconditioned #cellimaging

Making the beating heart of a zebrafish embryo visible in remarkable detail might sound simple but it's actually a major breakthrough. 💙 The zebrafish heart pumps the blood around the circulatory system at a speed of three beats per second. Capturing fast and dynamic processes in living organisms in 3D like this has always been one of the biggest challenges in microscopy. Now with the new ZEISS LSM Lightfield 4D from ZEISS Microscopy, researchers can image fastest movements in whole organisms with all spatial and temporal information. The innovative technology is complemented by ZEISS arivis AI-powered image analysis software. This software can process and analyze vast amounts of imaging data and identify patterns more efficiently than ever before. 🔬 #ZEISS #Microscopy #AI

Going to the International Ultrasonics Symposium (IUS) next week 🇳🇱 + 📍? Check out our recent work on diffusion model–based ultrasound despeckling, developed in collaboration with my college professor, Geoffrey Luke. Our research explores how an IR-SDE–based diffusion model can enhance ultrasound image quality by reducing speckle while preserving fine anatomical details. The lecture presentation will be led by Prof. Luke on September 18 at 2:30 pm (Netherlands time), as part of session C4L-05: MIS: Deep Learning for Image Reconstruction. The talk is titled “Generalizable Ultrasound Despeckling via Image Restoration Diffusion Method” (paper ID 3405). Looking forward to hearing your thoughts on generative modeling and deep learning for ultrasound imaging!

Researchers Unlock High-precision Position Measurements Using Two-photon Interferometry and SPAD Arrays Researchers achieve highly precise position measurements by exploiting a refined form of two-photon interference that overcomes limitations caused by differences between individual photons, opening possibilities for advanced imaging and potentially new approaches to photonic processing #quantum #quantumcomputing #technology https://lnkd.in/e2m6uEJt

I am pleased to share that our research paper "Quantum-Enhanced Dual-Backbone Architecture for Accurate Gastrointestinal Disease Detection Using Endoscopic Imaging" has been accepted and published in BioMedInformatics. This work explores the integration of quantum computing with deep learning for medical image analysis, specifically focusing on gastrointestinal disease detection from endoscopic images. I would like to thank my co-authors Khidhr Halab, Professor Othmane EL MESLOUHI, Professor Zouhair Elamrani Abou Elassad, and Professor Moulay Akhloufi for their valuable contributions to this research. The full paper is available here: https://lnkd.in/e5Tgpt7s #QuantumComputing #MedicalAI #DeepLearning #Research #MedicalImaging.

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