Serac Healthcare’s Post

Further research from our ongoing collaboration with the School of Biomedical Engineering & Imaging Sciences, King’s College London - which is investigating potential AI tools to help clinicians read and interpret scans using ⁹⁹ᵐTc-maraciclatide - will be presented at the annual conference of the Medical Image Computing and Computer Assisted Intervention Society (MICCAI Society) taking place next week from 6-10 October in Marrakesh, Morocco.   A poster authored by Robert Cobb, Professor Gary Cook and Professor Andrew Reader will be available throughout the conference onsite and on the virtual platform together with the accepted paper, and will be presented by Robert: On Wednesday, October 9, 2024, 10:30 to 11:30 At Poster Session 5: Image Registration, Computer Aided Diagnosis 2, and Transparency, Fairness and Uncertainty 2 Titled: W-AM-133: Improved Classification Learning from Highly Imbalanced Multi-Label Datasets of Inflamed Joints in [⁹⁹ᵐTc]Maraciclatide Imaging of Arthritic Patients by Natural Image and Diffusion Model Augmentation   Maraciclatide is in development to diagnose and detect inflammation in patients with inflammatory arthritis and endometriosis. The development of AI tools could enhance the potential of maraciclatide as a new imaging marker. Maraciclatide is for investigational use only and is not approved by the FDA or UK and European regulatory authorities. #molecularimaging #medicalimaging #AI #machinelearning #rheumatoidarthritis #endometriosis #nuclearmedicine #precisionmedicine #MICCAI2024 #inflammatoryarthritis   

Carnival is over (at least in Germany), spring is around the corner - and so is the BVM, the national conference for Medical Image Computing. Among many other scientists, our PhD student Jonas Bohn is participating. He presents his #MICCAI 2023 paper via poster: „RPTK: The Role of Feature Computation on Prediction Performance.“ The abstract highlights the growing importance of #radiomics in #medical #imaging for disease analysis and treatment prediction. It acknowledges challenges in standardization and manual pipeline construction. To address these issues, the Radiomics Processing Toolkit (RPTK) is proposed, integrating advanced feature extraction and selection components. Comparative analysis with existing frameworks demonstrates significantly improved performance, offering valuable insights for optimized radiomics analyses in clinical settings. The paper is available here: https://lnkd.in/eS4xCUjN.

I am excited to share that our recent work on using #AI to design #MRI radiofrequency (RF) pulses has been published online at Magnetic Resonance in Medicine. While AI has been widely used for image reconstruction, analysis, and processing, it has been less explored for image acquisition. Our work explores how AI can facilitate image acquisition and introduces a self-supervised #deeplearning framework for flexible RF pulse design and optimization. We have embedded a general physical module implementing #MR physics into this framework, allowing for the design of 1-D, 2-D (spatial and spectral), multi-dimensional RF pulses, and more general pulses. This new physics-guided self-supervised deep learning approach for generalized RF design (GPS-RF) has several unique features and advantages, including: - Target-specific optimization without the need for large training data - Generalizability to design RF pulses with flexible requirements - Robustness against MRI system imperfections through a rapid online adaption strategy - Practicality demonstrated through simulation, phantom study, and in-vivo human studies - Efficient and effective RF learning and optimization, with learning times as short as seconds 👉 The paper is now available at https://lnkd.in/eGNjdtA3 👉 The accompanying code can be found at https://lnkd.in/ei_5Tdpm You can try our methods and let us know what you think. We are seeking highly motivated individuals to join our project. If you are interested, please contact me. Please pass on this message if you know someone interested in this opportunity. #Research is conducted at The MGH/HST Martinos Center for Biomedical Imaging, Harvard Medical School, Massachusetts General Hospital and thanks to our funding support by National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) (R01AR081344; R01AR079442; R56AR081017) and National Institute of Biomedical Imaging and Bioengineering (NIBIB) (R21EB031185) #ismrm #machinelearning #imaging #biomedicalengineering #biomedicalimaging #GPS #artificalintelligence

ISBI 2024 coming up soon (International Symposium on Biomedical Imaging 2024). #medicalimaging #imageprocessing #imageanalysis #machinelearning

My team and I are excited to be apart of the #SPIE Medical Imaging conference this year. Representing #UF #CMIL is Sayat Mimar presenting #ComPRePS our #AI tool for #DigitalPathology, Nicholas Lucarelli presenting on behalf of Julio Maragall and his #CODEX research, Ahmed Naglah, PhD presenting a poster on the correlation of glomerular histomorphometry changes with spatially resolved transcriptomic profiles in diabetic nephropathy, and Nicholas Lucarelli presenting a poster on the computational integration of #CODEX and #BrightfieldHistology for cell annotation using #deeplearning.

I'm thrilled to share that our latest research paper, "Harnessing ResUHybridNet with Federated Learning: A New Paradigm in Brain Tumour Segmentation," has been published in IIETA, under the Creative Commons BY 4.0 license. This study introduces the Federated ResUHybridNet, a novel approach that combines the strengths of ResNet and U-Net within a federated learning framework, prioritizing data privacy while enhancing the precision of brain tumor segmentation from MRI scans. Key Highlights: 🧠 Advanced brain tumor segmentation using 3D MRI scans. 🔄 Federated learning framework to maintain high standards of data privacy. 🤝 Collaboration across multiple hospital nodes for model training. This research could significantly improve diagnostic and treatment strategies for brain tumor patients. I invite all professionals, especially those in medical imaging and AI, to view our findings. 📄 Read the full article here: DOI: 10.18280/ria.380303 Let's connect and discuss how this innovative approach can be further developed and applied in the healthcare industry. Your insights and feedback are invaluable! #BrainTumorSegmentation #FederatedLearning #MedicalAI #DeepLearning #ResUHybridNet #HealthcareInnovation

The release of Ca2+ ions from intracellular stores plays a crucial role in many cellular processes, acting as a secondary messenger in various cell types, including cardiomyocytes, smooth muscle cells, hepatocytes, and many others. Detecting and classifying associated local Ca2+ release events is particularly important, as these events provide insight into the mechanisms, interplay, and interdependencies of local Ca2+ release events underlying global intracellular Ca2+ signaling. However, time-consuming and labor-intensive procedures often complicate analysis, especially with low signal-to-noise ratio imaging data. Prisca Dotti's PhD thesis, which she successfully defended at the ARTORG Center for Biomedical Engineering Research on 18 July, addresses these challenges by introducing an innovative deep learning-based method for the automatic detection and classification of local Ca2+ release events. The model successfully detects over 75% of events, with performance comparable to expert human annotations. This approach offers a significant, time-saving alternative to traditional labour-intensive analysis methods. 👩🏻🔬🔬 #congrats🎉 #PhDdefense #DeepLearning #CalciumSignaling #CellBiology #ArtificialIntelligence #AI #KI #ConfocalImaging #ResearchInnovation #MedicalResearch #Cardiomyocytes #SignalProcessing #BiomedicalEngineering #ARTORGCenter #PhD #Research #Innovation💡 #MedResearch #Bern #translationalresearch #InselGruppe 🏥#UniversityofBern https://lnkd.in/gWY2ry2w

VASCage imparts STEM knowledge in schools together with klasse!forschung. Here Nadja Gruber presents to students of Reithmann Gymnasium in Innsbruck how artificial intelligence helps radiologists to better detect very small structures on medical images and diagnose diseases such as #stroke. AI for automated segmentation of 3D tissue images is an important focus of VASCage research. #mintbildung #imageanalysis #imageprocessing #imagesegmentation

Last month, I had the opportunity to speak with Dr. Satish E. Viswanath, an Associate Professor of Biomedical Engineering, at Case Western Reserve University. His research is focused on the application of artificial intelligence, radiomics, and machine learning for disease characterization as well as predicting and evaluating disease response via different imaging modalities. Our discussion touched on: 🖥️ His Research @ INVent Lab 🏥 Innovation in imaging modalities 🗃️ Data Shortages 👤 AI’s role in the personalized healthcare revolution 💡 Developing a research project and much more! I’m beyond grateful to Dr. Satish E. Viswanath for having this conversation with me. This was such a diverse, yet complete discussion that focused around so many aspects of AI. It serves testament to the myriad of applications that AI will have in the short and long term. Dr. Viswanath is extremely accomplished in machine learning, and I look forward to seeing his future research! Make sure to watch and comment on anything you find interesting below! Additionally, if anyone has questions they would like me to ask future speakers please comment here or on the YouTube interview. Link to the interview: https://lnkd.in/gqN6rf9A To stay up-to-date with future discussions, subscribe, turn on notifications, like, and share with friends & family! 🔔 Follow me on LinkedIn and subscribe to my channel ( linked below) to support the efforts of All Things AI! 🌎 Follow the channel: https://lnkd.in/eT7sdNUA

Exploring Counterfactual Image Generation in Biomedical Research Continuing our series on innovative research, we turn to a new benchmarking framework for counterfactual image generation, aiming to push the boundaries in medical imaging. This approach involves evaluating how well different models can generate realistic and causally consistent images, enabling new possibilities in understanding medical scenarios. Key Takeaways: • Hierarchical VAEs Shine: HVAE models demonstrate superior performance across datasets, including natural and medical images. • SCM-Based Evaluation: Utilizes Structural Causal Models (SCM) for realistic edits, maintaining the integrity of original data. • Comprehensive Metrics: The study compares image quality and causal consistency, offering a new standard for the field. https://lnkd.in/etfdpu2h Thomas Melistas Nefeli Gkouti Pedro P. Sanchez Dr Athanasios Vlontzos Yannis Panagakis Giorgos Papanastasiou, PhD Sotirios (Sotos) Tsaftaris #GenerativeAI #BiomedicalResearch #AIinHealthcare #InnovationInMedicine