Yiming Xiao’s Post

Undergraduate students have contributed greatly to our research environment. A story of our Concordia University USRA trainee Owen Hellum for his research journey on medical VR at our Health-X Lab!

Want a fun and intuitive virtual reality platform to learn about the brain? We are proud to present SONIA, a novel, user-friendly VR system with a multi-scale interaction paradigm that allows flexible customization of learning materials.  As the first immersive system that integrated customizable design and detailed narratives of the brain sub-systems for the education of neuroanatomy and brain connectivity, SONIA showcased new potential directions and provided valuable insights regarding medical learning and exploration in VR. SONIA is the work of our multi-talented undergraduate trainee Owen Hellum, who has completed 3 journal papers on medical VR at the Health-X Lab (http://www.healthx-lab.ca) in the past two years. Truly amazing achievements! Check out our publication: Hellum O, Steele C and Xiao Y (2024) SONIA: an immersive customizable virtual reality system for the education and exploration of brain networks. Front. Virtual Real. 4:1244096. doi: 10.3389/frvir.2023.1244096 https://lnkd.in/g5V856Jh Christopher Steele Gina Cody School of Engineering and Computer Science Concordia University #virtualreality #neuroscience #game #humancomputerinteraction

Day 1 of Brainhack Montreal 2023. 🧠 💻 Lots of cool projects taking place! For the event schedule: https://lnkd.in/enEwW_A4 Gina Cody School of Engineering and Computer Science Concordia University Tristan Glatard Christopher Steele Mathieu D.

While AI algorithms have shown great performance for medical image segmentation tasks for disease analysis and surgical planning, the ground truths provided by human raters can still suffer greatly from inconsistent protocols and level of training in anatomical segmentation, as well as familiarity with segmentation software. To help mitigate these, Dr. Maryse Fortin and I are happy to introduce "Project PILLAR" (https://lnkd.in/ewKdwsch), a comprehensive online resource to guide manual segmentation of paraspinal muscles for the study and AI algorithm building towards better understanding of painful spinal disorders! The project has just been published in BMC Musculoskelet Disord Anstruther, M., Rossini, B., Zhang, T. et al. PILLAR: ParaspInaL muscLe segmentAtion pRoject - a comprehensive online resource to guide manual segmentation of paraspinal muscles from magnetic resonance imaging. BMC Musculoskelet Disord 24, 909 (2023). https://lnkd.in/eceJQHh2 This is a great team effort. Meagan Anstruther and Bianca Rossini from Dr Fortin's InSpire Lab did an amazing job creating the online tutorials. I would like to congratulate our undergraduate trainees, Tongwei Zhang and Terrance Liang at the Health-X Lab (www.healthx-lab.ca) for their first research paper through the Concordia University Undergraduate Student Research Awards (CURSA) program!

We are thrilled to announce that we will host Brainhack Montreal 2023 at Concordia University on Dec 8 & 11-12! We look forward to your participation to dive into the world of neuroscience and open science! 🔬 What to expect: 🌟Educational tutorials 🌟Hands-on hacking projects 🌟Social gatherings and networking Please follow our website for more info: https://lnkd.in/enEwW_A4 To register for the event: https://lnkd.in/eYRqZkPa Tristan Glatard, Christopher Steele Gina Cody School of Engineering and Computer Science Faculty of Arts and Science, Concordia University

My great honour to be a new Concordia University Research Chair (New Scholar) in Intelligent and Intuitive Surgical Technology!

This year, our Health-X lab (healthx-lab.ca) will have a number of presentations on various perspectives of medical AI research at MICCAI 2023 and the satellite events. Our trainees and I look forward to discussing our works with you in the next one week in Vancouver! *Main conference: In Oral Session 4 (M-01-047)on October 9th, PhD trainee Soorena Salari will present: FocalErrorNet: Uncertainty-aware focal modulation network for inter-modal registration error estimation in ultrasound-guided neurosurgery https://lnkd.in/eBZ-sjiZ In Poster Session (M-01-131) on October 9th, PhD trainee Soorena Salari will present: Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning https://lnkd.in/e-TnmHX9 * MICCAI Machine Learning in Clinical Neuroimaging (MLCN) workshop: During the oral session on Oct 8, PhD trainee Mumu Aktar will present: VesselShot: Few-shot learning for cerebral blood vessel segmentation https://lnkd.in/e9NYtmTV * MICCAI Machine Learning in Medical Imaging (MLMI) workshop: During the poster session on Oct 8, MSc trainee Zirui Qiu will present: Is visual explanation with Grad-CAM more reliability for deeper neural networks? a case study with automatic pneumothorax diagnosis https://lnkd.in/exifsS9T * MICCAI UNSURE workshop: During the oral session on Oct 12, MSc trainee Parinaz Roshanzamir will present: How inter-rater variability relates to aleatoric and epistemic uncertainty: a case study with deep learning-based paraspinal muscle segmentation https://lnkd.in/eQMdZdkQ We thank all the collaborators for their contributions to these works! Hassan Rivaz Marta Kersten-Oertel Maryse Fortin Gina Cody School of Engineering and Computer Science #medicalimaging #AI #deeplearning #MICCAI #computerscience

Low back pain is the top musculoskeletal disorder in adults, but its causes are still largely unclear. With recent evidences that link the morphometry and composition changes in paraspinal muscles to painful spinal disorders, efficient automatic segmentation algorithms for these muscle groups are crucial to investigate the pathology in large cohort studies. If you need to automatically segment paraspinal muscles from T2w MRIs with predicted estimation of inter-rater variability maps, we have just released the multi-task TransUNet model from our UNSURE2022 paper by MSc trainee Parinaz Roshanzamir (co-supervised with Hassan Rivaz): Github link: https://lnkd.in/e_tgRdae Reference: Roshanzamir, P., et al. (2022). Joint Paraspinal Muscle Segmentation and Inter-rater Labeling Variability Prediction with Multi-task TransUNet. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2022. Lecture Notes in Computer Science, vol 13563. Springer, Cham. https://lnkd.in/eQWmx3Nc The work is a collaboration of Gina Cody School of Engineering and Computer Science, Dr. Maryse Fortin at Faculty of Arts and Science, Concordia University and Dr. Michele Battie at Western University's Bone and Joint Institute