- 59
- 498 186
Kimia Lab
Canada
Registrace 10. 06. 2010
The Laboratory for Knowledge Inference in Medical Image Analysis, short KIMIA Lab, established in Fall 2013 at the University of Waterloo, envisions to conduct research at the forefront of mass image data in medical archives using machine learning schemes with ultimate goal of extracting information that cannot only support a more speedy and accurate diagnosis and treatment of many diseases but also, and more significantly, establish new quality assurance based on mining of collective knowledge and wisdom.
This channel promotes teaching and research activities at Kimia Lab, Mayo Clinic, Rochester, MN, USA.
History of this channel:
2010-2013 Segasist Technologies
2013-2023 Kimia Lab, University of Waterloo
2024-present Kimia Lab, Mayo Clinic, USA
This channel promotes teaching and research activities at Kimia Lab, Mayo Clinic, Rochester, MN, USA.
History of this channel:
2010-2013 Segasist Technologies
2013-2023 Kimia Lab, University of Waterloo
2024-present Kimia Lab, Mayo Clinic, USA
Foundation Models and Information Retrieval in Digital Pathology
Speaker: Hamid R Tizhoosh, Mayo Clinic
Date: May 21, 2024
Venue: Pathology Informatics Summit, 2024, Ypsilanti MI
Date: May 21, 2024
Venue: Pathology Informatics Summit, 2024, Ypsilanti MI
zhlédnutí: 420
Video
Image Search in Histopathology - The Past, Present, and the Path Forward
zhlédnutí 136Před 2 měsíci
Speaker: Hamid R. Tizhoosh, Mayo Clinic Date: May 20, 2024 Venue: HIMA Workshop, Pathology Summit, Ypsilanti, MI
Learning or Searching in Digital Pathology
zhlédnutí 143Před 2 měsíci
Talk at TIA Warwick @tiawarwick6042 Date: April 15, 2024 Speaker: Hamid R. Tizhoosh, Mayo Clinic Topic: Image search and retrieval and its relationship to foundation models in histopathology
Kimia Lab - A Snapshot
zhlédnutí 2,3KPřed 2 lety
The Laboratory for Knowledge Inference in Medical Image Analysis, short KIMIA Lab, founded in Fall 2013 at the University of Waterloo by Professor Hamid R Tizhoosh, envisions to conduct research at the forefront of mass image data in medical archives using machine learning schemes with ultimate goal of extracting information that support a more speedy and accurate diagnosis and treatment of man...
Matching Breast Biopsy Images to the Digital WHO Atlas
zhlédnutí 721Před 2 lety
Presented at by Professor Hamid R Tizhoosh at The Inaugural Digital Pathology and AI Virtual Summit, September 30, 2021 The classification of common and rare breast tumors by the World Health Organization provides a definitive illustrated description of each tumor type and is published in print and online. Recent advances in artificial intelligence (AI) allow comparing histopathological pattern...
Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images
zhlédnutí 803Před 2 lety
A talk at MICCAI 2021 by Shivam Kalra Whole Slide Image Representation
Digitizing Glass Slides to use AI for Computational Pathology
zhlédnutí 850Před 2 lety
Kimia Lab (University of Waterloo, ON), in collaboration with the Grand River Hospital (Kitchener, ON), has been digitizing a large number of glass slides to enable AI research in histopathology. The video shows the typical steps from finding glass slides, digitizing them, and anonymizing files to applying AI on digital images.
AI, Digital Pathology and Observer Variability: From Image Search to Building Diagnostic Consensus
zhlédnutí 1,6KPřed 3 lety
KEYNOTE ADDRESS: HAMID TIZHOOSH Professor, Director of Kimia Lab, University of Waterloo, Canada The talk investigates the following questions and attempt to find some answers: • What does AI offer for digital pathology? • How does observer variability affect diagnosis? • How does image search work? • How can image search contribute to diagnostic 6TH DIGITAL PATHOLOGY & AI CONGRESS: USA UTILIZI...
Artificial Intelligence in Medical Imaging
zhlédnutí 7KPřed 3 lety
A talk by Dr. Hamid Tizhoosh at the MCMASTER WORLD CONGRESS 2020 NOVEMBER 2, 2020 - NOVEMBER 27, 2020 AI is thought to represent not only a symbolic system of human thought, but a new era in human life. Whether we are aware of it or not, it is beginning to influence our global society. It is therefore imperative to understand its process, and implications, for our everyday lives. The world of A...
KimiaNet - Training a Histopathology Deep Network from Scratch
zhlédnutí 1,3KPřed 3 lety
A Talk by Professor Tizhoosh at the Pathology Visions 2020. Deep embeddings, or feature vectors, provided by pre-trained deep artificial neural networks have become a dominant source for image representation in digital pathology. Their contribution to the performance of image analysis can be improved through fine-tuning. One might even train a deep network from scratch with the histopathology i...
Recognizing Magnification Levels in Microscopic Snapshots - EMBC 2020
zhlédnutí 251Před 4 lety
Recent advances in digital imaging has transformed computer vision and machine learning to new tools for analyzing pathology images. This trend could automate some of the tasks in the diagnostic pathology and elevate the pathologist workload. The final step of any cancer diagnosis procedure is performed by the expert pathologist. These experts use microscopes with high level of optical magnific...
Supervision & Source Domain Impact on Representation Learning: A Histopathology Case Study -EMBC2020
zhlédnutí 395Před 4 lety
As many algorithms depend on a suitable representation of data, learning unique features is considered a crucial task. Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large set of labeled data limits the application of such methods. As an example, high-quality delineations of regions of interest in the field of pa...
A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images - IJCNN 2020
zhlédnutí 308Před 4 lety
During the last decade, the digitization of pathology has gained considerable momentum. Digital pathology offers many advantages including more efficient workflows, easier collaboration as well as a powerful venue for telepathology. At the same time, applying Computer-Aided Diagnosis (CAD) on Whole Slide Images (WSIs) has received substantial attention as a direct result of the digitization. Th...
Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks - IJCNN 2020
zhlédnutí 425Před 4 lety
Siamese neural network is a very powerful architecture for both feature extraction and metric learning. It usually consists of several networks that share weights. The Siamese concept is topology-agnostic and can use any neural network as its backbone. The two most popular loss functions for training these networks are the triplet and contrastive loss functions. In this paper, we propose two no...
Representation Learning of Histopathology Images using Graph Neural Networks - CVPR 2020 CVMI
zhlédnutí 1,1KPřed 4 lety
Representation learning for Whole Slide Images (WSIs) is pivotal in developing image-based systems to achieve higher precision in diagnostic pathology. We propose a two-stage framework for WSI representation learning. We sample relevant patches using a color-based method and use graph neural networks to learn relations among sampled patches to aggregate the image information into a single vecto...
AI in Pathology - A Dell Technologies Video on Huron Digital Pathology and Kimia Lab
zhlédnutí 2,3KPřed 4 lety
AI in Pathology - A Dell Technologies Video on Huron Digital Pathology and Kimia Lab
Image Search for Pan-Cancer Diagnostic Consensus - Dell Technologies Virtual HIMSS20 Webinar
zhlédnutí 343Před 4 lety
Image Search for Pan-Cancer Diagnostic Consensus - Dell Technologies Virtual HIMSS20 Webinar
AI system more accurately identifies collapsed lungs using chest x-rays | CTV News
zhlédnutí 1,3KPřed 4 lety
AI system more accurately identifies collapsed lungs using chest x-rays | CTV News
Can AI Agents be Ethical? (Ethics of Artificial intelligence in Medical Imaging)
zhlédnutí 2,4KPřed 5 lety
Can AI Agents be Ethical? (Ethics of Artificial intelligence in Medical Imaging)
Introduction to Digital Pathology and AI Algorithms
zhlédnutí 13KPřed 5 lety
Introduction to Digital Pathology and AI Algorithms
Machine Intelligence - Lecture 21 (Naive Bayes, Swarm Intelligence, Ant Colonies)
zhlédnutí 5KPřed 5 lety
Machine Intelligence - Lecture 21 (Naive Bayes, Swarm Intelligence, Ant Colonies)
Machine Intelligence - Lecture 20 (Bayesian Learning, Bayes Theorem, Naive Bayes)
zhlédnutí 10KPřed 5 lety
Machine Intelligence - Lecture 20 (Bayesian Learning, Bayes Theorem, Naive Bayes)
Machine Intelligence - Lecture 19 (Opposition-Based Learning, GAs, DE)
zhlédnutí 6KPřed 5 lety
Machine Intelligence - Lecture 19 (Opposition-Based Learning, GAs, DE)
Machine Intelligence - Lecture 18 (Evolutionary Algorithms)
zhlédnutí 29KPřed 5 lety
Machine Intelligence - Lecture 18 (Evolutionary Algorithms)
Machine Intelligence - Lecture 17 (Fuzzy Logic, Fuzzy Inference)
zhlédnutí 97KPřed 5 lety
Machine Intelligence - Lecture 17 (Fuzzy Logic, Fuzzy Inference)
Machine Intelligence - Lecture 16 (Decision Trees)
zhlédnutí 9KPřed 5 lety
Machine Intelligence - Lecture 16 (Decision Trees)
Machine Intelligence - Lecture 15 (Reinforcement Learning, Q-Learning)
zhlédnutí 5KPřed 5 lety
Machine Intelligence - Lecture 15 (Reinforcement Learning, Q-Learning)
Machine Intelligence - Lecture 14 (Overfitting in Deep Learning, Reinforcement Learning)
zhlédnutí 4,3KPřed 5 lety
Machine Intelligence - Lecture 14 (Overfitting in Deep Learning, Reinforcement Learning)
Image Search for Medical Imaging - Huron Digital Pathology
zhlédnutí 992Před 5 lety
Image Search for Medical Imaging - Huron Digital Pathology
Machine Intelligence - Lecture 13 (Convolutional Neural Networks, CNNs)
zhlédnutí 6KPřed 5 lety
Machine Intelligence - Lecture 13 (Convolutional Neural Networks, CNNs)