NEWS
New research to develop smart microscopes
Danaher Corporation has launched a research collaboration with Stanford University’s Department of Bioengineering intended to shape the future of cancer drug screening through ‘smart microscopy’. Combining spatial biology with artificial intelligence (AI), the research team at the Danaher Beacon for Spatialomics aims to help de-risk cancer drug development. Tumours are highly variable, not
just from tumour to tumour but within each tumour itself. This variation in the ‘microenvironment’ leads to unpredictable clinical outcomes, including high failure rates during clinical trials. The collaboration aims to leverage the latest findings in spatial biology coupled with cutting-edge AI to make it possible to screen more complex cellular systems. Chandra
Ramanathan, VP and
Head of External Innovation of Danaher’s DH Life Sciences LLC subsidiary, said: “Many oncology drug trials fail because we cannot yet capture and analyse the nuances of the tumour microenvironment and how key proteins spatially interact with each other. Addressing this challenge will require collecting data at scale and designing new ways to analyse it. We are delighted to commit Danaher’s expertise to seek to develop AI-driven phenotyping that could improve drug screening and bring more effective and safer drugs to cancer patients.”
The collaboration is a partnership between Leica Microsystems, a Danaher subsidiary, and Lundberg, a researcher and leader in the field of spatial proteomics and cell biology known for her involvement in the Human Protein Atlas project. The outcome could be an analysis engine that can detect spatial, proteomic, and metabolic changes in the tumour microenvironment and more accurately predict how tumours will respond to potential therapies. The project is the latest addition to the Danaher Beacons program, which funds product-driven scientific research with globally recognised academic investigators.
14
Open-source AI foundation model for pathology
French startup Bioptimus has announced the release of
H-optimus-0, which the company says is the world’s largest open-source AI foundation model for pathology. With 1.1 billion parameters, H-optimus-0 is trained on a proprietary dataset of several hundreds of millions of images extracted from over 500,000 histopathology slides across 4,000 clinical practices.
Bioptimus says its new foundation model sets a new benchmark for state-of-the-art performance in several critical medical diagnostic tasks, from identifying cancerous cells to detecting genetic abnormalities in tumours. Rodolphe Jenatton, Chief Technology Officer at Bioptimus commented: “Having launched less than five months ago, we are excited to introduce H-optimus-0, a fully open-source model that represents a significant leap forward in the field of pathology. We are committed to advancing medical research and improving patient care. By encouraging collaboration and the adoption of new practices, we aim to speed up innovations in pathology and beyond, ultimately benefiting patients worldwide.” Trained on a vast dataset of over
500,000 pathology slides, H-optimus-0 has been exposed to a diverse array of cases, enabling it to generalise effectively across different diagnostic scenarios. H-optimus-0 achieves state-of-the-art performance in several key diagnostics tasks, consistently meeting the performance or outperforming existing models and setting new standards in the field. The model was assessed on 5 tile-level tasks to identify tissue types or tissue characteristics and 6 slide-level tasks to detect the presence of biomarkers or the presence of metastasis across several cancer types.
As an open-source model, H-optimus-0 can be utilised by researchers to accelerate the development of novel digital pathology models and will foster collaboration among researchers, clinicians, and developers, driving further advancements and solutions in pathology AI. For more information, visit
https://www.bioptimus.com.
Thermo Fisher Scientific completes Olink acquisition
Thermo Fisher Scientific has announced that it has completed its acquisition of Olink, a Sweden-based provider of next- generation proteomics solutions. The transaction values Olink at approximately $3.1 billion. Olink will become part of Thermo Fisher’s Life Sciences Solutions segment. “We are excited to welcome Olink colleagues to Thermo Fisher,” said Marc N Casper, Chairman, President and Chief Executive Officer of Thermo Fisher. “Protein research is key to
advancing our understanding of human biology and delivering on the promise of precision medicine. Olink’s proven and transformative solutions for proteomics are highly complementary to our leading mass spectrometry and life-sciences offerings. By expanding our capabilities in the high-growth proteomics market, we will enable scientists and researchers around the globe to meaningfully accelerate discovery and scientific breakthroughs while delivering significant value to our shareholders.”
AUGUST 2024
WWW.PATHOLOGYINPRACTICE.COM
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
