Suggestions
Heather Couture
Accelerating machine learning projects for pathology startups - CV/ML/DL Consultant
Heather Couture is a seasoned professional with over 17 years of experience in academia and industry, specializing in machine learning and computer vision.
With a PhD in Computer Science and a background in robotics and mathematics, Heather focuses on helping pathology startups accelerate their machine learning projects for precision medicine.
She distills and adapts the latest research in machine learning and computer vision to assist clients in planning and executing projects that align with current best practices.
Heather's expertise lies in strategy development, roadmap creation, and providing valuable advising to ensure the success of pathology startups.
Throughout her career, she has led various ML initiatives, collaborated on impactful research projects, and contributed significantly to the fields of technology and science.
Heather's past experiences include working with organizations like WattTime, the University of North Carolina, Digitalsmiths (now acquired by TiVo), Mars Space Flight Facility at Arizona State University, and more.
She has a strong publication record, with 10+ peer-reviewed publications in reputable conferences and journals such as CVPR, NeurIPS, and MICCAI.
Furthermore, Heather holds multiple patents in the field, demonstrating her innovative approach to problem-solving and technology development.
To stay connected with the industry and share her insights, Heather publishes the 'Pathology ML Insights' newsletter and operates the website pixelscientia.com.
For those seeking guidance on machine learning projects in the pathology domain, Heather Couture is a go-to consultant with a proven track record of success.
Highlights
There are now a few different AI foundation models available for Earth Observation (EO) data. These vast neural networks can be rapidly fine-tuned for many downstream tasks, making them a highly versatile and appealing tool.
Today on Impact AI, I am joined by Hamed Alemohammad, Associate Professor in the Department of Geography at Clark University, Director of the Clark Center for Geospatial Analytics, and former Chief Data Scientist of the Radiant Earth Foundation, to discuss the applications of foundation models for remote sensing. Hamed’s research interests lie at the intersection of geographic information science and geography, using observations and analytical methods like machine learning to better understand the changing systems of our planet.
In this episode, he shares his perspective on the myriad purposes that foundation models serve and offers insight into training and fine-tuning them for different downstream applications. We also discuss how to choose the right one for a given project, ethical considerations for using them responsibly, and more. For a glimpse at the future of foundation models for remote sensing, tune in today!
https://lnkd.in/gKgwv2iE
#ImpactAI #earthobservation #machinelearning #deeplearning #computervision #satellite #remotesensing
Prior work has demonstrated the power of histopathology images and transcriptomic profiles in predicting patient outcomes. However, research on how to combine these types of data to make better predictions is still ongoing.
Andrew H. Song et al. proposed an alternative that involves summarizing the content of images into morphological prototypes and the cellular functions encoded by transcriptomic profiles with biological pathway prototypes.
This approach significantly reduces the number of tokens to be combined.
Their experiments on six cancer types demonstrated overall improved performance in predicting disease-specific survival.
paper: https://lnkd.in/eyPdrGPB code: https://lnkd.in/eTF8wwS2
To learn more about the latest research, subscribe to my Computer Vision Insights newsletter: https://lnkd.in/g9bSuQDP
#Pathology #CancerResearch #PrecisionMedicine #MedicalImaging #MachineLearning #DeepLearning #ComputerVision
