Send us a text

What do cancer and climate change have in common? Both are very serious problems and in both, machine learning (ML) and artificial intelligence (AI) can be used to support potential solutions. Even though these AI applications may seem very different the ML methods used to support work on both problems are very similar. 

Today’s episode’s guest, Heather Couture from Pixel Scientia Labs does exactly that – fights cancer and climate change with AI. She is a computer scientist specializing in computer vision machine learning and deep learning. She started her company during her Ph.D. when she was doing contract work and expanded her work after receiving her degree. She assists companies with accelerating their machine learning projects by distilling and adapting cutting-edge research and applying her over 16 years of experience in the field for analyzing images. 

Not only does she stay on top of the current research herself, but she also posts about it on LinkedIn several times a week, extracting the most important and actionable information out of the most recent publications on machine learning applications in pathology. 

Her consulting company gives her the opportunity to optimize her work for impact and get engaged with companies and projects that can really make a difference. 

Teamwork is important in every area of life, but in the medical domain and especially in pathology it acquires a whole new dimension. No longer is it possible for a single observer to analyze the data in conjunction with the pathology images. The use of computer vision algorithms is often a must and to come up with medically and diagnostically relevant solutions the domain experts from pathology and computer vision need to work together. 

In clinical settings and in medically focused companies machine learning expertise is necessary to leverage the power of artificial intelligence and apply it to their problems and challenges. 

Heather supports her clients with such tasks as nuclear detection and classification, mitosis detection, segmentation of different tissue types in pathology images, stain normalization, and other techniques to enable a deep learning model to generalize images from a different scanner. All these things come into a lot of different projects, even if the project endpoints vary. Another important aspect of every deep learning project is data collection and data labeling. 

Are you working with deep learning for pathology image analysis? If so, visit https://pixelscientia.com/ to learn more about the machine learning expertise you can leverage for your projects.

Support the show

Get the "Digital Pathology 101" FREE E-book and join us!