From cutting-edge research to commercialization: transforming histopathology with deep learning-based virtual staining

By Aydogan Ozcan, Yair Rivenson, Kevin De Haan, Hongda Wang

Like Comment
Read the paper

Over a year ago, we published our paper in Nature Biomedical Engineering which introduced a deep learning-based method to “virtually stain” autofluorescence images of unlabeled histological tissue sections, eliminating the need for chemical staining1 (see the Figure).  This technology was developed to leverage the speed and computational power of deep learning to improve upon century-old histochemical staining techniques which can be slow, laborious and expensive. In our paper we showed that this virtual staining technology using deep neural networks is capable of generating highly accurate stains across a wide variety of tissue and stain types. It has the potential to revolutionize the field of histopathology by reducing the cost of tissue staining, while making it much faster, less destructive to the tissue and more consistent/repeatable.

Since the publication of our paper, we have had a number of exciting developments moving the technology forward. We have continued to find new clinical applications for this unique technology, and used the computational nature of the technique to generate stains which would be impossible to create using traditional histochemical staining. For example, we have created what we refer to as a “digital staining matrix”2,3 which allows us to generate and digitally blend multiple stains using a single deep neural network, by specifying which stain should be performed on the pixel level. Not only can this framework be used to create micro-structured stains, digitally staining different areas of labelfree tissue with different types of stains, it can also enable these stains to be blended together in unique combinations. This technology can be used to train new virtual staining networks and can help pathologists receive the most relevant information possible from the various virtual stains being performed.3

Motivated by transformative potential of the virtual staining technology, we have also begun the process of its commercialization and founded Pictor Labs, a new Los Angeles-based startup. Pictor in Latin means “painter” and at Pictor Labs we virtually “paint” the microstructure of tissue samples using deep learning. In 2020, we were successful in raising funding from venture capital firms including M Ventures (a subsidy of Merck KGaA), Motus Ventures, as well as private investors. Through Pictor Labs, we aim to revolutionize the histopathology staining workflow using virtual staining, and by building a cloud computing-based platform which facilitates histopathology through artificial intelligence, enables tissue-based diagnoses and helps clinicians better manage patient care. Our team is very excited to have this unique opportunity to bring our cutting-edge academic research into the commercialization phase and looks forward to impacting human health over the coming years using this transformative virtual staining technology.

  1. Rivenson, Y. et al. Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning. Nature Biomedical Engineering 1 (2019) doi:10.1038/s41551-019-0362-y.
  2. Zhang, Y. et al. Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue. Light: Science & Applications 9, 78 (2020).
  3. Rivenson, Y., de Haan, K., Wallace, W. D. & Ozcan, A. Emerging Advances to Transform Histopathology Using Virtual Staining. BME Frontiers 2020, 9647163 (2020).

Figure: Examples of different virtual stains generated using our deep learning-based method.1

Aydogan Ozcan

Professor, UCLA

bio-photonics, computational imaging and sensing, mobile health, diagnostics, telemedicine