Format

Send to

Choose Destination
Nat Med. 2020 Jan;26(1):52-58. doi: 10.1038/s41591-019-0715-9. Epub 2020 Jan 6.

Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks.

Author information

1
Department of Neurosurgery, University of Michigan, Ann Arbor, MI, USA.
2
School of Medicine, University of Michigan, Ann Arbor, MI, USA.
3
College of Physicians and Surgeons, Columbia University, New York, NY, USA.
4
Department of Neurological Surgery, University of Miami, Miami, FL, USA.
5
Department of Neurological Surgery, Columbia University, New York, NY, USA.
6
Invenio Imaging, Inc., Santa Clara, CA, USA.
7
Department of Pediatrics Oncology, Columbia University, New York, NY, USA.
8
Department of Otolaryngology, University of Michigan, Ann Arbor, MI, USA.
9
Department of Neurological Surgery, University of California San Francisco, San Francisco, CA, USA.
10
Department of Pathology, New York University, New York, NY, USA.
11
Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, USA.
12
Department of Pathology & Cell Biology, Columbia University, New York, NY, USA.
13
Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA.
14
Department of Pathology, University of Michigan, Ann Arbor, MI, USA.
15
Department of Neurosurgery, University of Michigan, Ann Arbor, MI, USA. Daniel.Orringer@nyulangone.org.
16
Department of Neurosurgery, New York University, New York, NY, USA. Daniel.Orringer@nyulangone.org.

Abstract

Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery1. The existing workflow for intraoperative diagnosis based on hematoxylin and eosin staining of processed tissue is time, resource and labor intensive2,3. Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed, pathology workforce4. In the present study, we report a parallel workflow that combines stimulated Raman histology (SRH)5-7, a label-free optical imaging method and deep convolutional neural networks (CNNs) to predict diagnosis at the bedside in near real-time in an automated fashion. Specifically, our CNNs, trained on over 2.5 million SRH images, predict brain tumor diagnosis in the operating room in under 150 s, an order of magnitude faster than conventional techniques (for example, 20-30 min)2. In a multicenter, prospective clinical trial (n = 278), we demonstrated that CNN-based diagnosis of SRH images was noninferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% versus 93.9%). Our CNNs learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors. In addition, we implemented a semantic segmentation method to identify tumor-infiltrated diagnostic regions within SRH images. These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complementary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.

PMID:
31907460
PMCID:
PMC6960329
[Available on 2020-07-06]
DOI:
10.1038/s41591-019-0715-9

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center