Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery 1. The existing workflow for intraoperative diagnosis based on hematoxylin and eosin-staining of processed tissue is time-, resource-, and labor-intensive 2,3. Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed pathology workforce 4. Here, we report a parallel workflow that combines stimulated Raman histology (SRH) 5-7 , a label-free optical imaging method, and deep convolutional neural networks (CNN) to predict diagnosis at the bedside in near real-time in an automated fashion. Specifically, our CNN, trained on over 2.5 million SRH images, predicts brain tumor diagnosis in the operating room in under 150 seconds, an order of magnitude faster than conventional techniques (e.g., 20-30 minutes) 2. In a multicenter, prospective clinical trial (n = 278) we demonstrated that CNN-based diagnosis of SRH images was non-inferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% vs. 93.9%). Our CNN learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors. Additionally, 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 complimentary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.

Abstract-The complement cascade has been implicated in ischemia/reperfusion injury, and recent studies have shown that complement inhibition is a promising treatment option for acute stroke. The development of clinically useful therapies has been hindered, however, by insufficient understanding of which complement subcomponents contribute to post-ischemic injury. To address this issue, we subjected mice deficient in selected complement proteins (C1q, C3, C5) to transient focal cerebral ischemia. Of the strains investigated, only C3 Ϫ/Ϫ mice were protected, as demonstrated by 34% reductions in both infarct volume (PϽ0.01) and neurological deficit score (PϽ0.05). C3-deficient mice also manifested decreased granulocyte infiltration (PϽ0.02) and reduced oxidative stress (PϽ0.05). Finally, administration of a C3a-receptor antagonist resulted in commensurate neurological improvement and stroke volume reduction (PϽ0.05). Together, these results establish C3 activation as the key constituent in complement-related inflammatory tissue injury following stroke and suggest a C3a anaphylatoxin-mediated mechanism. (Circ Res. 2006;99:209-217.)