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.
Object. The objective of this study was to compare the accuracy of 3 methods of ventricular catheter placement during CSF shunt operations: the freehand technique using surface anatomy, ultrasonic guidance, and stereotactic neuronavigation.Methods. This retrospective cohort study included all patients from a single institution who underwent a ven tricular CSF shunting procedure in which a new ventricular catheter was placed between January 2005 and March 2010. Data abstracted for each patient included age, sex, diagnosis, method of ventricular catheter placement, site and side of ventricular catheter placement, Evans ratio, and bifrontal ventricular span. Postoperative radiographic stud ies were reviewed for accuracy of ventricular catheter placement. Medical records were also reviewed for evidence of shunt failure requiring revision through December 2011. Statistical analysis was then performed comparing the 3 methods of ventricular catheter placement and to determine risk factors for inaccurate placement.Results. There were 249 patients included in the study; 170 ventricular catheters were freehand passed, 51 were placed using stereotactic neuronavigation, and 28 were placed under intraoperative ultrasonic guidance. There was a statistically significant difference between freehand catheters and stereotactic-guided catheters (p < 0.001), as well as between freehand catheters and ultrasound-guided catheters (p < 0.001). The only risk factor for inaccurate place ment identified in this study was use of the freehand technique. The use of stereotactic neuronavigation and ultrasonic guidance reduced proximal shunt failure rates (p < 0.05) in comparison with a freehand technique.Conclusions. Stereotactic-and ultrasound-guided ventricular catheter placements are significantly more accu rate than freehand placement, and the use of these intraoperative guidance techniques reduced proximal shunt failure in this study.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.