Search

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.

Introduction: Suicide rates are elevated after cancer diagnosis. Existential distress caused by awareness of one's impending death is well‐described in patients with cancer. The authors hypothesized that suicide risk is associated with cancer prognosis, and the impact of prognosis on suicide risk is greatest for populations with higher baseline suicide risk. Methods: The authors identified patients (≥16 years old) with newly diagnosed cancers from 2000 to 2019 in the Surveillance, Epidemiology, and End Results database, representing 27% of US cancers. Multiple primary‐standardized mortality ratios (SMR) were used to estimate the relative risk of suicide within 6 months of diagnosis compared to the general US population, adjusted for age, sex, race, and year of follow‐up. Suicide rates by 20 most common cancer sites were compared with respective 2‐year overall survival rates (i.e., prognosis) using a weighted linear regression model. Results: Among 6,754,704 persons diagnosed with cancer, there were 1610 suicide deaths within 6 months of diagnosis, three times higher than the general population (SMR = 3.1; 95% confidence interval, 3.0–3.3). Suicide risk by cancer site was closely associated with overall prognosis (9.5%/percent survival deficit, R2 = 0.88, p <.0001). The association of prognosis with suicide risk became attenuated over time. For men, the risk of suicide increased by 2.8 suicide deaths per 100,000 person‐years (p <.0001) versus 0.3 in women (p <.0001). The risk was also higher for persons ≥60 old and for the White (vs. Black) race. Conclusions: Poorer prognosis was closely associated with suicide risk early after cancer diagnosis and had a greater effect on populations with higher baseline risks of suicide. This model highlights the need for enhanced psychiatric surveillance and continued research in this patient population. [ABSTRACT FROM AUTHOR]