No abstract

Determining the presence of tumor in biopsies and the decision-making during resections is often dependent on intraoperative rapid frozen-section histopathology. Recently, stimulated Raman scattering microscopy has been introduced to rapidly generate digital hematoxylin-and-eosin-stained-like images (stimulated Raman histology) for intraoperative analysis. To enable intraoperative prediction of tumor presence, we aimed to develop a new deep residual convolutional neural network in an automated pipeline and tested its validity. In a monocentric prospective clinical study with 94 patients undergoing biopsy, brain or spinal tumor resection, Stimulated Raman histology images of intraoperative tissue samples were obtained using a fiber-laser-based stimulated Raman scattering microscope. A residual network was established and trained in ResNetV50 to predict three classes for each image: (1) tumor, (2) non-tumor, and (3) low-quality. The residual network was validated on images obtained in three small random areas within the tissue samples and were blindly independently reviewed by a neuropathologist as ground truth. 402 images derived from 132 tissue samples were analyzed representing the entire spectrum of neurooncological surgery. The automated workflow took in a mean of 240 s per case, and the residual network correctly classified tumor (305/326), non-tumorous tissue (49/67), and low-quality (6/9) images with an inter-rater agreement of 89.6% (κ = 0.671). An excellent internal consistency was found among the random areas with 90.2% (Cα = 0.942) accuracy. In conclusion, the novel stimulated Raman histology-based residual network can reliably detect the microscopic presence of tumor and differentiate from non-tumorous brain tissue in resection and biopsy samples within 4 min and may pave a promising way for an alternative rapid intraoperative histopathological decision-making tool.

OBJECTIVE Current guidelines primarily suggest resection of brain metastases (BMs) in patients with limited lesions. With a growing number of highly effective local and systemic treatment options, this view may be challenged. The purpose of this study was to evaluate the role of metastasectomy, disregarding BM count, in a comprehensive treatment setting. METHODS In this monocentric retrospective analysis, the authors included patients who underwent resection for at least 1 BM and collected demographic, clinical, and tumor-associated parameters. Prognostic factors for local control and overall survival (OS) were analyzed with the log-rank test and Cox proportional hazards analysis. RESULTS The authors analyzed 216 patients. One hundred twenty-nine (59.7%) patients were diagnosed with a single/solitary BM, whereas 64 (29.6%) patients had 2–3 BMs and the remaining 23 (10.6%) had more than 3 BMs. With resection of symptomatic BMs, a significant improvement in Karnofsky Performance Scale (KPS) was achieved (p < 0.001), thereby enabling adjuvant radiotherapy for 199 (92.1%) patients and systemic treatment for 119 (55.1%) patients. During follow-up, 83 (38.4%) patients experienced local recurrence. BM count did not significantly influence local control rates. By the time of analysis, 120 (55.6%) patients had died; the leading cause of death was systemic tumor progression. The mean (range) OS after surgery was 12.7 (0–88) months. In univariate analysis, the BM count did not influence OS (p = 0.844), but age < 65 years (p = 0.007), preoperative and postoperative KPS ≥ 70 (p = 0.002 and p = 0.005, respectively), systemic metastases other than BM (p = 0.004), adjuvant radiation therapy (p < 0.001), and adjuvant systemic treatment (p < 0.001) were prognostic factors. In regression analysis, the presence of extracranial metastases (HR 2.30, 95% CI 1.53–3.48, p < 0.001), adjuvant radiation therapy (HR 0.97, 95% CI 0.23–0.86, p = 0.016), and adjuvant systemic treatment (HR 0.37, 95% CI 0.25–0.55, p < 0.001) remained as independent factors for survival. CONCLUSIONS Surgery for symptomatic BM from non–small cell lung cancer may be indicated even for patients with multiple lesions in order to alleviate their neurological symptoms and to consequently facilitate further treatment.