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.

Purpose: Recent artificial intelligence algorithms aided intraoperative decision-making via stimulated Raman histology (SRH) during craniotomy. This study assesses deep learning algorithms for rapid intraoperative diagnosis from SRH images in small stereotactic-guided brain biopsies. It defines a minimum tissue sample size threshold to ensure diagnostic accuracy. Experimental Design: A prospective single-center study examined 121 SRH images from 84 patients with unclear intracranial lesions undergoing stereotactic brain biopsy. Unprocessed, label-free samples were imaged using a portable fiber laser Raman scattering microscope. Three deep learning models were tested to (i) identify tumorous/nontumorous tissue as qualitative biopsy control; (ii) subclassify into high-grade glioma (central nervous system World Health Organization grade 4), diffuse low-grade glioma (central nervous system World Health Organization grades 2–3), metastases, lymphoma, or gliosis; and (iii) molecularly subtype IDH and 1p/19q statuses of adult-type diffuse gliomas. Model predictions were evaluated against frozen section analysis and final neuropathologic diagnoses. Results: The first model identified tumorous/nontumorous tissue with 91.7% accuracy. Sample size on slides impacted accuracy in brain tumor subclassification (81.6%, κ = 0.72 frozen section; 73.9%, κ = 0.61 second model), with SRH images being smaller than hematoxylin and eosin images (4.1 ± 2.5 mm2 vs. 16.7 ± 8.2 mm2, P < 0.001). SRH images with more than 140 high-quality patches and a mean squeezed sample of 5.26 mm2 yielded 89.5% accuracy in subclassification and 93.9% in molecular subtyping of adult-type diffuse gliomas. Conclusions: Artificial intelligence–based SRH image analysis is non-inferior to frozen section analysis in detecting and subclassifying brain tumors during small stereotactic-guided biopsies once a critical squeezed sample size is reached. Beyond frozen section analysis, it enables valid molecular glioma subtyping, allowing faster treatment decisions in the future; however, refinement is needed for long-term application.

Background: Accurate intraoperative diagnosis is crucial for differentiating between primary central nervous system (CNS) lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge. Methods: We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within <3 min. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and 2 additional independent test cohorts. We trained on 54 000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS neoplastic/nonneoplastic lesions. Training and test data were collected from 4 tertiary international medical centers. The final histopathological diagnosis served as ground truth. Results: In the prospective test cohort of PCNSL and non-PCNSL entities (n = 160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ± 0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 77.77%). The additional test cohorts (n = 420, n = 59) reached balanced accuracy rates of 95.44% ± 0.74 and 95.57% ± 2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma’s capabilities to detect class-specific histomorphological key features. Conclusions: RapidLymphoma proves reliable and valid for intraoperative PCNSL detection and differentiation from other CNS entities. It provides visual feedback within 3 min, enabling fast clinical decision-making and subsequent treatment strategy planning.

Label-free identification of tumor cells using spectroscopic assays has emerged as a technological innovation with a proven ability for rapid implementation in clinical care. Machine learning facilitates the optimization of processing and interpretation of extensive data, such as various spectroscopy data obtained from surgical samples. The here-described preclinical work investigates the potential of machine learning algorithms combining confocal Raman spectroscopy to distinguish non-differentiated glioblastoma cells and their respective isogenic differentiated phenotype by means of confocal ultra-rapid measurements. For this purpose, we measured and correlated modalities of 1146 intracellular single-point measurements and sustainingly clustered cell components to predict tumor stem cell existence. By further narrowing a few selected peaks, we found indicative evidence that using our computational imaging technology is a powerful approach to detect tumor stem cells in vitro with an accuracy of 91.7% in distinct cell compartments, mainly because of greater lipid content and putative different protein structures. We also demonstrate that the presented technology can overcome intra- and intertumoral cellular heterogeneity of our disease models, verifying the elevated physiological relevance of our applied disease modeling technology despite intracellular noise limitations for future translational evaluation.

Background Accurate intraoperative diagnosis is crucial for differentiating between primary CNS lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge. We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within less than three minutes. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and two additional independent test cohorts. We trained on 54,000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS tumor/non-tumor lesions. Training and test data were collected from four tertiary international medical centers. The final histopathological diagnosis served as ground-truth. In the prospective test cohort of PCNSL and non-PCNSL entities (n=160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ±0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 78.94%). The additional test cohorts (n=420, n=59) reached balanced accuracy rates of 95.44% ±0.74 and 95.57% ±2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma’s capabilities to detect class-specific histomorphological key features. RapidLymphoma is valid and reliable in detecting PCNSL and differentiating from other CNS entities within three minutes, as well as visual feedback in an intraoperative setting. This leads to fast clinical decision-making and further treatment strategy planning. Importance of the study This study introduces RapidLymphoma, a novel self-supervised-based deep-learning model for visual representations to leverage the detection of primary CNS Lymphoma (PCNSL) and differentiation from common and rare CNS entities using intraoperative label-free stimulated Raman histology. While PCNSL is rare, time-critical personalized treatment with fast intraoperative decision-making is needed. In an international multicentric clinical trial, RapidLymphoma first demonstrated its ability to detect and differentiate PCNSL from other CNS lesions with an overall diagnostic balanced accuracy of 97.81% ± 0.91 compared to formalin-fixed paraffin-embedded diagnosis and is non-inferior to frozen section analysis. It provides near real-time intraoperative feedback and guidance to the surgeon, delivering a diagnosis in under three minutes. RapidLymphoma extracts key histomorphological features for detecting and differentiating CNS lesions by utilizing the benefits of intraoperative stimulated Raman histology. This guidance is assisted through a visual prediction heatmap feedback, highlighting critical areas for the surgeon and pathologist.