Rapid Intraoperative Diagnosis of Pediatric Brain Tumors Using Stimulated Raman Histology

Abstract

Accurate histopathologic diagnosis is essential for providing optimal surgical management of pediatric brain tumors. Current methods for intraoperative histology are time- and labor-intensive and often introduce artifact that limit interpretation. Stimulated Raman histology (SRH) is a novel label-free imaging technique that provides intraoperative histologic images of fresh, unprocessed surgical specimens. Here we evaluate the capacity of SRH for use in the intraoperative diagnosis of pediatric type brain tumors. SRH revealed key diagnostic features in fresh tissue specimens collected from 33 prospectively enrolled pediatric type brain tumor patients, preserving tumor cytology and histoarchitecture in all specimens. We simulated an intraoperative consultation for 25 patients with specimens imaged using both SRH and standard hematoxylin and eosin histology. SRH-based diagnoses achieved near-perfect diagnostic concordance (Cohen's kappa, > 0.90) and an accuracy of 92% to 96%. We then developed a quantitative histologic method using SRH images based on rapid image feature extraction. Nuclear density, tumor-associated macrophage infiltration, and nuclear morphology parameters from 3337 SRH fields of view were used to develop and validate a decision-tree machine-learning model. Using SRH image features, our model correctly classified 25 fresh pediatric type surgical specimens into normal versus lesional tissue and low-grade versus high-grade tumors with 100% accuracy. Our results provide insight into how SRH can deliver rapid diagnostic histologic data that could inform the surgical management of pediatric brain tumors. A new imaging method simplifies diagnosis and informs decision making during pediatric brain tumor surgery. .

AI-Assisted In Situ Detection of Human Glioma Infiltration Using a Novel Computational Method for Optical Coherence Tomography

“…Unfortunately, several limitations are associated to these techniques, including the intrinsic weakness of the Raman signal, limited imaging depth and field of view (FOV), and slow imaging speed [23][24][25]. In addition, the capability of Raman spectroscopy and/or imaging for detecting cancer-infiltrated brain tissue intraoperatively has not yet fully demonstrated [26,27]. More recently, coherent Raman Scattering (CRS) and Stimulated Raman Scattering Microscopy (SRS) have been explored for brain tumor margin differentiation; however, a definite intraoperative Computer-Aided Diagnosis system for human brain tissue differentiation has not been reported [23,26,28,29].…”

Repurposing Molecular Imaging and Sensing for Cancer Image–Guided Surgery

“…Raman spectroscopy has been successfully used to determine tissue pathology, identifying subtle changes in tissue composition in freshly excised brain tissue (74). Further application in pediatric brain cancers also demonstrated strong agreement between Raman and conventional pathology (75). The diverse sources of contrast for Raman spectroscopy allow the use of tissue-specific properties to determine which contrast source is most valuable.…”

What does it mean to provide decision support to a responsible and competent expert?

“…Titano et al (2018) proposed a ML-based DDSS dedicated to anticipating neurological events by analyzing cranial radiographs. Numerous ML-based DDSSs are also dedicated to supporting the detection of tumors, such as breast tumors (Joo et al, 2004), brain tumors (Hollon et al, 2018), or skin tumors (Esteva et al, 2017). Elsner et al (2018) and Pasquali et al (2020) also reported the use of ML-based DDSSs in teledermatology to support physicians in the detection of skin tumors during teleconsultations.…”