⚡ Quick Summary
This study explored the use of stimulated Raman histology (SRH) combined with artificial intelligence for rapid intraoperative tissue diagnostics in brain tumor surgeries. The results demonstrated a promising accuracy of 77% in predicting tissue types, with an impressive AUC of 0.93 for identifying IDH mutations.
🔍 Key Details
- 📊 Sample Size: 70 consecutive adult cases with brain tumors
- 🧩 Techniques Used: Stimulated Raman histology (SRH) and AI-based image classification
- ⚙️ Evaluation Metrics: Logistic regression and Receiver Operator Curve (ROC) analysis
- 🏆 Performance: AUC of 0.77 for overall predictions, AUC of 0.93 for IDH mutations
🔑 Key Takeaways
- 🧠 SRH provides a label-free imaging method for intraoperative diagnostics.
- 💡 AI integration enhances the speed and accuracy of tissue classification.
- 📈 High accuracy was observed for meningiomas and high-grade gliomas.
- 🔬 IDH mutations were predicted with an AUC of 0.93, indicating strong diagnostic potential.
- 🖼️ Postoperative MRI results aligned with SRH findings in 4 out of 5 cases.
- 🚀 Future improvements in AI classification could enhance reliability and integration into surgical workflows.
📚 Background
Accurate intraoperative tissue diagnostics are crucial for making informed decisions regarding the extent of resection (EOR) during brain tumor surgeries. Traditional methods often involve lengthy processing times, which can delay critical surgical decisions. The advent of stimulated Raman histology (SRH) offers a novel, label-free approach that leverages the biochemical properties of tissues to generate images similar to those produced by conventional histology.
🗒️ Study
This study aimed to evaluate the accuracy of SRH in providing rapid intraoperative tissue diagnoses compared to final histopathological results. Conducted on 70 adult patients with various brain tumors, the researchers utilized three different SRH classifiers: diagnostic, molecular, and tumor/non-tumor. Additionally, they assessed IDH mutations in a subset of patients, further enhancing the diagnostic capabilities of this innovative imaging technique.
📈 Results
The analysis revealed that the SRH predictions had an overall AUC of 0.77, indicating a significant agreement with final diagnoses. Specific tumor types showed variable accuracies, with meningiomas achieving the highest accuracy. Notably, the prediction of IDH mutations demonstrated an exceptional AUC of 0.93, underscoring the potential of SRH in molecular diagnostics. Furthermore, the correlation between SRH results and early postoperative MRI was promising, with a concordance rate of 80%.
🌍 Impact and Implications
The findings from this study suggest that SRH, when combined with AI, could revolutionize intraoperative diagnostics in neurosurgery. By providing rapid and accurate tissue characterization, surgeons can make more informed decisions during procedures, potentially improving patient outcomes. As the technology matures and becomes better integrated into surgical workflows, we can anticipate enhanced reliability and broader applications in various surgical fields.
🔮 Conclusion
This initial experience with stimulated Raman histology highlights its potential as a transformative tool for intraoperative tissue diagnostics. With an impressive accuracy rate and the ability to predict critical genetic mutations, SRH could significantly enhance surgical decision-making processes. Continued research and development in this area are essential to fully realize the benefits of this innovative technology in clinical practice.
💬 Your comments
What are your thoughts on the integration of AI and novel imaging techniques in surgical settings? We invite you to share your insights and engage in a discussion! 💬 Please leave your comments below or connect with us on social media:
Intraoperative label-free tissue diagnostics using a stimulated Raman histology imaging system with artificial intelligence: An initial experience.
Abstract
BACKGROUND: Accurate intraoperative tissue diagnostics could impact on decision making regarding the extent of resection (EOR) during brain tumor surgery. Stimulated Raman histology (SRH) is a label-free optical imaging method that uses different biochemical properties of tissue to generate a hematoxylin-eosin-like image and, in combination with an artificial intelligence-based image classifier, offers the opportunity to obtain rapid intraoperative tissue diagnoses.
OBJECTIVE: The goal of this study was to report on our initial experience with SRH to evaluate its accuracy in comparison to final tissue diagnosis.
MATERIALS & METHODS: We evaluated 70 consecutive adult cases with brain tumors. We compared results of the three different SRH classifier (diagnostic, molecular and tumor/non-tumor) to the respective final histopathological result. Similarly, we evaluated the isocitrate dehydrogenase (IDH) mutations in 18 patients using SRH. Lastly, we compared SRH results of samples taken from the tumor margins with early postoperative MRI. Prediction accuracy was evaluated by logistic regression and Receiver Operator Curve (ROC) analysis.
RESULTS: We included 19 gliomas, 9 metastases, 22 meningiomas and 14 other tumor entities. Regarding accuracy of intraoperative SRH predictions, regression analysis showed an Area Under the Curve (AUC) of 0.77 (95 % C.I. 0.64-0.89, p = 0.0008), suggesting agreement of predictions with final diagnosis. For specific tumor entities, variable accuracies were observed: The highest accuracy was obtained for meningiomas followed by high-grade glioma. IDH mutations were predicted with an AUC of 0.93 (95 % C.I. 0.88-0.98; p < 0.0001). The SRH examination of tissue samples from tumor margins corresponded with postoperative MRI in 4 out of 5 cases.
CONCLUSION: Our initial experience with SRH shows that this novel imaging technique is a promising approach to obtain rapid intraoperative tissue diagnosis to guide surgical decision making based on histology and cell-density. With further refinement of AI-based automated image classification and a better integration into the surgical workflow, prediction accuracy and reliability could be improved.
Author: [‘Nohman AI’, ‘Ivren M’, ‘Alhalabi OT’, ‘Sahm F’, ‘Dao Trong P’, ‘Krieg SM’, ‘Unterberg A’, ‘Scherer M’]
Journal: Clin Neurol Neurosurg
Citation: Nohman AI, et al. Intraoperative label-free tissue diagnostics using a stimulated Raman histology imaging system with artificial intelligence: An initial experience. Intraoperative label-free tissue diagnostics using a stimulated Raman histology imaging system with artificial intelligence: An initial experience. 2024; 247:108646. doi: 10.1016/j.clineuro.2024.108646