Stimulated Raman Histology and Machine learning provides an alternative approach in brain tumor diagnosis

The study published in Nature Medicine examined the diagnostic accuracy of brain tumor image classification through artificial intelligence tool, compared with the accuracy of pathologist interpretation of conventional histologic images. The results for both methods were comparable: the artificial intelligence based diagnosis was 94.6% accurate, compared with 93.9% for the traditional pathologist-based assessment and interpretation. This research was conducted at NYU Langone Health.

The imaging technique known as stimulated Raman histology (SRH), reveals tumor infiltration in human tissue by collecting scattered laser light, illuminating essential features not typically seen in standard histologic images. Using deep convolutional neural network (CNN) with more than 2.5 million samples from 415 patients researchers trained a machine-learning algorithm to classify tissue into 13 histologic categories that represent the most common brain tumors, including malignant glioma, lymphoma, metastatic tumors, and meningioma.

Researchers note advantages with this method include quicker and almost realtime results (two and half minutes) with this method compared to traditional pathological examination (twenty to thirty minutes). This can be very useful especially during intraoperative decision making. In addition, researchers found that diagnostic errors due to this method are different from traditional pathology and combining both methods would increase diagnostic accuracy to 100%.

New biomarker based on expression of SHOX2 gene for predicting survival in Gliomas

Researchers at UT Southwestern Medical Center have found a new biomarker for glioma, a common type of brain cancer, that can help doctors determine how aggressive a cancer is and that could eventually help determine the best course of treatment. The findings are published in EBiomedicine.

Researchers from the Harold C. Simmons Comprehensive Cancer Center found that high expression of a gene called SHOX2 predicted poor survival in intermediate-grade gliomas.  “As an independent biomarker, SHOX2 expression is as potent as the currently best and widely used marker known as IDH mutations,” said Dr. Adi Gazdar, Professor of Pathology in the Nancy B. and Jake L. Hamon Center for Therapeutic Oncology and a member of the Simmons Cancer Center.

Word cloud for article
According to the National Cancer Institute, cancers of the brain and nervous system affect nearly 24,000 people annually. In 2013, there were an estimated 152,751 people living with brain and other nervous system cancer in the United States. The overall 5-year survival rate is 33.8 percent.
Knowing the probable survival status of an individual patient may help physicians choose the best treatment. In combination with IDH mutations or several other biomarkers, SHOX2 expression helped to identify subgroups of patients with a good prognosis even though other biomarkers had predicted a bad prognosis.

“Our findings are based on analysis of previously published studies. They will have to be confirmed in prospective studies, and their clinical contribution and method of use remain to be determined,” said Dr. Gazdar, who holds the W. Ray Wallace Distinguished Chair in Molecular Oncology Research.

Citation: “SHOX2 is a Potent Independent Biomarker to Predict Survival of WHO Grade II–III Diffuse Gliomas”. Yu-An Zhang1, Yunyun Zhou1, Xin Luo, Kai Song, Xiaotu Ma, Adwait Sathe, Luc Girard, Guanghua Xiao and Adi F Gazdar. EBioMedicine 2016 vol: 13 pp: 80-89.
DOI: 10.1016/j.ebiom.2016.10.040
Research funding: NIH
Adapted from press release by UT Southwestern Medical Center.