Deep learning based on preoperative magnetic resonance (MR) images improves the predictive power of survival models in primary spinal cord astrocytomas

Advances in Molecular Pathology, Diagnosis and Treatment of Spinal Cord Astrocytomas

Spinal cord astrocytoma (SCA) is a rare subtype of astrocytoma, posing challenges in diagnosis and treatment. Low-grade SCA can achieve long-term survival solely through surgery, while high-grade has a disappointing prognosis even with comprehensive treatment. Diagnostic criteria and standard treatment of intracranial astrocytoma have shown obvious limitations in SCA. Research on the molecular mechanism in SCA is lagging far behind that on intracranial astrocytoma. In recent years, huge breakthroughs have been made in molecular pathology of astrocytoma, and novel techniques have emerged, including DNA methylation analysis and radiomics. These advances are now making it possible to provide a precise diagnosis and develop corresponding treatment strategies in SCA. Our aim is to review the current status of diagnosis and treatment of SCA, and summarize the latest research advancement, including tumor subtype, molecular characteristics, diagnostic technology, and potential therapy strategies, thus deepening our understanding of this uncommon tumor type and providing guidance for accurate diagnosis and treatment.

Automated Determination of the H3 K27-Altered Status in Spinal Cord Diffuse Midline Glioma by Radiomics Based on T2-Weighted MR Images

BACKGROUND AND PURPOSE

Conventional MR imaging is not sufficient to discern the H3 K27-altered status of spinal cord diffuse midline glioma. This study aimed to develop a radiomics-based model based on preoperative T2WI to determine the H3 K27-altered status of spinal cord diffuse midline glioma.

MATERIALS AND METHODS

Ninety-seven patients with confirmed spinal cord diffuse midline gliomas were retrospectively recruited and randomly assigned to the training (n = 67) and test (n = 30) sets. One hundred seven radiomics features were initially extracted from automatically-segmented tumors on T2WI, then 11 features selected by the Pearson correlation coefficient and the Kruskal-Wallis test were used to train and test a logistic regression model for predicting the H3 K27-altered status. Sensitivity analysis was performed using additional random splits of the training and test sets, as well as applying other classifiers for comparison. The performance of the model was evaluated through its accuracy, sensitivity, specificity, and area under the curve. Finally, a prospective set including 28 patients with spinal cord diffuse midline gliomas was used to validate the logistic regression model independently.

RESULTS

The logistic regression model accurately predicted the H3 K27-altered status with accuracies of 0.833 and 0.786, sensitivities of 0.813 and 0.750, specificities of 0.857 and 0.833, and areas under the curve of 0.839 and 0.818 in the test and prospective sets, respectively. Sensitivity analysis confirmed the robustness of the model, with predictive accuracies of 0.767-0.833.

CONCLUSIONS

Radiomics signatures based on preoperative T2WI could accurately predict the H3 K27-altered status of spinal cord diffuse midline glioma, providing potential benefits for clinical management.

Independent Prognostic Factors and Nomogram Prediction of Cancer-Specific Survival in Postoperative Patients With Spinal Cord Astrocytoma

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

Spinal cord astrocytoma (SCA) is a rare central nervous system malignancy that typically requires early surgical intervention. However, the substantial frequency of relapse and bad outcomes limit the surgical advantage for patients. Herein, we aimed to determine the independent prognostic factors of cancer-specific survival (CSS) in post-surgical patients with primary SCA and to develop a new method to estimate the chances of CSS in these patients at 3-, 5- and 10-year.

METHODS

A total of 364 postoperative patients with SCA were recruited from the Surveillance, Epidemiology, and End Results database and randomly assigned to the training and validation sets. Univariate and multivariate Cox regression assessments were used to identify independent prognostic indicators. Second, a nomogram was established by integrating these indicators to estimate 3-, 5-, and 10-year CSS in patients with SCA who underwent surgery. Subsequently, the discriminatory power and predictive performance of the nomogram were assessed using the receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). Finally, a mortality risk stratification system was generated.

RESULTS

Age, tumor stage, histological type, and radiotherapy were recognized as potential predictive indicators of CSS for postoperative patients with SCA. The ROC curve and DCA indicate that the nomogram has good accuracy and high clinical utility. Furthermore, the mortality risk stratification system efficiently divides patients into 3 risk subgroups.

CONCLUSIONS

The nomogram could accurately anticipate the 3-, 5-, and 10-year percentages of CSS in postoperative patients with SCA. It could assist clinicians with personalized medical counseling, risk stratification management, and clinical decision-making, improving the clinical outcomes of these patients.