Survival, neurocognitive function, and health-related quality of life outcomes after rituximab-methotrexate, BCNU, teniposide, and prednisolone for primary CNS lymphoma: Final results of the HOVON 105/ALLG NHL 24 study

Diagnostics and treatment delay in primary central nervous system lymphoma: What the neurosurgeon should know

PURPOSE

The gold standard for diagnostics in primary central nervous system lymphoma (PCNSL) is histopathological diagnosis after stereotactic biopsy. Yet, PCNSL has a multidisciplinary diagnostic work up, which associated with diagnostic delay and could result in treatment delay. This article offers recommendations to neurosurgeons involved in clinical decision-making regarding (novel) diagnostics and care for patients with PCNSL with the aim to improve uniformity and timeliness of the diagnostic process for patients with PCNSL.

METHODS

We present a mini review to discuss the role of stereotactic biopsy in the context of novel developments in diagnostics for PCNSL, as well as the role for cytoreductive surgery.

RESULTS

Cerebrospinal fluid-based diagnostics are supplementary and cannot replace stereotactic biopsy-based diagnostics.

CONCLUSION

Histopathological diagnosis after stereotactic biopsy of the brain remains the gold standard for diagnosis. Additional diagnostics should not be a cause of diagnostic delay. There is currently no sufficient evidence supporting cytoreductive surgery in PCNSL, with recent studies showing contradictive data and suboptimal study designs.

Utility of contrast-enhanced MRI radiomics features combined with clinical indicators for predicting induction chemotherapy response in primary central nervous system lymphoma

PURPOSE

To assess the utility of combining contrast-enhanced magnetic resonance imaging (CE-MRI) radiomics features with clinical variables in predicting the response to induction chemotherapy (IC) for primary central nervous system lymphoma (PCNSL).

METHODS

A total of 131 patients with PCNSL (101 in the training set and 30 in the testing set) who had undergone contrast-enhanced MRI scans were retrospectively analyzed. Pyradiomics was utilized to extract radiomics features, and the clinical variables of the patients were gathered. Radiomics prediction models were developed using different combinations of feature selection methods and machine learning models, and the best combination was ultimately chosen. We screened clinical variables associated with treatment outcomes and developed clinical prediction models. The predictive performance of radiomics model, clinical model, and combined model, which integrates the best radiomics model and clinical characteristics, was independently assessed and compared using Receiver Operating Characteristic (ROC) curves.

RESULTS

In total, we extracted 1598 features. The best radiomics model we selected as the best utilized T-test and Recursive Feature Elimination (RFE) for feature selection and logistic regression for model building. Serum Interleukin 2 Receptor (IL-2R) and Eastern Cooperative Oncology Group (ECOG) Score were utilized to develop a clinical predictive model for assessing the response to induction chemotherapy. The results of the testing set revealed that the combined prediction model (radiomics and IL-2R) achieved the highest area under the ROC curve at 0.868 (0.683, 0.967), followed by the radiomics model at 0.857 (0.681, 0.957), and the clinical prediction model (IL-2R and ECOG) at 0.618 (0.413, 0.797). The combined model was significantly more accurate than the clinical model, with an AUC of 0.868 compared to 0.618 (P < 0.05). While the radiomics model had slightly better predictive power than the clinical model, this difference was not statistically significant (AUC, 0.857 vs. 0.618, P > 0.05).

CONCLUSIONS

Our prediction model, which combines radiomics signatures from CE-MRI with serum IL-2R, can effectively stratify patients with PCNSL before high-dose methotrexate (HD-MTX) -based chemotherapy.