Apparent diffusion coefficient as a valuable quantitative parameter for predicting clinical outcomes in patients with newly diagnosed primary CNS lymphoma

MRI-Based Machine Learning for Prediction of Clinical Outcomes in Primary Central Nervous System Lymphoma

A portion of individuals diagnosed with primary central nervous system lymphomas (PCNSL) may experience early relapse or refractory (R/R) disease following treatment. This research explored the potential of MRI-based radiomics in forecasting R/R cases in PCNSL. Forty-six patients with pathologically confirmed PCNSL diagnosed between January 2008 and December 2020 were included in this study. Only patients who underwent pretreatment brain MRIs and complete postoperative follow-up MRIs were included. Pretreatment contrast-enhanced T1WI, T2WI, and T2 FLAIR imaging were analyzed. A total of 107 radiomic features, including 14 shape-based, 18 first-order statistical, and 75 texture features, were extracted from each sequence. Predictive models were then built using five different machine learning algorithms to predict R/R in PCNSL. Of the included 46 PCNSL patients, 20 (20/46, 43.5%) patients were found to have R/R. In the R/R group, the median scores in predictive models such as support vector machine, k-nearest neighbors, linear discriminant analysis, naïve Bayes, and decision trees were significantly higher, while the apparent diffusion coefficient values were notably lower compared to those without R/R (p < 0.05). The support vector machine model exhibited the highest performance, achieving an overall prediction accuracy of 83%, a precision rate of 80%, and an AUC of 0.78. Additionally, when analyzing tumor progression, patients with elevated support vector machine and naïve Bayes scores demonstrated a significantly reduced progression-free survival (p < 0.05). These findings suggest that preoperative MRI-based radiomics may provide critical insights for treatment strategies in PCNSL.

Prognostic Assessment in Patients With Primary Diffuse Large B-Cell Lymphoma of the Central Nervous System Using MRI-Based Radiomics

BACKGROUND

Primary central nervous system lymphoma (PCNSL) carries a poor prognosis. Radiomics may hold potential value in prognostic assessment.

PURPOSE

To develop and validate an MRI-based radiomics model and combine it with clinical factors to assess progression-free survival (PFS) and overall survival (OS) of patients with PCNSL.

STUDY TYPE

Retrospective and prospective.

POPULATION

Three hundred seventy-nine patients (179 female, 53 ± 7 years) from 2014 to 2022.

FIELD STRENGTH/SEQUENCE

T2/fluid-attenuated inversion recovery, contrast-enhanced T1WI and diffusion-weighted echo-planar imaging sequences on 3.0 T.

ASSESSMENT

Radiomics features were extracted from enhanced tumor regions on preoperative multi-sequence MRI. Using a least absolute shrinkage and selection operator (LASSO) Cox regression model to select radiomic signatures in training cohort (N = 169). Cox proportional hazards models were constructed for clinical, radiomics, and combined models, with internal (N = 72) and external (N = 32) cohorts validating model performance.

STATISTICAL TESTS

Chi-squared, Mann-Whitney, Kaplan-Meier, log-rank, LASSO, Cox, decision curve analysis, time-dependent Receiver Operating Characteristic, area under the curve (AUC), and likelihood ratio test. P-value <0.05 was considered significant.

RESULTS

Follow-up duration was 28.79 ± 22.59 months (median: 25). High-risk patients, determined by the median radiomics score, showed significantly lower survival rates than low-risk patients. Compared with NCCN-IPI, conventional imaging and clinical models, the combined model achieved the highest C-index for both PFS (0.660 internal, 0.802 external) and OS (0.733 internal, 0.781 external) in validation. Net benefit was greater with radiomics than with clinical alone. The combined model exhibited performance with AUCs of 0.680, 0.752, and 0.830 for predicting 1-year, 3-year, and 5-year PFS, and 0.770, 0.789, and 0.863 for OS in internal validation, with PFS AUCs of 0.860 and 0.826 and OS AUCs of 0.859 and 0.748 for 1-year and 3-year survival in external validation.

DATA CONCLUSION

Incorporating a multi-sequence MR-based radiomics model into clinical models enhances the assess accuracy for the prognosis of PCNSL.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Extranodal lymphoma: pathogenesis, diagnosis and treatment

Approximately 30% of lymphomas occur outside the lymph nodes, spleen, or bone marrow, and the incidence of extranodal lymphoma has been rising in the past decade. While traditional chemotherapy and radiation therapy can improve survival outcomes for certain patients, the prognosis for extranodal lymphoma patients remains unsatisfactory. Extranodal lymphomas in different anatomical sites often have distinct cellular origins, pathogenic mechanisms, and clinical manifestations, significantly influencing their diagnosis and treatment. Therefore, it is necessary to provide a comprehensive summary of the pathogenesis, diagnosis, and treatment progress of extranodal lymphoma overall and specifically for different anatomical sites. This review summarizes the current progress in the common key signaling pathways in the development of extranodal lymphomas and intervention therapy. Furthermore, it provides insights into the pathogenesis, diagnosis, and treatment strategies of common extranodal lymphomas, including gastric mucosa-associated lymphoid tissue (MALT) lymphoma, mycosis fungoides (MF), natural killer/T-cell lymphoma (nasal type, NKTCL-NT), and primary central nervous system lymphoma (PCNSL). Additionally, as PCNSL is one of the extranodal lymphomas with the worst prognosis, this review specifically summarizes prognostic indicators and discusses the challenges and opportunities related to its clinical applications. The aim of this review is to assist clinical physicians and researchers in understanding the current status of extranodal lymphomas, enabling them to make informed clinical decisions that contribute to improving patient prognosis.

Pretreatment diffusion-weighted imaging for prediction of relapsed and refractory primary central nervous system lymphoma

Objectives

A subset of primary central nervous system lymphoma (PCNSL) has been shown to undergo an early relapsed/refractory (R/R) period after first-line chemotherapy. This study investigated the pretreatment clinical and MRI features to predict R/R in PCNSL, emphasizing the apparent diffusion coefficient (ADC) values in diffusion-weighted imaging (DWI).

Methods

This retrospective study investigated the pretreatment MRI features for predicting R/R in PCNSL. Only patients who had undergone complete preoperative and postoperative MRI follow-up studies were included. From January 2006 to December 2021, 52 patients from two medical institutions with a diagnosis of PCNSL were included (median follow-up time, 26.3 months). Among these, 24 (46.2%) had developed R/R (median time to relapse, 13 months). Cox proportional hazard regression analyses were performed to determine hazard ratios for all parameters.

Results

Significant predictors of R/R in PCNSL were female sex, complete response (CR) to first-line chemotherapy, and ADC value/ratio (p < 0.05). Cut-off points of ADC values and ADC ratios for prediction of R/R were 0.68 × 10-3 mm2/s and 0.97, with AUCs of 0.78 and 0.77, respectively (p < 0.05). Multivariate Cox proportional hazards analysis showed that failure of CR to first-line chemotherapy and low ADC values (<0.68 × 10-3 mm2/s) were significant risk factors for R/R, with hazard ratios of 5.22 and 14.45, respectively (p < 0.05). Kaplan-Meier analysis showed that lower ADC values and ratios predicted significantly shorter progression-free survival (p < 0.05).

Conclusion

Pretreatment ADC values in DWI offer quantitative valuable information for the treatment planning in PCNSL.

Neurosurgical Management of Central Nervous System Lymphoma: Lessons Learnt from a Neuro-Oncology Multidisciplinary Team Approach

Central nervous system lymphoma (CNSL) represents one of the most aggressive forms of extranodal lymphoma. The gold standard for CNSL diagnosis remains the stereotactic biopsy, with a limited role for cytoreductive surgery that has not been supported by historical data. Our study aims to provide a comprehensive overview of neurosurgery's role in the diagnosis of systemic relapsed and primary CNSL, with an emphasis on the impact on management and survival. This is a single center retrospective cohort study with data collected between August 2012 and August 2020, including patients referred with a potential diagnosis of CNSL to the local Neuro-oncology Multidisciplinary Team (MDT). The concordance between the MDT outcome and histopathological confirmation was assessed using diagnostic statistics. A Cox regression is used for overall survival (OS) risk factor analysis, and Kaplan-Meier statistics are performed for three prognostic models. The diagnosis of lymphoma is confirmed in all cases of relapsed CNSL, and in all but two patients who underwent neurosurgery. For the relapsed CNSL group, the highest positive predictive value (PPV) is found for an MDT outcome when lymphoma had been considered as single or topmost probable diagnosis. Neuro-oncology MDT has an important role in establishing the diagnosis in CNSL, not only to plan tissue diagnosis but also to stratify the surgical candidates. The MDT outcome based on history and imaging has good predictive value for cases where lymphoma is considered the most probable diagnosis, with the best prediction for cases of relapsed CNSL, questioning the need for invasive tissue diagnosis in the latter group.

Prognostic value of combined MTV and ADC derived from baseline FDG PET/MRI in aggressive non-Hodgkins lymphoma

PURPOSE

The aim of this prospective study was to investigate the prognostic value of metabolic tumor volume (MTV) and apparent diffusion coefficient (ADC) from baseline FDG PET/MRI compared to established clinical risk factors in terms of progression free survival (PFS) at 2 years in a cohort of diffuse large B-cell Lymphoma (DLBCL) and high-grade-B-cell lymphoma (HGBCL).

METHODS

Thirty-three patients and their baseline PET/MRI examinations were included. Images were read by two pairs of nuclear medicine physicians and radiologists for defining lymphoma lesions. MTV was computed on PET, and up to six lymphoma target lesions with restricted diffusion was defined for each PET/MRI examination. Minimum ADC (ADC_min) and the corresponding mean ADC (ADC_mean) from the target lesion with the lowest ADC_min were included in the analyses. For the combined PET/MRI parameters, the ratio between MTV and the target lesion with the lowest ADC_min (MTV/ADC_min) and the corresponding ADC_mean (MTV/ADC_mean) was calculated for each patient. Clinical, histological, and PET/MRI parameters were compared between the treatment failure and treatment response group, while survival analyses for each variable was performed by using univariate Cox regression. In case of significant variables in the Cox regression analyses, Kaplan-Meier survival analyses with log-rank test was used to study the effect of the variables on PFS.

RESULTS

ECOC PS scale ≥2 (p = 0.05) and ADC_mean (p = 0.05) were significantly different between the treatment failure group (n = 6) and those with treatment response (n = 27). Survival analyses showed that ADC_mean was associated with PFS (p = 0.02, [HR 2.3 for 1 SD increase]), while combining MTV and ADC did not predict outcome. In addition, ECOG PS ≥2 (p = 0.01, [HR 13.3]) and histology of HGBCL (p = 0.02 [HR 7.6]) was significantly associated with PFS.

CONCLUSIONS

ADC_mean derived from baseline MRI could be a prognostic imaging biomarker for DLBCL and HGBCL. Baseline staging with PET/MRI could therefore give supplementary prognostic information compared to today's standard PET/CT.

Prognostic factors in primary central nervous system lymphoma

PURPOSE OF REVIEW

Primary central nervous system lymphoma (PCNSL) is a rare and aggressive extranodal diffuse large B cell lymphoma. Despite its apparent immunopathological homogeneity, PCNSL displays a wide variability in outcome. Identifying prognostic factors is of importance for patient stratification and clinical decision-making. The purpose of this review is to focus on the clinical, neuroradiological and biological variables correlated with the prognosis at the time of diagnosis in immunocompetent patients.

RECENT FINDINGS

Age and performance status remain the most consistent clinical prognostic factors. The current literature suggests that neurocognitive dysfunction is an independent predictor of poor outcome. Cumulating data support the prognostic value of increased interleukin-10 level in the cerebrospinal fluid (CSF), in addition to its interest as a diagnostic biomarker. Advances in neuroimaging and in omics have identified several semi-quantitative radiological features (apparent diffusion restriction measures, dynamic contrast-enhanced perfusion MRI (pMRI) pattern and 18F-fluorodeoxyglucose metabolism) and molecular genetic alterations with prognostic impact in PCNSL.

SUMMARY

Validation of new biologic and neuroimaging markers in prospective studies is required before integrating future prognostic scoring systems. In the era of radiomic, large clinicoradiological and molecular databases are needed to develop multimodal artificial intelligence algorithms for the prediction of accurate outcome.

The Role of Pretherapeutic Diffusion-Weighted MR Imaging Derived Apparent Diffusion Coefficient in Predicting Clinical Outcomes in Immunocompetent Patients with Primary CNS Lymphoma: A Systematic Review and Meta-Analysis

OBJECTIVE

This systematic review and meta-analysis aimed to confirm the role of Apparent Diffusion Coefficient (ADC) values in predicting the prognosis of PCNSL patients based on previous studies.

METHODS

A systematic review with meta-analysis was conducted on related articles PubMed, Scopus, Sciencedirect, Cochrane, DOAJ, and Embase databases with last updated search on November 30, 2021. This systematic review and meta-analysis included a total of four studies.

RESULT

All studies that examined the association between pretherapeutic ADC values and OS and PFS discovered that lower ADC values were associated with significantly shorter OS and PFS. The analysis revealed that patients with low ADC values had a higher risk of death than those with high ADC values, with a pooled HR of 0.24 (95% CI: 0.10-0.56; Z = 3.26; p = 0.001). A meta-analysis of five data from three studies examining the association between ADC values and PFS was also conducted using a fixed-effects model due to the low heterogeneity values (I2 = 4%; p = 0.38). The data analysis revealed that the pooled HR was 0.25 (95% confidence interval [CI]: 0.14-0.44, Z = 4.18; p 0.00001).

CONCLUSION

Patients with low ADC values had significantly shorter overall survival and progression-free survival than those with high ADC values, so ADC values assessment prior to initial therapy administration can provide clinicians with valuable information about the prognosis of PCNSL.

Primary central nervous system lymphoma: a narrative review of ongoing clinical trials and goals for future studies

Primary central nervous system lymphoma (PCNSL) is a rare disease of the brain, spine, cerebrospinal fluid (CSF) and/or vitreoretinal space. PCNSL is chemo and radiosensitive but relapse is common even years after initial treatment. Outside of consensus regarding the use of high-dose methotrexate (HD-MTX) for first line treatment, there is little uniformity in the management of newly diagnosed or relapsed PCNSL. The lack of consensus is driven by a paucity of randomized trials in this disease. Prospective studies are troubled by low enrollment, the lack of a standard induction regimen, and a varied approach to consolidation strategies. Moreover, the PCNSL patient population is heterogeneous and includes a high proportion of elderly or frail patients and consists of patients manifesting disease in varied compartments of the central nervous system (CNS). As a result, current treatment strategies vary widely and are often dictated by physician and institutional preference or regional practice. This review provides an overview of recently completed and ongoing therapeutic studies for patients with newly diagnosed and recurrent or refractory PCNSL. It discusses the existing evidence behind common approaches to induction and consolidation or maintenance regimens as well as the recent data regarding management of recurrent disease. Finally, it highlights the complexity of trial design in this disease and provides a framework for the design of future studies, which are needed to identify patient populations likely to benefit from specific induction, consolidation, or maintenance therapies.