Dataset Information

Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation.

ABSTRACT: Background:Radiomics is a rapidly growing field in neuro-oncology, but studies have been limited to conventional MRI, and external validation is critically lacking. We evaluated technical feasibility, diagnostic performance, and generalizability of a diffusion radiomics model for identifying atypical primary central nervous system lymphoma (PCNSL) mimicking glioblastoma. Methods:A total of 1618 radiomics features were extracted from diffusion and conventional MRI from 112 patients (training set, 70 glioblastomas and 42 PCNSLs). Feature selection and classification were optimized using a machine-learning algorithm. The diagnostic performance was tested in 42 patients of internal and external validation sets. The performance was compared with that of human readers (2 neuroimaging experts), cerebral blood volume (90% histogram cutoff, CBV90), and apparent diffusion coefficient (10% histogram, ADC10) using the area under the receiver operating characteristic curve (AUC). Results:The diffusion radiomics was optimized with the combination of recursive feature elimination and a random forest classifier (AUC 0.983, stability 2.52%). In internal validation, the diffusion model (AUC 0.984) showed similar performance with conventional (AUC 0.968) or combined diffusion and conventional radiomics (AUC 0.984) and better than human readers (AUC 0.825-0.908), CBV90 (AUC 0.905), or ADC10 (AUC 0.787) in atypical PCNSL diagnosis. In external validation, the diffusion radiomics showed robustness (AUC 0.944) and performed better than conventional radiomics (AUC 0.819) and similar to combined radiomics (AUC 0.946) or human readers (AUC 0.896-0.930). Conclusion:The diffusion radiomics model had good generalizability and yielded a better diagnostic performance than conventional radiomics or single advanced MRI in identifying atypical PCNSL mimicking glioblastoma.

SUBMITTER: Kang D

PROVIDER: S-EPMC6071659 | biostudies-literature | 2018 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation.

Kang Daesung D Park Ji Eun JE Kim Young-Hoon YH Kim Jeong Hoon JH Oh Joo Young JY Kim Jungyoun J Kim Yikyung Y Kim Sung Tae ST Kim Ho Sung HS

Neuro-oncology 20180801 9

<h4>Background</h4>Radiomics is a rapidly growing field in neuro-oncology, but studies have been limited to conventional MRI, and external validation is critically lacking. We evaluated technical feasibility, diagnostic performance, and generalizability of a diffusion radiomics model for identifying atypical primary central nervous system lymphoma (PCNSL) mimicking glioblastoma.<h4>Methods</h4>A total of 1618 radiomics features were extracted from diffusion and conventional MRI from 112 patients ...[more]

PMID: 29438500

Similar Datasets

Project description:Lessons learnedThe findings from this study using monotherapy with pemetrexed in a pretreated patient population are, overall, encouraging. Unlike high-dose methotrexate, which requires several days of inpatient hospitalization, pemetrexed is relatively easy to administer in the outpatient setting and remains a viable treatment option in this patient population. The maximum tolerated dose of pemetrexed administered (900 mg/m2 every 2 weeks) was generally well tolerated and showed activity in patients with relapsed or refractory CNSL.BackgroundThere is currently no standard salvage treatment for patients with relapsed/refractory central nervous system (CNS) lymphoma (CNSL). We report the results of a phase I study of pemetrexed, an antifolate drug with broader activity than methotrexate (MTX). We provide the safety, tolerability, and maximum tolerated dose (MTD) of pemetrexed in patients with recurrent CNSL.MethodsThrough October 2015, 17 patients with relapsed/refractory CNSL received pemetrexed every 2 weeks with the first cohort receiving 600 mg/m2 and dose escalation in increments of 300 mg/m2 to a maximum of 1,200 mg/m2 . Three patients were to enroll at each dose level with expansion to six patients in the event of dose-limiting toxicity. Patients with both primary CNS lymphoma (PCNSL) and secondary CNS lymphoma (SCNSL) could be enrolled.ResultsSeventeen patients were evaluable with a median age of 63.7 years. Main adverse events included fatigue (82.4%), anemia (82.4%), and neutropenia (70.6%). The MTD was established at 900 mg/m2 . Dose-limiting toxicities were recorded in one patient in the 600 mg/m2 cohort and in two patients in the 1,200 mg/m2 cohort. Fourteen patients were evaluable for response assessment; 21.4% achieved a complete response, 35.7% had a partial response, 14.3% had stable disease, and 28.6% had progressive disease. The median progression-free survival was 4.2 months. The median overall survival was 44.5 months. In the original study protocol, the plan was to add an expansion cohort of six patients at MTD level. However, the first phase of the study was characterized by slow recruitment. Therefore, after achieving the primary objective of the study and establishing the MTD, the investigators decided to amend the protocol and to close the study.ConclusionPemetrexed administered at 900 mg/m2 every 2 weeks exhibits single-agent activity in patients with recurrent CNSL; it is well tolerated, and side effects are manageable.

Dataset Information

Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation.

Publications

Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets