Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients

Abstract

Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of patients do not respond to HD–MTX-based chemotherapy (15–25%) or experience relapse (25–50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (p-value < 10−12). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.

Early MRI Predictors of Relapse in Primary Central Nervous System Lymphoma Treated with MATRix Immunochemotherapy

“…Longer-term follow up is planned to clarify in how far the candidate biomarkers relate to overall survival. Computational analysis of image data [31,42] could be explored as an adjunct for image-based outcome predictions though this would ideally benefit from large data sets for training.…”

Deep representation learning of tissue metabolome and computed tomography annotates NSCLC classification and prognosis

“…For the classification task, we selected a broad range of methods as suggested by previous studies. We used a cross-combination strategy to select the method with the best mean F1 score across the ten-fold validation 41 . The feature selection and classification task were performed using the scikit-learn package in Python 42 .…”

New hopes in relapsed refractory primary central nervous system lymphoma

“…Moreover, it is going to be largely accepted that more intensive treatment containing HD-MTX and HDT-ASCT could be administered by tailoring them to older patients [92]. Strictly linked to the concept of relapse prevention is the use of newer techniques, such as comprehensive genomic profiling, radiomics and artificial intelligence based approaches [93 ▪▪ ,94 ▪ ]. Indeed, molecular and radiological features merged with clinical data could potentially reveal new classification subgroups that might predict better risk and direct patients to newer and personalized therapeutic approaches [39 ▪▪ ,95 ▪ ].…”