Multi-label Inductive Matrix Completion for Joint MGMT and IDH1 Status Prediction for Glioma Patients

Abstract

MGMT promoter methylation and IDH1 mutation in high-grade gliomas (HGG) have proven to be the two important molecular indicators associated with better prognosis. Traditionally, the statuses of MGMT and IDH1 are obtained via surgical biopsy, which is laborious, invasive and time-consuming. Accurate presurgical prediction of their statuses based on preoperative imaging data is of great clinical value towards better treatment plan. In this paper, we propose a novel Multi-label Inductive Matrix Completion (MIMC) model, highlighted by the online inductive learning strategy, to jointly predict both MGMT and IDH1 statuses. Our MIMC model not only uses the training subjects with possibly missing MGMT/IDH1 labels, but also leverages the unlabeled testing subjects as a supplement to the limited training dataset. More importantly, we learn inductive labels, instead of directly using transductive labels, as the prediction results for the testing subjects, to alleviate the overfitting issue in small-sample-size studies. Furthermore, we design an optimization algorithm with guaranteed convergence based on the block coordinate descent method to solve the multivariate non-smooth MIMC model. Finally, by using a precious single-center multi-modality presurgical brain imaging and genetic dataset of primary HGG, we demonstrate that our method can produce accurate prediction results, outperforming the previous widely-used single- or multi-task machine learning methods. This study shows the promise of utilizing imaging-derived brain connectome phenotypes for prognosis of HGG in a non-invasive manner.

Multi-Label Nonlinear Matrix Completion With Transductive Multi-Task Feature Selection for Joint MGMT and IDH1 Status Prediction of Patient With High-Grade Gliomas

“…To validate the effectiveness of our proposed method, we have performed extensive experiments by also comparing with five different competing methods, including two widely-used classic methods (RF [57] and kernel Transductive SVM (TSVM) [58]) and three state-of-the-art matrix completion methods (MTMC [23], MIMC [27], and NTMC [32]). Table II summarizes the five competing methods and our proposed MNMC method with the characteristics of linear/nonlinear classification setting, inductive/transductive learning scheme, single-label/multi-label classification mode, and adaptive feature selection strategy.…”

“…As different subjects have different tumor locations, and the group-wise registration iteratively registers each subject to a group-averaged template gradually, the tumor effect (spatial misregistration) could be minimized. The registration quality was visually inspected by experts on MRI analysis (HZ, JL, and LL) with consensus [21], [27], [44]. One subject who have visible tumor-induced distortion in the registered T1 MRI were excluded from further study.…”

“…However, such a model is difficult to be generalized if a study has a limited sample size due to the increasing overfitting concern that many phenotypegenotype association studies may suffer. In order to address this challenge, in our preliminary work [27], we introduced an online inductive learning strategy into the conventional MTMC model, which resulted in a Multi-label Inductive Matrix Completion (MIMC) model for joint prediction of MGMT and IDH1 statuses. However, the MIMC model conducts transductive multi-task feature selection in a noisy feature space, rather than in a more ideal, noise-free feature space.…”

Putting the data before the algorithm in big data addressing personalized healthcare

“…Genome sequences, pathology slides, and radiology images have all been leveraged by inductive algorithms to derive novel relationships undiscovered by human interpretation alone. 38–40 It is likely not all derived relationships will be clinically impactful, as this approach also is susceptible to noncausal correlations. However, the hypothesis-generating capabilities of these methods have shown particular use for outputs with low prevalence, in which reductive thinking may be especially detrimental.…”

Assessing Versatile Machine Learning Models for Glioma Radiogenomic Studies across Hospitals

“…Some large public databases, such as The Cancer Imaging Archive (TCIA) GBM and LGG [ 6 ] or Repository of Molecular Brain Neoplasia Data (REMBRANDT) were published [ 11 ] in order to enhance radiogenomic studies targeting glioma. Many recent studies have applied a wide variety of machine learning (ML) methods from volumetric features to cutting-edge deep learning (DL) methods, in order to predict the grade and grouping of tumors [ 12 , 13 ], including IDH mutation [ 14 , 15 ], MGMT methylation status [ 16 , 17 , 18 , 19 , 20 , 21 ], survival [ 22 , 23 , 24 , 25 , 26 ], as well as other combinations of patient backgrounds [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ]. On the other hand, studies using local datasets showed significant diversity in prediction accuracy for the same prediction target.…”