Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations

Abstract

Gliomas are the most common primary malignant brain tumors in adults. Accurate grading is crucial as therapeutic strategies are often disparate for different grades and may influence patient prognosis. This study aims to provide an automated glioma grading platform on the basis of machine learning models. In this paper, we investigate contributions of multi-parameters from multimodal data including imaging parameters or features from the Whole Slide images (WSI) and the proliferation marker Ki-67 for automated brain tumor grading. For each WSI, we extract both visual parameters such as morphology parameters and sub-visual parameters including first-order and second-order features. On the basis of machine learning models, our platform classifies gliomas into grades II, III, and IV. Furthermore, we quantitatively interpret and reveal the important parameters contributing to grading with the Local Interpretable Model-Agnostic Explanations (LIME) algorithm. The quantitative analysis and explanation may assist clinicians to better understand the disease and accordingly to choose optimal treatments for improving clinical outcomes. The performance of our grading model was evaluated with cross-validation, which randomly divided the patients into non-overlapping training and testing sets and repeatedly validated the model on the different testing sets. The primary results indicated that this modular platform approach achieved the highest grading accuracy of 0.90 ± 0.04 with support vector machine (SVM) algorithm, with grading accuracies of 0.91 ± 0.08, 0.90 ± 0.08, and 0.90 ± 0.07 for grade II, III, and IV gliomas, respectively.

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

“…Second, one disadvantage of ML is that it is considered as a "black box" without a transparent interpretation of the learning process or the outputs, and the function between the clinical features and the response is invisible to the doctor (48). However, it is necessary for doctors to understand the reasons for the ML models to make such predictions in clinical settings and to provide expert knowledge-based validation for the interpretation of ML model outputs.…”

Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches

“…The study used an SVM model for multivariate integrative analysis of multiple image features to identify the signature. The features include the tumor's spatial distribution pattern leveraging a biophysical growth model (Akbari et al, 2018) and a distinct within-patient selfnormalized heterogeneity index (Wang et al, 2019). Mobadersany et al (2018) examined the application of deep learning techniques to predict outcomes in LGG and glioblastoma multiforme (GBM) patients.…”

Identification of the potential biomarkers in patients with glioma: a weighted gene co-expression network analysis

“…High-grade gliomas with a median overall survival of about 16–18 months can occur at any age. More importantly, there are challenges in distinguishing Grades II, III, and IV ( 4 ), and accurate grading is very important for the decision of patients’ treatment plan, which is related to the prognosis of patients ( 5 ). Although gliomas have made progress in diagnosis and treatment, but the survival rates of them in general is not optimistic, thus, the painstaking search for new treatments continues.…”