Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations
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 m...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2018.01046/full |
| _version_ | 1818483174072647680 |
|---|---|
| author | Xiuying Wang Dingqian Wang Zhigang Yao Bowen Xin Bao Wang Chuanjin Lan Yejun Qin Shangchen Xu Dazhong He Yingchao Liu |
| author_facet | Xiuying Wang Dingqian Wang Zhigang Yao Bowen Xin Bao Wang Chuanjin Lan Yejun Qin Shangchen Xu Dazhong He Yingchao Liu |
| author_sort | Xiuying Wang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T11:56:51Z |
| format | Article |
| id | doaj.art-1ac91dff974c4000a7d21a6afdaacec7 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-10T11:56:51Z |
| publishDate | 2019-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-1ac91dff974c4000a7d21a6afdaacec72022-12-22T01:49:44ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2019-01-011210.3389/fnins.2018.01046432416Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result InterpretationsXiuying Wang0Dingqian Wang1Zhigang Yao2Bowen Xin3Bao Wang4Chuanjin Lan5Yejun Qin6Shangchen Xu7Dazhong He8Yingchao Liu9School of Information Technologies, The University of Sydney, Sydney, NSW, AustraliaSchool of Information Technologies, The University of Sydney, Sydney, NSW, AustraliaDepartment of Pathology, Provincial Hospital Affiliated to Shandong University, Jinan, ChinaSchool of Information Technologies, The University of Sydney, Sydney, NSW, AustraliaSchool of Medicine, Shandong University, Jinan, ChinaSchool of Medicine, Shandong University, Jinan, ChinaDepartment of Pathology, Provincial Hospital Affiliated to Shandong University, Jinan, ChinaDepartment of Neurosurgery, Provincial Hospital Affiliated to Shandong University, Jinan, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaDepartment of Neurosurgery, Provincial Hospital Affiliated to Shandong University, Jinan, ChinaGliomas 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.https://www.frontiersin.org/article/10.3389/fnins.2018.01046/fullglioma gradingmachine learningmorphological featuressupport vector machinedigital pathology images |
| spellingShingle | Xiuying Wang Dingqian Wang Zhigang Yao Bowen Xin Bao Wang Chuanjin Lan Yejun Qin Shangchen Xu Dazhong He Yingchao Liu Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations Frontiers in Neuroscience glioma grading machine learning morphological features support vector machine digital pathology images |
| title | Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations |
| title_full | Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations |
| title_fullStr | Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations |
| title_full_unstemmed | Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations |
| title_short | Machine Learning Models for Multiparametric Glioma Grading With Quantitative Result Interpretations |
| title_sort | machine learning models for multiparametric glioma grading with quantitative result interpretations |
| topic | glioma grading machine learning morphological features support vector machine digital pathology images |
| url | https://www.frontiersin.org/article/10.3389/fnins.2018.01046/full |
| work_keys_str_mv | AT xiuyingwang machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT dingqianwang machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT zhigangyao machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT bowenxin machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT baowang machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT chuanjinlan machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT yejunqin machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT shangchenxu machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT dazhonghe machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations AT yingchaoliu machinelearningmodelsformultiparametricgliomagradingwithquantitativeresultinterpretations |