Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods
Gliomas are tumors of the central nervous system, which usually start within the glial cells of the brain or the spinal cord. These are extremely migratory and diffusive tumors, which quickly expand to the surrounding regions in the brain. There are different grades of gliomas, hinting about their g...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/20/10357 |
_version_ | 1797475656010825728 |
---|---|
author | Faisal Altaf Rathore Hafiz Saad Khan Hafiz Mudassar Ali Marwa Obayya Saim Rasheed Lal Hussain Zaki Hassan Kazmi Mohamed K. Nour Abdullah Mohamed Abdelwahed Motwakel |
author_facet | Faisal Altaf Rathore Hafiz Saad Khan Hafiz Mudassar Ali Marwa Obayya Saim Rasheed Lal Hussain Zaki Hassan Kazmi Mohamed K. Nour Abdullah Mohamed Abdelwahed Motwakel |
author_sort | Faisal Altaf Rathore |
collection | DOAJ |
description | Gliomas are tumors of the central nervous system, which usually start within the glial cells of the brain or the spinal cord. These are extremely migratory and diffusive tumors, which quickly expand to the surrounding regions in the brain. There are different grades of gliomas, hinting about their growth patterns and aggressiveness and potential response to the treatment. As part of routine clinical procedure for gliomas, both radiology images (rad), such as multiparametric MR images, and digital pathology images (path) from tissue samples are acquired. Each of these data streams are used separately for prediction of the survival outcome of gliomas, however, these images provide complimentary information, which can be used in an integrated way for better prediction. There is a need to develop an image-based method that can utilise the information extracted from these imaging sequences in a synergistic way to predict patients’ outcome and to potentially assist in building comprehensive and patient-centric treatment plans. The objective of this study is to improve survival prediction outcomes of gliomas by integrating radiology and pathology imaging. Multiparametric magnetic resonance imaging (MRI), rad images, and path images of glioma patients were acquired from The Cancer Imaging Archive. Quantitative imaging features were extracted from tumor regions in rad and path images. The features were given as input to an ensemble regression machine learning pipeline, including support vector regression, AdaBoost, gradient boost, and random forest. The performance of the model was evaluated in several configurations, including leave-one-out, five-fold cross-validation, and split-train-test. Moreover, the quantitative performance evaluations were conducted separately in the complete cohort (<i>n</i> = 171), high-grade gliomas (HGGs), <i>n</i> = 75, and low-grade gliomas (LGGs), <i>n</i> = 96. The combined rad and path features outperformed individual feature types in all the configurations and datasets. In leave-one-out configuration, the model comprising both rad and path features was successfully validated on the complete dataset comprising HGFs and LGGs (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mo>=</mo><mn>0.84</mn><mo> </mo><mi>p</mi><mo>=</mo><mn>2.2</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>16</mn></mrow></msup></mrow></semantics></math></inline-formula>). The Kaplan–Meier curves generated on the predictions of the proposed model yielded a hazard ratio of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.314</mn><mo> </mo><mrow><mo>[</mo><mrow><mn>95</mn><mo>%</mo><mi>C</mi><mi>I</mi><mo>:</mo><mn>1.718</mn><mo>−</mo><mn>6.394</mn></mrow><mo>]</mo></mrow><mo>,</mo><mo> </mo><mi>l</mi><mi>o</mi><mi>g</mi><mo>−</mo><mi>r</mi><mi>a</mi><mi>n</mi><mi>k</mi><mrow><mo>(</mo><mi>P</mi><mo>)</mo></mrow><mo>=</mo><mn>2</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula> on combined rad and path features. Conclusion: The proposed approach emphasizes radiology experts and pathology experts’ clinical workflows by creating prognosticators upon ‘rad’ radiology images and digital pathology ‘path’ images independently, as well as combining the power of both, also through delivering integrated analysis, that can contribute to a collaborative attempt between different departments for administration of patients with gliomas. |
first_indexed | 2024-03-09T20:47:13Z |
format | Article |
id | doaj.art-f7b9faa38bcf4f8e8200a1987d832a0d |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T20:47:13Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-f7b9faa38bcf4f8e8200a1987d832a0d2023-11-23T22:43:25ZengMDPI AGApplied Sciences2076-34172022-10-0112201035710.3390/app122010357Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression MethodsFaisal Altaf Rathore0Hafiz Saad Khan1Hafiz Mudassar Ali2Marwa Obayya3Saim Rasheed4Lal Hussain5Zaki Hassan Kazmi6Mohamed K. Nour7Abdullah Mohamed8Abdelwahed Motwakel9Department of Computer Science and Information Technology, University of Azad Jammu and Kashmir, Muzaffarabad 13100, Azad Kashmir, PakistanKidney Centre Bahawal Victoria Hospital Bahawalpur, Bahawalpur 63100, Punjab, PakistanRural Health Center (RHC) Roda, District Khushab, Khushab 41021, Punjab, PakistanDepartment of Biomedical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Information Technology, Faculty of Computing and IT, King Abdulaziz University, Jeddah 21589, Saudi ArabiaDepartment of Computer Science and Information Technology, University of Azad Jammu and Kashmir, Muzaffarabad 13100, Azad Kashmir, PakistanDepartment of Computer Science and Information Technology, University of Azad Jammu and Kashmir, Muzaffarabad 13100, Azad Kashmir, PakistanDepartment of Computer Science, College of Computing and Information System, Umm Al-Qura University, Mecca 24382, Saudi ArabiaResearch Centre, Future University in Egypt, New Cairo 11845, EgyptDepartment of Computer and Self Development, Preparatory Year Deanship, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi ArabiaGliomas are tumors of the central nervous system, which usually start within the glial cells of the brain or the spinal cord. These are extremely migratory and diffusive tumors, which quickly expand to the surrounding regions in the brain. There are different grades of gliomas, hinting about their growth patterns and aggressiveness and potential response to the treatment. As part of routine clinical procedure for gliomas, both radiology images (rad), such as multiparametric MR images, and digital pathology images (path) from tissue samples are acquired. Each of these data streams are used separately for prediction of the survival outcome of gliomas, however, these images provide complimentary information, which can be used in an integrated way for better prediction. There is a need to develop an image-based method that can utilise the information extracted from these imaging sequences in a synergistic way to predict patients’ outcome and to potentially assist in building comprehensive and patient-centric treatment plans. The objective of this study is to improve survival prediction outcomes of gliomas by integrating radiology and pathology imaging. Multiparametric magnetic resonance imaging (MRI), rad images, and path images of glioma patients were acquired from The Cancer Imaging Archive. Quantitative imaging features were extracted from tumor regions in rad and path images. The features were given as input to an ensemble regression machine learning pipeline, including support vector regression, AdaBoost, gradient boost, and random forest. The performance of the model was evaluated in several configurations, including leave-one-out, five-fold cross-validation, and split-train-test. Moreover, the quantitative performance evaluations were conducted separately in the complete cohort (<i>n</i> = 171), high-grade gliomas (HGGs), <i>n</i> = 75, and low-grade gliomas (LGGs), <i>n</i> = 96. The combined rad and path features outperformed individual feature types in all the configurations and datasets. In leave-one-out configuration, the model comprising both rad and path features was successfully validated on the complete dataset comprising HGFs and LGGs (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mo>=</mo><mn>0.84</mn><mo> </mo><mi>p</mi><mo>=</mo><mn>2.2</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>16</mn></mrow></msup></mrow></semantics></math></inline-formula>). The Kaplan–Meier curves generated on the predictions of the proposed model yielded a hazard ratio of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.314</mn><mo> </mo><mrow><mo>[</mo><mrow><mn>95</mn><mo>%</mo><mi>C</mi><mi>I</mi><mo>:</mo><mn>1.718</mn><mo>−</mo><mn>6.394</mn></mrow><mo>]</mo></mrow><mo>,</mo><mo> </mo><mi>l</mi><mi>o</mi><mi>g</mi><mo>−</mo><mi>r</mi><mi>a</mi><mi>n</mi><mi>k</mi><mrow><mo>(</mo><mi>P</mi><mo>)</mo></mrow><mo>=</mo><mn>2</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula> on combined rad and path features. Conclusion: The proposed approach emphasizes radiology experts and pathology experts’ clinical workflows by creating prognosticators upon ‘rad’ radiology images and digital pathology ‘path’ images independently, as well as combining the power of both, also through delivering integrated analysis, that can contribute to a collaborative attempt between different departments for administration of patients with gliomas.https://www.mdpi.com/2076-3417/12/20/10357survival predictionradiology images (rad)digital pathology images (path)magnetic resonance imaging (MRI)whole slide images (WSI)region of interest (ROI) |
spellingShingle | Faisal Altaf Rathore Hafiz Saad Khan Hafiz Mudassar Ali Marwa Obayya Saim Rasheed Lal Hussain Zaki Hassan Kazmi Mohamed K. Nour Abdullah Mohamed Abdelwahed Motwakel Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods Applied Sciences survival prediction radiology images (rad) digital pathology images (path) magnetic resonance imaging (MRI) whole slide images (WSI) region of interest (ROI) |
title | Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods |
title_full | Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods |
title_fullStr | Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods |
title_full_unstemmed | Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods |
title_short | Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods |
title_sort | survival prediction of glioma patients from integrated radiology and pathology images using machine learning ensemble regression methods |
topic | survival prediction radiology images (rad) digital pathology images (path) magnetic resonance imaging (MRI) whole slide images (WSI) region of interest (ROI) |
url | https://www.mdpi.com/2076-3417/12/20/10357 |
work_keys_str_mv | AT faisalaltafrathore survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT hafizsaadkhan survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT hafizmudassarali survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT marwaobayya survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT saimrasheed survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT lalhussain survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT zakihassankazmi survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT mohamedknour survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT abdullahmohamed survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods AT abdelwahedmotwakel survivalpredictionofgliomapatientsfromintegratedradiologyandpathologyimagesusingmachinelearningensembleregressionmethods |