Cargando…
A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features
Machine learning (ML) models have been shown to predict the presence of clinical factors from medical imaging with remarkable accuracy. However, these complex models can be difficult to interpret and are often criticized as “black boxes”. Prediction models that provide no insight into how their pred...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318445/ https://www.ncbi.nlm.nih.gov/pubmed/35890885 http://dx.doi.org/10.3390/s22145205 |
_version_ | 1784755292473393152 |
---|---|
author | Severn, Cameron Suresh, Krithika Görg, Carsten Choi, Yoon Seong Jain, Rajan Ghosh, Debashis |
author_facet | Severn, Cameron Suresh, Krithika Görg, Carsten Choi, Yoon Seong Jain, Rajan Ghosh, Debashis |
author_sort | Severn, Cameron |
collection | PubMed |
description | Machine learning (ML) models have been shown to predict the presence of clinical factors from medical imaging with remarkable accuracy. However, these complex models can be difficult to interpret and are often criticized as “black boxes”. Prediction models that provide no insight into how their predictions are obtained are difficult to trust for making important clinical decisions, such as medical diagnoses or treatment. Explainable machine learning (XML) methods, such as Shapley values, have made it possible to explain the behavior of ML algorithms and to identify which predictors contribute most to a prediction. Incorporating XML methods into medical software tools has the potential to increase trust in ML-powered predictions and aid physicians in making medical decisions. Specifically, in the field of medical imaging analysis the most used methods for explaining deep learning-based model predictions are saliency maps that highlight important areas of an image. However, they do not provide a straightforward interpretation of which qualities of an image area are important. Here, we describe a novel pipeline for XML imaging that uses radiomics data and Shapley values as tools to explain outcome predictions from complex prediction models built with medical imaging with well-defined predictors. We present a visualization of XML imaging results in a clinician-focused dashboard that can be generalized to various settings. We demonstrate the use of this workflow for developing and explaining a prediction model using MRI data from glioma patients to predict a genetic mutation. |
format | Online Article Text |
id | pubmed-9318445 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93184452022-07-27 A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features Severn, Cameron Suresh, Krithika Görg, Carsten Choi, Yoon Seong Jain, Rajan Ghosh, Debashis Sensors (Basel) Article Machine learning (ML) models have been shown to predict the presence of clinical factors from medical imaging with remarkable accuracy. However, these complex models can be difficult to interpret and are often criticized as “black boxes”. Prediction models that provide no insight into how their predictions are obtained are difficult to trust for making important clinical decisions, such as medical diagnoses or treatment. Explainable machine learning (XML) methods, such as Shapley values, have made it possible to explain the behavior of ML algorithms and to identify which predictors contribute most to a prediction. Incorporating XML methods into medical software tools has the potential to increase trust in ML-powered predictions and aid physicians in making medical decisions. Specifically, in the field of medical imaging analysis the most used methods for explaining deep learning-based model predictions are saliency maps that highlight important areas of an image. However, they do not provide a straightforward interpretation of which qualities of an image area are important. Here, we describe a novel pipeline for XML imaging that uses radiomics data and Shapley values as tools to explain outcome predictions from complex prediction models built with medical imaging with well-defined predictors. We present a visualization of XML imaging results in a clinician-focused dashboard that can be generalized to various settings. We demonstrate the use of this workflow for developing and explaining a prediction model using MRI data from glioma patients to predict a genetic mutation. MDPI 2022-07-12 /pmc/articles/PMC9318445/ /pubmed/35890885 http://dx.doi.org/10.3390/s22145205 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Severn, Cameron Suresh, Krithika Görg, Carsten Choi, Yoon Seong Jain, Rajan Ghosh, Debashis A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title | A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title_full | A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title_fullStr | A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title_full_unstemmed | A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title_short | A Pipeline for the Implementation and Visualization of Explainable Machine Learning for Medical Imaging Using Radiomics Features |
title_sort | pipeline for the implementation and visualization of explainable machine learning for medical imaging using radiomics features |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318445/ https://www.ncbi.nlm.nih.gov/pubmed/35890885 http://dx.doi.org/10.3390/s22145205 |
work_keys_str_mv | AT severncameron apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT sureshkrithika apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT gorgcarsten apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT choiyoonseong apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT jainrajan apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT ghoshdebashis apipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT severncameron pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT sureshkrithika pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT gorgcarsten pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT choiyoonseong pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT jainrajan pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures AT ghoshdebashis pipelinefortheimplementationandvisualizationofexplainablemachinelearningformedicalimagingusingradiomicsfeatures |