Data valuation for medical imaging using Shapley value and application to a large-scale chest X-ray dataset
Autor: | Sameer Rehman, James Zou, Amirata Ghorbani, Daniel L. Rubin, Siyi Tang, Rikiya Yamashita, Jared Dunnmon |
---|---|
Rok vydání: | 2020 |
Předmět: |
0301 basic medicine
FOS: Computer and information sciences Diagnostic Imaging Computer Science - Machine Learning Computer science Science media_common.quotation_subject Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Datasets as Topic computer.software_genre Article 030218 nuclear medicine & medical imaging Machine Learning (cs.LG) Imaging Machine Learning 03 medical and health sciences 0302 clinical medicine Medical imaging FOS: Electrical engineering electronic engineering information engineering Image Processing Computer-Assisted Humans Quality (business) Reliability (statistics) Valuation (algebra) media_common Multidisciplinary Observational error Image and Video Processing (eess.IV) Pneumonia Electrical Engineering and Systems Science - Image and Video Processing Shapley value 030104 developmental biology Data quality Medicine Radiography Thoracic Data mining Metric (unit) Neural Networks Computer computer Algorithms |
Zdroj: | Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-9 (2021) |
ISSN: | 2045-2322 |
Popis: | The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous quality due to artifacts and biases arising from equipment or measurement errors. Therefore, algorithms that can automatically identify low quality data are highly desired. In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset. We characterized the effectiveness of data Shapley in identifying low quality versus valuable data for pneumonia detection. We found that removing training data with high Shapley values decreased the pneumonia detection performance, whereas removing data with low Shapley values improved the model performance. Furthermore, there were more mislabeled examples in low Shapley value data and more true pneumonia cases in high Shapley value data. Our results suggest that low Shapley value indicates mislabeled or poor quality images, whereas high Shapley value indicates data that are valuable for pneumonia detection. Our method can serve as a framework for using data Shapley to denoise large-scale medical imaging datasets. |
Databáze: | OpenAIRE |
Externí odkaz: |