TY - JOUR
T1 - Quantifying Uncertainty in Deep Learning of Radiologic Images
AU - Faghani, Shahriar
AU - Moassefi, Mana
AU - Rouzrokh, Pouria
AU - Khosravi, Bardia
AU - Baffour, Francis I.
AU - Ringler, Michael D.
AU - Erickson, Bradley J.
N1 - Publisher Copyright:
© 2023 Radiological Society of North America Inc.. All rights reserved.
PY - 2023/8
Y1 - 2023/8
N2 - In recent years, deep learning (DL) has shown impressive performance in radiologic image analysis. However, for a DL model to be useful in a real-world setting, its confidence in a prediction must also be known. Each DL model’s output has an estimated probability, and these estimated probabilities are not always reliable. Uncertainty represents the trustworthiness (validity) of estimated probabilities. The higher the uncertainty, the lower the validity. Uncertainty quantification (UQ) methods determine the uncertainty level of each prediction. Predictions made without UQ methods are generally not trustworthy. By implementing UQ in medical DL models, users can be alerted when a model does not have enough information to make a confident decision. Consequently, a medical expert could reevaluate the uncertain cases, which would eventually lead to gaining more trust when using a model. This review focuses on recent trends using UQ methods in DL radiologic image analysis within a conceptual framework. Also discussed in this review are potential applications, challenges, and future directions of UQ in DL radiologic image analysis.
AB - In recent years, deep learning (DL) has shown impressive performance in radiologic image analysis. However, for a DL model to be useful in a real-world setting, its confidence in a prediction must also be known. Each DL model’s output has an estimated probability, and these estimated probabilities are not always reliable. Uncertainty represents the trustworthiness (validity) of estimated probabilities. The higher the uncertainty, the lower the validity. Uncertainty quantification (UQ) methods determine the uncertainty level of each prediction. Predictions made without UQ methods are generally not trustworthy. By implementing UQ in medical DL models, users can be alerted when a model does not have enough information to make a confident decision. Consequently, a medical expert could reevaluate the uncertain cases, which would eventually lead to gaining more trust when using a model. This review focuses on recent trends using UQ methods in DL radiologic image analysis within a conceptual framework. Also discussed in this review are potential applications, challenges, and future directions of UQ in DL radiologic image analysis.
UR - http://www.scopus.com/inward/record.url?scp=85166394883&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85166394883&partnerID=8YFLogxK
U2 - 10.1148/RADIOL.222217
DO - 10.1148/RADIOL.222217
M3 - Review article
C2 - 37526541
AN - SCOPUS:85166394883
SN - 0033-8419
VL - 308
JO - Radiology
JF - Radiology
IS - 2
M1 - e222217
ER -