Trustworthy in silico cell labeling via ensemble-based image translation

Sara Imboden; Xuanqing Liu; Marie C Payne; Cho-Jui Hsieh; Neil Y C Lin

doi:10.1016/j.bpr.2023.100133

Trustworthy in silico cell labeling via ensemble-based image translation

Biophys Rep (N Y). 2023 Oct 18;3(4):100133. doi: 10.1016/j.bpr.2023.100133. eCollection 2023 Dec 13.

Authors

Sara Imboden¹, Xuanqing Liu², Marie C Payne¹, Cho-Jui Hsieh², Neil Y C Lin^{1

3

4

5

6

7}

Affiliations

¹ Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, Los Angeles, California.
² Department of Computer Science, University of California, Los Angeles, Los Angeles, California.
³ Department of Bioengineering, University of California, Los Angeles, Los Angeles, California.
⁴ Institute for Quantitative and Computational Biosciences, University of California, Los Angeles, Los Angeles, California.
⁵ California NanoSystems Institute, University of California, Los Angeles, Los Angeles, California.
⁶ Jonsson Comprehensive Cancer Center, University of California, Los Angeles, Los Angeles, California.
⁷ Broad Stem Cell Center, University of California, Los Angeles, Los Angeles, California.

Abstract

Artificial intelligence (AI) image translation has been a valuable tool for processing image data in biological and medical research. To apply such a tool in mission-critical applications, including drug screening, toxicity study, and clinical diagnostics, it is essential to ensure that the AI prediction is trustworthy. Here, we demonstrate that an ensemble learning method can quantify the uncertainty of AI image translation. We tested the uncertainty evaluation using experimentally acquired images of mesenchymal stromal cells. We find that the ensemble method reports a prediction standard deviation that correlates with the prediction error, estimating the prediction uncertainty. We show that this uncertainty is in agreement with the prediction error and Pearson correlation coefficient. We further show that the ensemble method can detect out-of-distribution input images by reporting increased uncertainty. Altogether, these results suggest that the ensemble-estimated uncertainty can be a useful indicator for identifying erroneous AI image translations.

Abstract

Grants and funding