Toward confident prostate cancer detection using ultrasound: a multi-center study

Purpose: Deep learning-based analysis of micro-ultrasound images to detect cancerous lesions is a promising tool for improving prostate cancer (PCa) diagnosis. An ideal model should confidently identify cancer while responding with appropriate uncertainty when presented with out-of-distribution inputs that arise during deployment due to imaging artifacts and the biological heterogeneity of patients and prostatic tissue. Methods: Using micro-ultrasound data from 693 patients across 5 clinical centers who underwent micro-ultrasound guided prostate biopsy, we train and evaluate convolutional neural network models for PCa detection. To improve robustness to out-of-distribution inputs, we employ and comprehensively benchmark several state-of-the-art uncertainty estimation methods. Results: PCa detection models achieve performance scores up to <inline-formula id="IEq1"><alternatives><math><mrow><mn>76</mn><mo>%</mo></mrow></math><tex-math id="IEq1_TeX">\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$76\%$$\end{document}</tex-math><inline-graphic href="11548_2024_3119_Article_IEq1.gif"></inline-graphic></alternatives></inline-formula>average AUROC with a 10-fold cross validation setup. Models with uncertainty estimation obtain expected calibration error scores as low as <inline-formula id="IEq2"><alternatives><math><mrow><mn>2</mn><mo>%</mo></mrow></math><tex-math id="IEq2_TeX">\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2\%$$\end{document}</tex-math><inline-graphic href="11548_2024_3119_Article_IEq2.gif"></inline-graphic></alternatives></inline-formula>, indicating that confident predictions are very likely to be correct. Visualizations of the model output demonstrate that the model correctly identifies healthy versus malignant tissue. Conclusion: Deep learning models have been developed to confidently detect PCa lesions from micro-ultrasound. The performance of these models, determined from a large and diverse dataset, is competitive with visual analysis of magnetic resonance imaging, the clinical benchmark to identify PCa lesions for targeted biopsy. Deep learning with micro-ultrasound should be further studied as an avenue for targeted prostate biopsy.