A Novel Quality Control Algorithm for Medical Image Segmentation Based on Fuzzy Uncertainty

Deep learning methods have achieved an excellent performance in medical image segmentation. However, the practical application of deep learning-based segmentation models is limited in clinical settings due to the lack of reliable information about the segmentation quality. In this article, we propose a novel quality control algorithm based on fuzzy uncertainty to quantify the quality of the predicted segmentation results as part of the model inference process. First, test-time augmentation and Monte Carlo dropout are applied simultaneously to capture both the data and model uncertainties of the trained image segmentation model. Then, a fuzzy set is generated to describe the captured uncertainty with the assistance of the linear Euclidean distance transform algorithm. Finally, the fuzziness of the generated fuzzy set is adopted to calculate an image-level segmentation uncertainty and, therefore, to infer the segmentation quality. Extensive experiments using five medical image segmentation applications on the detection of skin lesion, nuclei, lung, breast, and cell are conducted to evaluate the proposed algorithm. The experimental results show that the estimated image-level uncertainties using the proposed method have strong correlations with the segmentation qualities measured by the Dice coefficient, resulting in absolute Pearson correlation coefficients of 0.60-0.92. Our method outperforms other five state-of-the-art quality control methods in classifying the segmentation results into good and poor quality groups (area under the receiver operating curve of greater than 0.92, while other methods are below 0.85).

Automated summary

In this article, a novel quality control algorithm based on fuzzy uncertainty is proposed to quantify the quality of deep learning-based segmentation results. Test-time augmentation and Monte Carlo dropout are used to capture data and model uncertainties, and a fuzzy set is generated to describe the captured uncertainty. The fuzziness of the generated fuzzy set is used to calculate image-level segmentation uncertainty and infer the segmentation quality.