R. J. G. van Sloun

M. M. A. Valiuddin, R. J. G. van Sloun, C. G. A. Viviers et al.

Advances in architectural design, data availability, and compute have driven remarkable progress in semantic segmentation. Yet, these models often rely on relaxed Bayesian assumptions, omitting critical uncertainty information needed for robust decision-making. The resulting reliance on point estimates has fueled interest in probabilistic segmentation, but the literature remains fragmented. In response, this review consolidates and contextualizes foundational concepts in uncertainty modeling, including the non-trivial task of distinguishing between epistemic and aleatoric uncertainty and examining their roles across four key downstream segmentation tasks, highlighting Active Learning as particularly promising. By unifying theory, terminology, and applications, we provide a coherent foundation for researchers and identify critical challenges, such as strong assumptions in spatial aggregation, lack of standardized benchmarks, and pitfalls in current uncertainty quantification methods. We identify trends such as the adoption of contemporary generative models, driven by advances in the broader field of generative modeling, with segmentation-specific innovation primarily in the conditioning mechanisms. Moreover, we observe growing interest in distribution- and sampling-free approaches to uncertainty estimation. We further propose directions for advancing uncertainty-aware segmentation in deep learning, including pragmatic strategies for disentangling different sources of uncertainty, novel uncertainty modeling approaches and improved Transformer-based backbones. In this way, we aim to support the development of more reliable, efficient, and interpretable segmentation models that effectively incorporate uncertainty into real-world applications.

M. M. A. Valiuddin, C. G. A. Viviers, R. J. G. van Sloun et al.

Quantifying uncertainty in medical image segmentation applications is essential, as it is often connected to vital decision-making. Compelling attempts have been made in quantifying the uncertainty in image segmentation architectures, e.g. to learn a density segmentation model conditioned on the input image. Typical work in this field restricts these learnt densities to be strictly Gaussian. In this paper, we propose to use a more flexible approach by introducing Normalizing Flows (NFs), which enables the learnt densities to be more complex and facilitate more accurate modeling for uncertainty. We prove this hypothesis by adopting the Probabilistic U-Net and augmenting the posterior density with an NF, allowing it to be more expressive. Our qualitative as well as quantitative (GED and IoU) evaluations on the multi-annotated and single-annotated LIDC-IDRI and Kvasir-SEG segmentation datasets, respectively, show a clear improvement. This is mostly apparent in the quantification of aleatoric uncertainty and the increased predictive performance of up to 14 percent. This result strongly indicates that a more flexible density model should be seriously considered in architectures that attempt to capture segmentation ambiguity through density modeling. The benefit of this improved modeling will increase human confidence in annotation and segmentation, and enable eager adoption of the technology in practice.

R. R. Wildeboer, R. J. G. van Sloun, C. K. Mannaerts et al.

Shear-wave elastography (SWE) permits local estimation of tissue elasticity, an important imaging marker in biomedicine. This recently-developed, advanced technique assesses the speed of a laterally-travelling shear wave after an acoustic radiation force "push" to estimate local Young's moduli in an operator-independent fashion. In this work, we show how synthetic SWE (sSWE) images can be generated based on conventional B-mode imaging through deep learning. Using side-by-side-view B-mode/SWE images collected in 50 patients with prostate cancer, we show that sSWE images with a pixel-wise mean absolute error of 4.5+/-0.96 kPa with regard to the original SWE can be generated. Visualization of high-level feature levels through t-Distributed Stochastic Neighbor Embedding reveals substantial overlap between data from two different scanners. Qualitatively, we examined the use of the sSWE methodology for B-mode images obtained with a scanner without SWE functionality. We also examined the use of this type of network in elasticity imaging in the thyroid. Limitations of the technique reside in the fact that networks have to be retrained for different organs, and that the method requires standardization of the imaging settings and procedure. Future research will be aimed at development of sSWE as an elasticity-related tissue typing strategy that is solely based on B-mode ultrasound acquisition, and the examination of its clinical utility.