IEEE Trans Pattern Anal Mach Intell. 2022 May;44(5):2346-2357. doi: 10.1109/TPAMI.2020.3039745. Epub 2022 Apr 1.
Advances in the image-based diagnostics of complex biological and manufacturing processes have brought unsupervised image segmentation to the forefront of enabling automated, on the fly decision making. However, most existing unsupervised segmentation approaches are either computationally complex or require manual parameter selection (e.g., flow capacities in max-flow/min-cut segmentation). In this work, we present a fully unsupervised segmentation approach using a continuous max-flow formulation over the image domain while optimally estimating the flow parameters from the image characteristics. More specifically, we show that the maximum a posteriori estimate of the image labels can be formulated as a continuous max-flow problem given the flow capacities are known. The flow capacities are then iteratively obtained by employing a novel Markov random field prior over the image domain. We present theoretical results to establish the posterior consistency of the flow capacities. We compare the performance of our approach using brain tumor image segmentation, defect identification in additively manufactured components using electron microscopic images, and segmentation of multiple real-world images. Comparative results with several state-of-the-art supervised as well as unsupervised methods suggest that the present method performs statistically similar to the supervised methods, but results in more than 90 percent improvement in the Dice score when compared to the state-of-the-art unsupervised methods.
基于图像的复杂生物和制造过程的诊断技术的进步使得无监督图像分割成为实现自动化、实时决策的前沿技术。然而，大多数现有的无监督分割方法要么计算复杂，要么需要手动参数选择（例如，最大流/最小割分割中的流容量）。在这项工作中，我们提出了一种完全无监督的分割方法，使用图像域上的连续最大流公式，同时从图像特征中最优地估计流参数。具体来说，我们表明，在已知流容量的情况下，可以将图像标签的最大后验估计公式化为连续最大流问题。然后，通过在图像域上采用新颖的马尔可夫随机场先验，迭代地获得流容量。我们提出了理论结果来建立流容量的后验一致性。我们使用脑肿瘤图像分割、电子显微镜图像中增材制造组件的缺陷识别以及多个真实世界图像的分割来比较我们方法的性能。与几种最先进的监督和无监督方法的比较结果表明，该方法在统计学上与监督方法相似，但与最先进的无监督方法相比，Dice 评分提高了 90%以上。
