Semi-Linearized Proximal Alternating Minimization for a Discrete Mumford-Shah Model

Deep Learning Image Segmentation Based on Adaptive Total Variation Preprocessing

This article proposes a two-stage image segmentation method based on the MS model, aiming to enhance the segmentation accuracy of images with complex structure and background. In the first stage, in order to obtain the smooth approximate solution of the image by minimizing the energy functional, an anisotropic regularization term formed by the combination of the gradient operator and an adaptive weighted matrix is introduced. Different weights in both horizontal and vertical directions can be provided by the adaptive weighting matrix according to the gradient information, so that the curve diffuses along the directions of local feature tangents of the objects. In addition, information irrelevant to the image target can be filtered out by the adaptive weighting matrix, thus reducing the interference of complex background. The alternating direction method of multipliers (ADMMs) is employed to solve the convex optimization problem in the first stage. In the second stage, the smoothed image obtained in the first stage is segmented by the deep learning method. By comparing with some traditional methods and deep learning methods, the results demonstrate that not only has good perceptual quality been achieved by this segmentation method, but also superior evaluation metrics have been obtained.

Foveal feedback in perceptual processing: Contamination of neural representations and task difficulty effects

Visual object recognition was traditionally believed to rely on a hierarchical feedforward process. However, recent evidence challenges this notion by demonstrating the crucial role of foveal retinotopic cortex and feedback signals from higher-level visual areas in processing peripheral visual information. The nature of the information conveyed through foveal feedback remains a topic of debate. To address this, we conducted a study employing a foveal mask paradigm with varying stimulus-mask onset asynchronies in a peripheral same/different task, where peripheral objects exhibited different degrees of similarity. Our hypothesis posited that simultaneous arrival of feedback and mask information in the foveal cortex would lead to neural contamination, biasing perception. Notably, when the two peripheral objects were identical, we observed a significant increase in the number of "different" responses, peaking at approximately 100 ms. Similar effect was found when the objects were dissimilar, but with an overall later timing (around 150 ms). No significant difference was found when comparing easy (dissimilar objects) and difficult trials (similar objects). The findings challenge the hypothesis that foveation planning alone accounts for the observed effects. Instead, these and previous observations support the notion that the foveal cortex serves as a visual sketchpad for maintaining and manipulating task-relevant information.

Self-mentoring: A new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation

BACKGROUND

Accurate segmentation of microscopic structures such as bio-artificial capsules in microscopy imaging is a prerequisite to the computer-aided understanding of important biomechanical phenomenons. State-of-the-art segmentation performances are achieved by deep neural networks and related data-driven approaches. Training these networks from only a few annotated examples is challenging while producing manually annotated images that provide supervision is tedious.

METHOD

Recently, self-supervision, i.e. designing a neural pipeline providing synthetic or indirect supervision, has proved to significantly increase generalization performances of models trained on few shots. The objective of this paper is to introduce one such neural pipeline in the context of micro-capsule image segmentation. Our method leverages the rather simple content of these images so that a trainee network can be mentored by a referee network which has been previously trained on synthetically generated pairs of corrupted/correct region masks.

RESULTS

Challenging experimental setups are investigated. They involve from only 3 to 10 annotated images along with moderately large amounts of unannotated images. In a bio-artificial capsule dataset, our approach consistently and drastically improves accuracy. We also show that the learnt referee network is transferable to another Glioblastoma cell dataset and that it can be efficiently coupled with data augmentation strategies.

CONCLUSIONS

Experimental results show that very significant accuracy increments are obtained by the proposed pipeline, leading to the conclusion that the self-supervision mechanism introduced in this paper has the potential to replace human annotations.

Smoothed-NUV Priors for Imaging

Variations of L1 -regularization including, in particular, total variation regularization, have hugely improved computational imaging. However, sharper edges and fewer staircase artifacts can be achieved with convex-concave regularizers. We present a new class of such regularizers using normal priors with unknown variance (NUV), which include smoothed versions of the logarithm function and smoothed versions of Lp norms with p ≤ 1 . All NUV priors allow variational representations that lead to efficient algorithms for image reconstruction by iterative reweighted descent. A preferred such algorithm is iterative reweighted coordinate descent, which has no parameters (in particular, no step size to control) and is empirically robust and efficient. The proposed priors and algorithms are demonstrated with applications to tomography. We also note that the proposed priors come with built-in edge detection, which is demonstrated by an application to image segmentation.