Domain Adapted Multitask Learning for Segmenting Amoeboid Cells in Microscopy.

The method proposed in this paper is a robust combination of multi-task learning and unsupervised domain adaptation for segmenting amoeboid cells in microscopy. A highlight of this work is the manner in which the model's hyperparameters are estimated. The detriments of ad-hoc parameter estimation are well known, but this issue remains largely unaddressed in the context of CNN-based segmentation. Using a novel min-max formulation of the segmentation cost function our proposed method analytically estimates the model's hyperparameters, while simultaneously learning the CNN weights during training. This end-to-end framework provides a consolidated mechanism to harness the potential of multi-task learning to isolate and segment clustered cells from low contrast brightfield images, and it simultaneously leverages deep domain adaptation to segment fluorescent cells without explicit pixel-level re- annotation of the data. Experimental validations on multi-cellular images strongly suggest the effectiveness of the proposed technique, and our quantitative results show at least 15% and 10% improvement in cell segmentation on brightfield and fluorescence images respectively compared to contemporary supervised segmentation methods.

Evaluating the Stability of Spatial Keypoints via Cluster Core Correspondence Index.

Detection and analysis of informative keypoints is a fundamental problem in image analysis and computer vision. Keypoint detectors are omnipresent in visual automation tasks, and recent years have witnessed a significant surge in the number of such techniques. Evaluating the quality of keypoint detectors remains a challenging task owing to the inherent ambiguity over what constitutes a good keypoint. In this context, we introduce a reference based keypoint quality index which is based on the theory of spatial pattern analysis. Unlike traditional correspondence-based quality evaluation which counts the number of feature matches within a specified neighborhood, we present a rigorous mathematical framework to compute the statistical correspondence of the detections inside a set of salient zones (cluster cores) defined by the spatial distribution of a reference set of keypoints. We leverage the versatility of the level sets to handle hypersurfaces of arbitrary geometry, and develop a mathematical framework to estimate the model parameters analytically to reflect the robustness of a feature detection algorithm. Extensive experimental studies involving several keypoint detectors tested under different imaging scenarios demonstrate efficacy of our method to evaluate keypoint quality for generic applications in computer vision and image analysis.

Visual attraction in Drosophila larvae develops during a critical period and is modulated by crowding conditions.

The development of social behavior is poorly understood. Many animals adjust their behavior to environmental conditions based on a social context. Despite having relatively simple visual systems, Drosophila larvae are capable of identifying and are attracted to the movements of other larvae. Here, we show that Drosophila larval visual recognition is encoded by the movements of nearby larvae, experienced during a specific developmental critical period. Exposure to moving larvae, only during a specific period, is sufficient for later visual recognition of movement. Larvae exposed to wild-type body movements, during the critical period, are not attracted to the movements of tubby mutants, which have altered morphology. However, exposure to tubby, during the critical period, results in tubby recognition at the expense of wild-type recognition indicating that this is true learning. Visual recognition is not learned in excessively crowded conditions, and this is emulated by exposure, during the critical period, to food previously used by crowded larvae. We propose that Drosophila larvae have a distinct critical period, during which they assess both social and resource conditions, and that this irreversibly determines later visually guided social behavior. This model provides a platform towards understanding the regulation and development of social behavior.

Tubularity flow field--a technique for automatic neuron segmentation.

A segmentation framework is proposed to trace neurons from confocal microscopy images. With an increasing demand for high throughput neuronal image analysis, we propose an automated scheme to perform segmentation in a variational framework. Our segmentation technique, called tubularity flow field (TuFF) performs directional regional growing guided by the direction of tubularity of the neurites. We further address the problem of sporadic signal variation in confocal microscopy by designing a local attraction force field, which is able to bridge the gaps between local neurite fragments, even in the case of complete signal loss. Segmentation is performed in an integrated fashion by incorporating the directional region growing and the attraction force-based motion in a single framework using level sets. This segmentation is accomplished without manual seed point selection; it is automated. The performance of TuFF is demonstrated over a set of 2D and 3D confocal microscopy images where we report an improvement of >75% in terms of mean absolute error over three extensively used neuron segmentation algorithms. Two novel features of the variational solution, the evolution force and the attraction force, hold promise as contributions that can be employed in a number of image analysis applications.