Split and Merge Watershed: a two-step method for cell segmentation in fluorescence microscopy images.

The development of advanced techniques in medical imaging has allowed scanning of the human body to microscopic levels, making research on cell behavior more complex and more in-depth. Recent studies have focused on cellular heterogeneity since cell-to-cell differences are always present in the cell population and this variability contains valuable information. However, identifying each cell is not an easy task because, in the images acquired from the microscope, there are clusters of cells that are touching one another. Therefore, the segmentation stage is a problem of considerable difficulty in cell image processing. Although several methods for cell segmentation are described in the literature, they have drawbacks in terms of over-segmentation, under-segmentation or misidentification. Consequently, our main motivation in studying cell segmentation was to develop a new method to achieve a good tradeoff between accurately identifying all relevant elements and not inserting segmentation artifacts. This article presents a new method for cell segmentation in fluorescence microscopy images. The proposed approach combines the well-known Marker-Controlled Watershed algorithm (MC-Watershed) with a new, two-step method based on Watershed, Split and Merge Watershed (SM-Watershed): in the first step, or split phase, the algorithm identifies the clusters using inherent characteristics of the cell, such as size and convexity, and separates them using watershed. In the second step, or the merge stage, it identifies the over-segmented regions using proper features of the cells and eliminates the divisions. Before applying our two-step method, the input image is first preprocessed, and the MC-Watershed algorithm is used to generate an initial segmented image. However, this initial result may not be suitable for subsequent tasks, such as cell count or feature extraction, because not all cells are separated, and some cells may be mistakenly confused with the background. Thus, our proposal corrects this issue with its two-step process, reaching a high performance, a suitable tradeoff between over-segmentation and under-segmentation and preserving the shape of the cell, without the need of any labeled data or relying on machine learning processes. The latter is advantageous over state-of-the-art techniques that in order to achieve similar results require labeled data, which may not be available for all of the domains. Two cell datasets were used to validate this approach, and the results were compared with other methods in the literature, using traditional metrics and quality visual assessment. We obtained 90% of average visual accuracy and an F-index higher than 80%. This proposal outperforms other techniques for cell separation, achieving an acceptable balance between over-segmentation and under-segmentation, which makes it suitable for several applications in cell identification, such as virus infection analysis, high-content cell screening, drug discovery, and morphometry.

Analysis of facial expressions in parkinson's disease through video-based automatic methods.

BACKGROUND: The automatic analysis of facial expressions is an evolving field that finds several clinical applications. One of these applications is the study of facial bradykinesia in Parkinson's disease (PD), which is a major motor sign of this neurodegenerative illness. Facial bradykinesia consists in the reduction/loss of facial movements and emotional facial expressions called hypomimia. NEW METHOD: In this work we propose an automatic method for studying facial expressions in PD patients relying on video-based METHODS: 17 Parkinsonian patients and 17 healthy control subjects were asked to show basic facial expressions, upon request of the clinician and after the imitation of a visual cue on a screen. Through an existing face tracker, the Euclidean distance of the facial model from a neutral baseline was computed in order to quantify the changes in facial expressivity during the tasks. Moreover, an automatic facial expressions recognition algorithm was trained in order to study how PD expressions differed from the standard expressions. RESULTS: Results show that control subjects reported on average higher distances than PD patients along the tasks. COMPARISON WITH EXISTING METHODS: This confirms that control subjects show larger movements during both posed and imitated facial expressions. Moreover, our results demonstrate that anger and disgust are the two most impaired expressions in PD patients. CONCLUSIONS: Contactless video-based systems can be important techniques for analyzing facial expressions also in rehabilitation, in particular speech therapy, where patients could get a definite advantage from a real-time feedback about the proper facial expressions/movements to perform.

CSMMI: class-specific maximization of mutual information for action and gesture recognition.

In this paper, we propose a novel approach called class-specific maximization of mutual information (CSMMI) using a submodular method, which aims at learning a compact and discriminative dictionary for each class. Unlike traditional dictionary-based algorithms, which typically learn a shared dictionary for all of the classes, we unify the intraclass and interclass mutual information (MI) into an single objective function to optimize class-specific dictionary. The objective function has two aims: 1) maximizing the MI between dictionary items within a specific class (intrinsic structure) and 2) minimizing the MI between the dictionary items in a given class and those of the other classes (extrinsic structure). We significantly reduce the computational complexity of CSMMI by introducing an novel submodular method, which is one of the important contributions of this paper. This paper also contributes a state-of-the-art end-to-end system for action and gesture recognition incorporating CSMMI, with feature extraction, learning initial dictionary per each class by sparse coding, CSMMI via submodularity, and classification based on reconstruction errors. We performed extensive experiments on synthetic data and eight benchmark data sets. Our experimental results show that CSMMI outperforms shared dictionary methods and that our end-to-end system is competitive with other state-of-the-art approaches.

Acute leukemia classification by ensemble particle swarm model selection.

OBJECTIVE: Acute leukemia is a malignant disease that affects a large proportion of the world population. Different types and subtypes of acute leukemia require different treatments. In order to assign the correct treatment, a physician must identify the leukemia type or subtype. Advanced and precise methods are available for identifying leukemia types, but they are very expensive and not available in most hospitals in developing countries. Thus, alternative methods have been proposed. An option explored in this paper is based on the morphological properties of bone marrow images, where features are extracted from medical images and standard machine learning techniques are used to build leukemia type classifiers. METHODS AND MATERIALS: This paper studies the use of ensemble particle swarm model selection (EPSMS), which is an automated tool for the selection of classification models, in the context of acute leukemia classification. EPSMS is the application of particle swarm optimization to the exploration of the search space of ensembles that can be formed by heterogeneous classification models in a machine learning toolbox. EPSMS does not require prior domain knowledge and it is able to select highly accurate classification models without user intervention. Furthermore, specific models can be used for different classification tasks. RESULTS: We report experimental results for acute leukemia classification with real data and show that EPSMS outperformed the best results obtained using manually designed classifiers with the same data. The highest performance using EPSMS was of 97.68% for two-type classification problems and of 94.21% for more than two types problems. To the best of our knowledge, these are the best results reported for this data set. Compared with previous studies, these improvements were consistent among different type/subtype classification tasks, different features extracted from images, and different feature extraction regions. The performance improvements were statistically significant. We improved previous results by an average of 6% and there are improvements of more than 20% with some settings. In addition to the performance improvements, we demonstrated that no manual effort was required during acute leukemia type/subtype classification. CONCLUSIONS: Morphological classification of acute leukemia using EPSMS provides an alternative to expensive diagnostic methods in developing countries. EPSMS is a highly effective method for the automated construction of ensemble classifiers for acute leukemia classification, which requires no significant user intervention. EPSMS could also be used to address other medical classification tasks.