Semi-supervised COVID-19 volumetric pulmonary lesion estimation on CT images using probabilistic active contour and CNN segmentation.

Purpose: A semi-supervised two-step methodology is proposed to obtain a volumetric estimation of COVID-19-related lesions on Computed Tomography (CT) images. Methods: First, damaged tissue was segmented from CT images using a probabilistic active contours approach. Second, lung parenchyma was extracted using a previously trained U-Net. Finally, volumetric estimation of COVID-19 lesions was calculated considering the lung parenchyma masks.Our approach was validated using a publicly available dataset containing 20 CT COVID-19 images previously labeled and manually segmented. Then, it was applied to 295 COVID-19 patients CT scans admitted to an intensive care unit. We compared the lesion estimation between deceased and survived patients for high and low-resolution images. Results: A comparable median Dice similarity coefficient of 0.66 for the 20 validation images was achieved. For the 295 images dataset, results show a significant difference in lesion percentages between deceased and survived patients, with a p-value of 9.1 × 10-4 in low-resolution and 5.1 × 10-5 in high-resolution images. Furthermore, the difference in lesion percentages between high and low-resolution images was 10 % on average. Conclusion: The proposed approach could help estimate the lesion size caused by COVID-19 in CT images and may be considered an alternative to getting a volumetric segmentation for this novel disease without the requirement of large amounts of COVID-19 labeled data to train an artificial intelligence algorithm. The low variation between the estimated percentage of lesions in high and low-resolution CT images suggests that the proposed approach is robust, and it may provide valuable information to differentiate between survived and deceased patients.

Optimising adjacent membrane segmentation and parameterisation in multicellular aggregates by piecewise active contours.

In fluorescence microscopy imaging, the segmentation of adjacent cell membranes within cell aggregates, multicellular samples, tissue, organs, or whole organisms remains a challenging task. The lipid bilayer is a very thin membrane when compared to the wavelength of photons in the visual spectra. Fluorescent molecules or proteins used for labelling membranes provide a limited signal intensity, and light scattering in combination with sample dynamics during in vivo imaging lead to poor or ambivalent signal patterns that hinder precise localisation of the membrane sheets. In the proximity of cells, membranes approach and distance each other. Here, the presence of membrane protrusions such as blebs; filopodia and lamellipodia; microvilli; or membrane vesicle trafficking, lead to a plurality of signal patterns, and the accurate localisation of two adjacent membranes becomes difficult. Several computational methods for membrane segmentation have been introduced. However, few of them specifically consider the accurate detection of adjacent membranes. In this article we present ALPACA (ALgorithm for Piecewise Adjacent Contour Adjustment), a novel method based on 2D piecewise parametric active contours that allows: (i) a definition of proximity for adjacent contours, (ii) a precise detection of adjacent, nonadjacent, and overlapping contour sections, (iii) the definition of a polyline for an optimised shared contour within adjacent sections and (iv) a solution for connecting adjacent and nonadjacent sections under the constraint of preserving the inherent cell morphology. We show that ALPACA leads to a precise quantification of adjacent and nonadjacent membrane zones in regular hexagons and live image sequences of cells of the parapineal organ during zebrafish embryo development. The algorithm detects and corrects adjacent, nonadjacent, and overlapping contour sections within a selected adjacency distance d, calculates shared contour sections for neighbouring cells with minimum alterations of the contour characteristics, and presents piecewise active contour solutions, preserving the contour shape and the overall cell morphology. ALPACA quantifies adjacent contours and can improve the meshing of 3D surfaces, the determination of forces, or tracking of contours in combination with previously published algorithms. We discuss pitfalls, strengths, and limits of our approach, and present a guideline to take the best decision for varying experimental conditions for in vivo microscopy.

Evaluating geodesic active contours in microcalcifications segmentation on mammograms.

Breast cancer is the most commonly occurring type of cancer among women, and it is the major cause of female cancer-related deaths worldwide. Its incidence is increasing in developed as well as developing countries. Efficient strategies to reduce the high death rates due to breast cancer include early detection and tumor removal in the initial stages of the disease. Clinical and mammographic examinations are considered the best methods for detecting the early signs of breast cancer; however, these techniques are highly dependent on breast characteristics, equipment quality, and physician experience. Computer-aided diagnosis (CADx) systems have been developed to improve the accuracy of mammographic diagnosis; usually such systems may involve three steps: (i) segmentation; (ii) parameter extraction and selection of the segmented lesions and (iii) lesions classification. Literature considers the first step as the most important of them, as it has a direct impact on the lesions characteristics that will be used in the further steps. In this study, the original contribution is a microcalcification segmentation method based on the geodesic active contours (GAC) technique associated with anisotropic texture filtering as well as the radiologists' knowledge. Radiologists actively participate on the final step of the method, selecting the final segmentation that allows elaborating an adequate diagnosis hypothesis with the segmented microcalcifications presented in a region of interest (ROI). The proposed method was assessed by employing 1000 ROIs extracted from images of the Digital Database for Screening Mammography (DDSM). For the selected ROIs, the rate of adequately segmented microcalcifications to establish a diagnosis hypothesis was at least 86.9%, according to the radiologists. The quantitative test, based on the area overlap measure (AOM), yielded a mean of 0.52±0.20 for the segmented images, when all 2136 segmented microcalcifications were considered. Moreover, a statistical difference was observed between the AOM values for large and small microcalcifications. The proposed method had better or similar performance as compared to literature for microcalcifications with maximum diameters larger than 460µm. For smaller microcalcifications the performance was limited.

Segmentação automática 2D de vias aéreas em imagens de tomografia computadorizada do tórax / Automatic 2D segmentation of airways in thorax computed tomography images

INTRODUÇÃO: Grande parte da população mundial é afetada por doenças pulmonares, como é o caso das broncopatias constituídas pela asma, bronquiectasia e a bronquite. O diagnóstico de broncopatias é baseado no estado das vias aéreas. Neste sentido, a segmentação automática das vias aéreas em imagens de Tomografia Computadorizada (TC) do tórax é uma etapa fundamental para auxílio ao diagnóstico dessas doenças. MÉTODOS: O presente trabalho avalia algoritmos e desenvolve métodos de segmentação automática das vias aéreas 2D. Tais métodos são compostos por algoritmos de detecção de vias aéreas, sendo estes rede neural Multilayer Perceptron (MLP) e Análise de Densidades Pulmonares (ADP), e por algoritmos de segmentação de vias aéreas, sendo estes Crescimento de Região (CR), Método de Contornos Ativos (MCA) Balão e Topológico Adaptativo. RESULTADOS: Os resultados foram obtidos em três etapas: análise comparativa entre os algoritmos de detecção MLP e ADP, com um padrão-ouro adquirido por três médicos com expertise em imagens de TC do tórax; análise comparativa entre algoritmos de segmentação MCA balão, MCA topológico adaptativo, MLP e CR; e avaliação das possíveis combinações entre os algoritmos de detecção e segmentação, resultando no método completo para segmentação automática das vias aéreas em 2D. CONCLUSÃO: A baixa incidência de falso-negativo e a redução significativa de falso-positivo, resulta em coeficiente de similaridade e sensibilidade superior a 91% e 87% respectivamente, para uma combinação dos algoritmos, com qualidade de segmentação satisfatória.

INTRODUCTION: Much of the world population is affected by pulmonary diseases, such as the bronchial asthma, bronchitis and bronchiectasis. The bronchial diagnosis is based on the airways state. In this sense, the automatic segmentation of the airways in Computed Tomography (CT) scans is a critical step in the aid to diagnosis of these diseases. METHODS: This paper evaluates algorithms for airway automatic segmentation, using Neural Network Multilayer Perceptron (MLP) and Lung Densities Analysis (LDA) for detecting airways, along with Region Growing (RG), Active Contour Method (ACM) Balloon and Topology Adaptive to segment them. RESULTS: We obtained results in three stages: comparative analysis of the detection algorithms MLP and LDA, with a gold standard acquired by three physicians with expertise in CT imaging of the chest; comparative analysis of segmentation algorithms ACM Balloon, ACM Topology Adaptive, MLP and RG; and evaluation of possible combinations between segmentation and detection algorithms, resulting in the complete method for automatic segmentation of the airways in 2D. CONCLUSION: The low incidence of false negative and the significant reduction of false positive, results in similarity coefficient and sensitivity exceeding 91% and 87% respectively, for a combination of algorithms with satisfactory segmentation quality.