Correction of out-of-focus microscopic images by deep learning.

Motivation: Microscopic images are widely used in basic biomedical research, disease diagnosis and medical discovery. Obtaining high-quality in-focus microscopy images has been a cornerstone of the microscopy. However, images obtained by microscopes are often out-of-focus, resulting in poor performance in research and diagnosis. Results: To solve the out-of-focus issue in microscopy, we developed a Cycle Generative Adversarial Network (CycleGAN) based model and a multi-component weighted loss function. We train and test our network in two self-collected datasets, namely Leishmania parasite dataset captured by a bright-field microscope, and bovine pulmonary artery endothelial cells (BPAEC) captured by a confocal fluorescence microscope. In comparison to other GAN-based deblurring methods, the proposed model reached state-of-the-art performance in correction. Another publicly available dataset, human cells dataset from the Broad Bioimage Benchmark Collection is used for evaluating the generalization abilities of the model. Our model showed excellent generalization capability, which could transfer to different types of microscopic image datasets. Availability and Implementation: Code and dataset are publicly available at: https://github.com/jiangdat/COMI.

Cellulose-based micro-fibrous materials imaged with a home-built smartphone microscope.

Micro-fibrous materials are one of the highly explored materials and form a major component of composite materials. In resource-limited settings, an affordable and easy to implement method that can characterize such material would be important. In this study, we report on a smartphone microscopic system capable of imaging a sample in transmission mode. As a proof of concept, we implemented the method to image handmade paper samples-cellulosic micro-fibrous material of different thickness. With 1 mm diameter ball lens, individual cellulose fibers, fiber web, and micro-porous regions were resolved in the samples. Imaging performance of the microscopic system was also compared with a commercial bright field microscope. For thin samples, we found the image quality comparable to commercial system. Also, the diameter of cellulose fiber measured from both methods was found to be similar. We also used the system to image surfaces of a three ply surgical facemask. Finally, we explored the application of the system in the study of chemical induced fiber damage. This study suggested that the smartphone microscope system can be an affordable alternative in imaging thin micro-fibrous material in resource limited setting.

LeukocyteMask: An automated localization and segmentation method for leukocyte in blood smear images using deep neural networks.

Digital pathology and microscope image analysis is widely used in comprehensive studies of cell morphology. Identification and analysis of leukocytes in blood smear images, acquired from bright field microscope, are vital for diagnosing many diseases such as hepatitis, leukaemia and acquired immune deficiency syndrome (AIDS). The major challenge for robust and accurate identification and segmentation of leukocyte in blood smear images lays in the large variations of cell appearance such as size, colour and shape of cells, the adhesion between leukocytes (white blood cells, WBCs) and erythrocytes (red blood cells, RBCs), and the emergence of substantial dyeing impurities in blood smear images. In this paper, an end-to-end leukocyte localization and segmentation method is proposed, named LeukocyteMask, in which pixel-level prior information is utilized for supervisor training of a deep convolutional neural network, which is then employed to locate the region of interests (ROI) of leukocyte, and finally segmentation mask of leukocyte is obtained based on the extracted ROI by forward propagation of the network. Experimental results validate the effectiveness of the propose method and both the quantitative and qualitative comparisons with existing methods indicate that LeukocyteMask achieves a state-of-the-art performance for the segmentation of leukocyte in terms of robustness and accuracy .

Occurrence of Capillaria sp. in the liver of sheep (Ovis aries ) in a slaughterhouse in the state of Acre, Brazil / Ocorrência de Capillaria sp. em fígado de ovino ( Ovis aries) em um abatedouro no estado do Acre, Brasil

Abstract Although sheep farming has grown in the state of Acre over the past four decades, little is known about occurrences of helminthiases in the herds of this region. The objective of the study was to assess the occurrences of non-intestinal helminthiasis among sheep slaughtered in Rio Branco. A total of 110 sheep livers were inspected from two slaughter batches (july 2014 and march 2015) in a slaughterhouse in Rio Branco. Livers with macroscopic lesions were photographed and were then subjected to histopathological analysis under an optical microscope. The macroscopic lesions showed small nodes with inflammatory characteristics and areas of fibrosis, which appeared to be calcified, thus suggesting a granulomatous reaction. Of the 110 evaluated livers, we noticed 110 nodules in total; these nodules have an average size of 0.5 cm. The histopathological analysis showed alterations to the architecture of the hepatic lobe, with multiple foci of necrosis and polymorphonuclear cells. Two samples revealed the presence of helminths from Nematode class and Capillaria sp. eggs identified by the typical morphology and morphometry. This seems to be the first report of Capillaria sp. in sheep livers in Brazil, and it serves as an important alert regarding animal health surveillance and control and regarding the Capillaria sp. zoonotic role in humans.

Resumo Embora a ovinocultura tenha despertado o interesse de criadouros no estado do Acre nas últimas quatro décadas, pouco se conhece sobre a ocorrência de helmintoses no plantel de ovinos dessa região. O objetivo do presente estudo foi avaliar a possibilidade de ocorrência de helmintíases não intestinais entre ovinos abatidos no município de Rio Branco. Foram inspecionados 110 fígados de ovinos em dois abates (julho de 2014 e março de 2015) em um abatedouro no município de Rio Branco. Fígados com lesões macroscópicas foram fotografados com posterior análise histopatológica por microscopia de luz. Nas lesões macroscópicas foram encontrados pequenos nódulos apresentando características inflamatórias com áreas de fibrose, aparentemente calcificadas, sugerindo uma reação granulomatosa. Dos 110 fígados avaliados, observou-se 110 nódulos no total; estes nódulos têm um tamanho médio de 0,5 cm. A análise histopatológica mostrou alterações na arquitetura do lóbulo hepático, com múltiplos focos de necrose, além da formação de abscessos hepáticos constituídos por polimorfonucleares. Duas amostras revelaram a presença de helmintos da Classe Nematoda e ovos de Capillaria sp. identificados pela morfologia típica e morfometria. Esse resultado parece ser o primeiro registro de Capillaria sp. em fígado de ovino no Brasil, o que é um importante alerta para a vigilância no controle sanitário animal e o seu papel zoonótico para humanos.

An efficient and robust hybrid method for segmentation of zebrafish objects from bright-field microscope images.

Accurate segmentation of zebrafish from bright-field microscope images is crucial to many applications in the life sciences. Early zebrafish stages are used, and in these stages the zebrafish is partially transparent. This transparency leads to edge ambiguity as is typically seen in the larval stages. Therefore, segmentation of zebrafish objects from images is a challenging task in computational bio-imaging. Popular computational methods fail to segment the relevant edges, which subsequently results in inaccurate measurements and evaluations. Here we present a hybrid method to accomplish accurate and efficient segmentation of zebrafish specimens from bright-field microscope images. We employ the mean shift algorithm to augment the colour representation in the images. This improves the discrimination of the specimen to the background and provides a segmentation candidate retaining the overall shape of the zebrafish. A distance-regularised level set function is initialised from this segmentation candidate and fed to an improved level set method, such that we can obtain another segmentation candidate which preserves the explicit contour of the object. The two candidates are fused using heuristics, and the hybrid result is refined to represent the contour of the zebrafish specimen. We have applied the proposed method on two typical datasets. From experiments, we conclude that the proposed hybrid method improves both efficiency and accuracy of the segmentation of the zebrafish specimen. The results are going to be used for high-throughput applications with zebrafish.