Search

The image processing of muscular fibers has seen significant improvements over the last decades, from light microscopy acquisition to virtual microscopy and from manual segmentation and fiber typing to automatic. The present study aims to discuss the main tools employed in different histo-enzymological image processing phases applied to muscle fibers, which are respectively: the acquisition, segmentation and fiber typing as well as their efficiency in the determination of morphometric parameters. First, the acquisition: to count the cell numbers within the muscle fiber sections, optical microscopic images with different magnifications (x100, x200, x250, and x400) were compared with virtual slides digitized by Slide Scanner. Second, the segmentation: Three softwares (Fiji "Digitizing pen, Mouse", Image Pro Plus 10 [semi-automatic], and Cytoinformatics LLC [automatic]) were compared for image segmentation quality and the determining of fiber numbers. Third, manual fiber typing: employing Fiji of segmented images using the 3 previously mentioned softwares were performed to calculate the accuracy of the morphometric parameter (Cross sectional Area [CSA], perimeter and Minimal Feret's Diameter [MFD]). The results of the acquisition showed that the scanner slides have a better resolution and detected a higher number of cells than when optical microscopes with different magnifications were used; with the latter, the processing can be performed only with an acceptable resolution, where the number of cells is lesser, which unfortunately requires several repetitions and exhausting work. Our findings regarding segmentation indicate that the Cytoinformatics LLC showed the best processing time and the highest quality followed by IP and Fiji. Finally and for the ultimate step, the morphometric parameter calculation: showed that the best accuracy was attained by using Fiji followed by Cytoinformatics and finally by IP. The findings of this study suggest that Fiji (semi-automatic) showed the best quality/price ratio (open access software) for segmentation and fiber typing, but it proved to be time consuming when compared to Image Pro Plus 10 (semi-automatic) and Cytoinformatics LLC (automatic). [ABSTRACT FROM AUTHOR]

[Display omitted] • A total of 13 different edible and non-edible oils are tested under image processing. • 1300 images are captured under a fluorescent lamp with CANON-EOS-200D digital camera. • KNN and SVM models are used for validation. • High Accuracy RGB image pixel extraction process with Fiji. • Significant properties of oils are predicted accurately. Renewable oils from different feedstocks are considered a potential replacement for the current petroleum products, and they are widely used in various applications like alternative fuels to heat engines and bio-coolants for metal removal operations, and their analysis of significant physicochemical properties is significant before their application. This study attempts to analyze the significant oil properties of different edible and non-edible oils using an image processing technique. For this purpose, 11 different oils are considered for experimentation, and their surface images of all the oils are captured and utilized to extract significant pixel information of Red, Green and Blue (RGB). The RGB pixel information is correlated with experimental properties (viscosity, density, flash point, fire point, cloud and pour points) and the developed model is validated with KNN, SVM and Fiji techniques and observed a high prediction accuracy (99%, 90.9% and 99%). Finally, two different oils which are not used in the experiment are chosen to test the prediction accuracy of the developed model. The results show that the RGB pixel predicts the significant oil properties, and they are validated experimentally and observed that the developed model predicts the oil properties with 91.7% accuracy. [ABSTRACT FROM AUTHOR]

In recent years, image treatment has been appraised as a very powerful tool to facilitate ichnological analysis, especially in marine cores of modern sediments, supporting the determination of certain ichnological features. However, it is still a new approach and detailed research is necessary to encounter a faster and more efficient method. The present study focuses on two image processing techniques, Fiji and ICY, and their comparison with a refined version of the well-established high-resolution image treatment. Strengths and weaknesses of the methodologies for the determination of three main features were explored: i) visibility of trace fossils; ii) quantification of the percentage of bioturbated surface, and iii) penetration depth estimation. Refined high-resolution image treatment gives the best results for enhanced visibility of trace fossils, whereas Fiji is found to be a sound and rapid option. One disadvantage shared by Fiji and ICY is the binary character of the produced images, which may impede later ichnotaxonomical differentiation. Both Fiji and ICY (+ Fiji) are rapid alternatives for quantifying the bulk amount of bioturbated surface. The Magic Wand Method (+ RefineEdge), based on high-resolution image treatment, provides good results regardless of the contrast of the images, and it additionally allows for a more detailed quantification. The semi-automatic character of ICY favors quick estimation of penetration depth and facilitates differentiation between distinct tracemaker communities, based on a rapid quantification of pixel values. Thus, Fiji and ICY methods offer good results and are much less time-consuming than high-resolution image treatment. They are proposed as faster alternatives for the estimation of ichnological features, especially useful at the beginning stages of research, when a large number of samples must be analyzed. • Image treatment methods have been proved in ichnological research • High-resolution image treatment RefineEdge is the best to increase visibility • Fiji (CLAHE) is a rapid alternative for preliminary analysis of cores • Fiji and ICY (+ Fiji) is a rapid alternatives to quantify bioturbated surface • Intensity Profile plugin by ICY are useful for estimating penetration depth. [ABSTRACT FROM AUTHOR]

• Deep learning models often require large volumes of labelled data. • The labelling process is usually very labour intensive. • We demonstrate a method of generating and labelling B-mode ultrasound images automatically. • This approach may have applications in image processing and data sharing. Deep learning approaches are common in image processing, but often rely on supervised learning, which requires a large volume of training images, usually accompanied by hand-crafted labels. As labelled data are often not available, it would be desirable to develop methods that allow such data to be compiled automatically. In this study, we used a Generative Adversarial Network (GAN) to generate realistic B-mode musculoskeletal ultrasound images, and tested the suitability of two automated labelling approaches. We used a model including two GANs each trained to transfer an image from one domain to another. The two inputs were a set of 100 longitudinal images of the gastrocnemius medialis muscle, and a set of 100 synthetic segmented masks that featured two aponeuroses and a random number of 'fascicles'. The model output a set of synthetic ultrasound images and an automated segmentation of each real input image. This automated segmentation process was one of the two approaches we assessed. The second approach involved synthesising ultrasound images and then feeding these images into an ImageJ/Fiji-based automated algorithm, to determine whether it could detect the aponeuroses and muscle fascicles. Histogram distributions were similar between real and synthetic images, but synthetic images displayed less variation between samples and a narrower range. Mean entropy values were statistically similar (real: 6.97, synthetic: 7.03; p = 0.218), but the range was much narrower for synthetic images (6.91 – 7.11 versus 6.30 – 7.62). When comparing GAN-derived and manually labelled segmentations, intersection-over-union values- denoting the degree of overlap between aponeurosis labels- varied between 0.0280 – 0.612 (mean ± SD: 0.312 ± 0.159), and pennation angles were higher for the GAN-derived segmentations (25.1° vs. 19.3°; p < 0.001). For the second segmentation approach, the algorithm generally performed equally well on synthetic and real images, yielding pennation angles within the physiological range (13.8–20°). We used a GAN to generate realistic B-mode ultrasound images, and extracted muscle architectural parameters from these images automatically. This approach could enable generation of large labelled datasets for image segmentation tasks, and may also be useful for data sharing. Automatic generation and labelling of ultrasound images minimises user input and overcomes several limitations associated with manual analysis. [ABSTRACT FROM AUTHOR]