Image analysis of real-time classification of cherry fruit from colour features

An image analysis algorithm for the classification of cherries in real time by processing their digitalized colour images was developed, and tested. A set of five digitalized images of colour pattern, corresponding to five colour classes defined for commercial cherries, was characterized. The algorithm performs the segmentation of the cheery image by rejecting the pixels of the background and keeping the image features corresponding to the coloured area of the fruit. A histogram analysis was carried out for the RGB and HSV colour spaces, where the Red and Hue components showed differences between each of the specified colour patterns of the exporting reference system. This information led to the development of a hybrid Bayesian classification algorithm based on the components R and H. Its accuracy was tested with a set of cherry samples within the colour range of interest. The algorithm was implemented by means of a real time C++ code in Microsoft Visual Studio environment. When testing, the algorithm showed a 100% effectiveness in classifying a sample set of cherries into the five standardized cherry classes. The components of the hardware-software system for implementing the methodology are low cost, thus ensuring an affordable commercial deployment.

Development and testing of a novel image analysis algorithm for descriptive evaluation of shape change of a shrinkable soft material

Soft material can undergo non-uniform deformation or change of shape upon processing. Identifying shape and its change is nevertheless not straightforward. In this study, novel image-based algorithm that can be used to identify shapes of input images and at the same time classify non-uniform deformation into various patterns, i.e., swelling/shrinkage, horizontal and vertical elongations/contractions as well as convexity and concavity, is proposed. The algorithm was first tested with computer-generated images and later applied to agar cubes, which were used as model shrinkable soft material, undergoing drying at different temperatures. Shape parameters and shape-parameter based algorithm as well as convolutional neural networks (CNNs) either incorrectly identified some complicated shapes or could only identify the point where non-uniform deformation started to take place; CNNs lacked ability to describe non-uniform deformation evolution. Shape identification accuracy of the newly developed algorithm against computer-generated images was 65.88%, while those of the other tested algorithms ranged from 34.76 to 97.88%. However, when being applied to the deformation of agar cubes, the developed algorithm performed superiorly to the others. The proposed algorithm could both identify the shapes and describe their changes. The interpretation agreed well with that via visual observation.

Tropomyosin isoforms segregate into distinct clusters on single actin filaments

Tropomyosins (Tpm) are rod-shaped proteins that interact head-to-tail to form a continuous polymer along both sides of most cellular actin filaments. Head-to-tail interaction between adjacent Tpm molecules and the formation of an overlap complex between them leads to the assembly of actin filaments with one type of Tpm isoform in time and space. Variations in the affinity of tropomyosin isoforms for different actin structures are proposed as a potential sorting mechanism. However, the detailed mechanisms of spatio-temporal sorting of Tpms remain elusive. In this study, we investigated the early intermediates during actin-tropomyosin filament assembly, using skeletal/cardiac Tpm isoform (Tpm1.1) and a cytoskeletal isoform (Tpm1.6) that differ only in the last 27 amino acids. We investigated how the muscle isoform Tpm1.1 and the cytoskeletal isoform Tpm1.6 nucleate domains on the actin filament and tested whether (1) recruitment is affected by the actin isoform (muscle vs cytoskeletal) and (2) whether there is specificity in recruiting the same isoform to a domain at these early stages. To address these questions, actin filaments were exposed to low concentrations of fluorescent tropomyosins in solution. The filaments were immobilized onto glass coverslips and the pattern of decoration was visualized by TIRF microscopy. We show that at the early assembly stage, tropomyosins formed multiple distinct fluorescent domains (here termed "cluster") on the actin filaments. An automated image analysis algorithm was developed and validated to identify clusters and estimate the number of tropomyosins in each cluster. The analysis showed that tropomyosin isoform sorting onto an actin filament is unlikely to be driven by a preference for nucleating on the corresponding muscle or cytoskeletal actin isoforms but rather is facilitated by a higher probability of incorporating the same tropomyosin isoforms into an early assembly intermediate. We showed that the 27 amino acids at the end of each tropomyosin seem to provide enough molecular information for attachment of the same tropomyosin isoforms adjacent to each other on an actin filament. This results in the formation of homogeneous clusters composed of the same isoform rather than clusters with mixed isoforms.

Validation of a DKK1 RNAscope chromogenic in situ hybridization assay for gastric and gastroesophageal junction adenocarcinoma tumors

Dickkopf-1 (DKK1) is a secreted modulator of Wnt signaling that is frequently overexpressed in tumors and associated with poor clinical outcomes. DKN-01 is a humanized monoclonal therapeutic antibody that binds DKK1 with high affinity and has demonstrated clinical activity in gastric/gastroesophageal junction (G/GEJ) patients with elevated tumoral expression of DKK1. Here we report on the validation of a DKK1 RNAscope chromogenic in situ hybridization assay to assess DKK1 expression in G/GEJ tumor tissue. To reduce pathologist time, potential pathologist variability from manual scoring and support pathologist decision making, a digital image analysis algorithm that identifies tumor cells and quantifies the DKK1 signal was developed. Following CLIA guidelines the DKK1 RNAscope chromogenic in situ hybridization assay and digital image analysis algorithm were successfully validated for sensitivity, specificity, accuracy, and precision. The DKK1 RNAscope assay in conjunction with the digital image analysis solution is acceptable for prospective screening of G/GEJ adenocarcinoma patients. The work described here will further advance the companion diagnostic development of our DKK1 RNAscope assay and could generally be used as a guide for the validation of RNAscope assays with digital image quantification.

PulseNet international: the missing link between PFGE and WGS

IntroductionDNA-based surveillance of bacterial diseases has been using pulsed field gel electrophoresis (PFGE) since 1996. Currently, the international surveillance network (PulseNet international) is turning toward whole genome sequencing (WGS). ATCGs of WGS are compared using several sequence alignment methods. While patterns of horizontal lines of PFGE profiles are being compared using relative positioning of bands within a range of tolerance. A recently suggested image analysis algorithm and a deployed database (geltowgs.uofk.edu) collectively invented a promising method for comparing PFGE to in-silico obtained digestion models (DMs) derived from WGS. The database requires a parameter that determines PFGE resolution. Here, the author suggests a new method for calculating this factor. Epidemiological and molecular conclusions returned by the database are evaluated.Methodologytwo PFGE profiles representing XbaI digests of E. coli and Salmonella enterica analyzed by the suggested image analysis algorithm were submitted to the database after calculating resolution of PFGE using Dice percentage of difference between the closest PFGE bands in length. E. coli and Salmonella enterica test subjects were compared to 489 and 401 DMs respectively. The three data sets returned were analyzed.Results and conclusionsaccording to modified PFGE evaluation criteria; a single DM is possibly related to E. coli test subject. It belonged to the same serovar. No epidemiologically related DM was shown for S. enterica test subject. Conclusions mentioned earlier could never be made ignoring co-migration. Standardization of both; suggested image analysis and database algorithms will deepen our understanding of bacterial epidemiology by means of possible qualitative approach built upon identification of fragment sequences and their locations within chromosomes.