scholarly journals A neural network for glomerulus classification based on histological images of kidney biopsy

2021 ◽  
Vol 21 (S1) ◽  
Author(s):  
Giacomo Donato Cascarano ◽  
Francesco Saverio Debitonto ◽  
Ruggero Lemma ◽  
Antonio Brunetti ◽  
Domenico Buongiorno ◽  
...  
Keyword(s):  
Neural Network ◽  
Clinical Practice ◽  
Periodic Acid ◽  
Digital Pathology ◽  
Feature Reduction ◽  
Training Procedure ◽  
Good Precision ◽  
Periodic Acid Schiff ◽  
Cad Systems ◽  
Cad System

Abstract Background Computer-aided diagnosis (CAD) systems based on medical images could support physicians in the decision-making process. During the last decades, researchers have proposed CAD systems in several medical domains achieving promising results. CAD systems play an important role in digital pathology supporting pathologists in analyzing biopsy slides by means of standardized and objective workflows. In the proposed work, we designed and tested a novel CAD system module based on image processing techniques and machine learning, whose objective was to classify the condition affecting renal corpuscles (glomeruli) between sclerotic and non-sclerotic. Such discrimination is useful for the biopsy slides evaluation performed by pathologists. Results We collected 26 digital slides taken from the kidneys of 19 donors with Periodic Acid-Schiff staining. Expert pathologists have conducted the slides preparation, digital acquisition and glomeruli annotations. Before setting the classifiers, we evaluated several feature extraction techniques from the annotated regions. Then, a feature reduction procedure followed by a shallow artificial neural network allowed discriminating between the glomeruli classes. We evaluated the workflow considering an independent dataset (i.e., processing images not used in the training procedure). Ten independent runs of the training algorithm, and evaluation, allowed achieving MCC and Accuracy of 0.95 (± 0.01) and 0.99 (standard deviation < 0.00), respectively. We also obtained good precision (0.9844 ± 0.0111) and recall (0.9310 ± 0.0153). Conclusions Results on the test set confirm that the proposed workflow is consistent and reliable for the investigated domain, and it can support the clinical practice of discriminating the two classes of glomeruli. Analyses on misclassifications show that the involved images are usually affected by staining artefacts or present partial sections due to slice preparation and staining processes. In clinical practice, however, pathologists discard images showing such artefacts.

scholarly journals Hepatic Hyaline Arteriolosclerosis in Patients with Chronic Hyperglycemia

2021 ◽  
Vol 156 (Supplement_1) ◽  
pp. S124-S124
Author(s):  
M Kilpatrick ◽  
D Lewin
Keyword(s):  
Periodic Acid ◽  
Digital Pathology ◽  
Cardiovascular Complications ◽  
Diabetic Microangiopathy ◽  
Positive Staining ◽  
Histologic Finding ◽  
Periodic Acid Schiff ◽  
Chronic Hyperglycemia ◽  
Chi Squared ◽  
Liver Biopsies

Abstract Introduction/Objective Hyaline arteriolosclerosis is a common feature of diabetic microangiopathy. It results from hyperglycemia-induced endothelial cell dysfunction and can be found in many sites including the retina, kidney, and skin. This histologic finding is important because studies have shown that in the kidney it is an independent risk factor for cardiovascular complications. To our knowledge, an association between hyperglycemia and hyaline arteriolosclerosis in the liver has not be studied. We aimed to investigate whether chronic hyperglycemia is associated with this histologic finding in liver arterioles. Methods/Case Report The first 50 liver biopsies performed at our institution starting January 1, 2020 were scanned into a digital pathology system (Philips, Cambridge, MA). For each biopsy, the patient’s highest recorded hemoglobin A1c (HbA1c) up to one year from the date of biopsy was recorded. The biopsies were then grouped into two groups: those from patients with a HbA1c greater than 6.5%, and those with a HbA1c value less than 6.5 %. Next, the digested periodic acid Schiff (DPAS) intensity of the arteriolar vessels in each biopsy was graded 0 to 3 by a single pathology resident who was blinded to its corresponding HbA1c group. Grade 0 to 1 was considered negative staining. Grade 2 to 3 was considered positive staining and indicative of hyaline arteriolosclerosis. By the end of the data collection, each case had been given a staining category and a HbA1c group. A 2 x 2 contingency table was constructed. Results (if a Case Study enter NA) 37 of 50 patients had a recorded HbA1c meeting the study criteria. Of these 37 patients, 11 had an HbA1c greater than 6.5 % while 26 had an HbA1c less than 6.5%. Seven of the 11 biopsies from patients with an elevated HbA1c showed positive staining. Six of the 26 biopsies from patients with an HbA1c less than 6.5% showed positive staining. Conclusion We hypothesized that patients living with hyperglycemia may be more likely to exhibit hepatic hyaline arteriolosclerosis. A chi-squared test of independence was performed to examine the association between a liver biopsy’s HbA1c group and staining category. The relation between these variables was significant at p = &lt; .05, χ 2 (2, N= 36) = 5.57, p = .0182, indicating liver biopsies with a HbA1c greater than 6.5 % are more likely to have this histologic finding. Future studies are needed to characterize diabetic hepatopathy, and its relatedness to macrovascular complications.

scholarly journals Deep Learning–Based Segmentation and Quantification in Experimental Kidney Histopathology

2020 ◽  
Vol 32 (1) ◽  
pp. 52-68 ◽  
Author(s):  
Nassim Bouteldja ◽  
Barbara M. Klinkhammer ◽  
Roman D. Bülow ◽  
Patrick Droste ◽  
Simon W. Otten ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
High Throughput ◽  
Clinical Studies ◽  
High Performance ◽  
Periodic Acid ◽  
Kidney Tissue ◽  
Disease Models ◽  
Periodic Acid Schiff

BackgroundNephropathologic analyses provide important outcomes-related data in experiments with the animal models that are essential for understanding kidney disease pathophysiology. Precision medicine increases the demand for quantitative, unbiased, reproducible, and efficient histopathologic analyses, which will require novel high-throughput tools. A deep learning technique, the convolutional neural network, is increasingly applied in pathology because of its high performance in tasks like histology segmentation.MethodsWe investigated use of a convolutional neural network architecture for accurate segmentation of periodic acid–Schiff-stained kidney tissue from healthy mice and five murine disease models and from other species used in preclinical research. We trained the convolutional neural network to segment six major renal structures: glomerular tuft, glomerulus including Bowman’s capsule, tubules, arteries, arterial lumina, and veins. To achieve high accuracy, we performed a large number of expert-based annotations, 72,722 in total.ResultsMulticlass segmentation performance was very high in all disease models. The convolutional neural network allowed high-throughput and large-scale, quantitative and comparative analyses of various models. In disease models, computational feature extraction revealed interstitial expansion, tubular dilation and atrophy, and glomerular size variability. Validation showed a high correlation of findings with current standard morphometric analysis. The convolutional neural network also showed high performance in other species used in research—including rats, pigs, bears, and marmosets—as well as in humans, providing a translational bridge between preclinical and clinical studies.ConclusionsWe developed a deep learning algorithm for accurate multiclass segmentation of digital whole-slide images of periodic acid–Schiff-stained kidneys from various species and renal disease models. This enables reproducible quantitative histopathologic analyses in preclinical models that also might be applicable to clinical studies.

Ultrastructure of the Parotid Gland of the Nine-Banded Armadillo

1977 ◽  
Vol 35 ◽  
pp. 640-641
Author(s):  
J. R. Ruby
Keyword(s):  
Endoplasmic Reticulum ◽  
Parotid Gland ◽  
Periodic Acid ◽  
Acinar Cells ◽  
Duct System ◽  
Parotid Glands ◽  
Dasypus Novemcinctus ◽  
Anterior Portion ◽  
Periodic Acid Schiff ◽  
Thin Sections

Parotid glands were obtained from five adult (four male and one female) armadillos (Dasypus novemcinctus) which were perfusion-fixed. The glands were located in a position similar to that of most mammals. They extended interiorly to the anterior portion of the submandibular gland.In the light microscope, it was noted that the acini were relatively small and stained strongly positive with the periodic acid-Schiff (PAS) and alcian blue techniques, confirming the earlier results of Shackleford (1). Based on these qualities and other structural criteria, these cells have been classified as seromucous (2). The duct system was well developed. There were numerous intercalated ducts and intralobular striated ducts. The striated duct cells contained large amounts of PAS-positive substance.Thin sections revealed that the acinar cells were pyramidal in shape and contained a basally placed, slightly flattened nucleus (Fig. 1). The rough endoplasmic reticulum was also at the base of the cell.

Detection of Carriers in Glanzmann's Thrombasthenia

1983 ◽  
Vol 49 (03) ◽  
pp. 182-186
Author(s):  
G T E Zonneveld ◽  
E F van Leeuwen ◽  
A Sturk ◽  
J W ten Cate
Keyword(s):  
Bleeding Time ◽  
Periodic Acid ◽  
Type I ◽  
Clot Retraction ◽  
Periodic Acid Schiff ◽  
Glanzmann’S Thrombasthenia ◽  
Aggregation Response ◽  
Glanzmann's Thrombasthenia ◽  
Sds Page ◽  
Reduced State

SummaryQuantitative glycoprotein (GP) analysis of whole platelets or platelet membranes was performed by SDS-polyacrylamide gelelectrophoresis (SDS-PAGE) and periodic acid Schiff staining in the families of two unrelated Glanzmann’s thrombasthenia (GT) patients. Each family consisted of two symptom free parents, a symptom free daughter and a GT daughter. All symptom free members had a normal bleeding time, clot retraction and platelet aggregation response to adenosine 5’-diphosphate (ADP), collagen and adrenalin. Platelet Zw* antigen was normally expressed in these subjects. GT patiens, classified as a type I and II subject, showed reduced amounts of GP lib and of GP nia. Analysis of isolated membranes in the non-reduced state, however, showed that the amount of GP Ilia was also reduced in three of the four parents, whereas one parent (of the GT type I patient) and the two unaffected daughters had normal amounts of GP Ilia. Quantitative SDS-PAGE may therefore provide a method for the detection of asymptomatic carriers in GT type I and II.

Swim bladder mycosis in farmed rainbow trout Oncorhynchus mykiss caused by Phoma herbarum and experimental verification of pathogenicity

2020 ◽  
Vol 138 ◽  
pp. 237-246 ◽  
Author(s):  
J Řehulka ◽  
A Kubátová ◽  
V Hubka
Keyword(s):  
Rainbow Trout ◽  
Histopathological Examination ◽  
Periodic Acid ◽  
Bladder Wall ◽  
Swim Bladder ◽  
Cell Reactivity ◽  
Periodic Acid Schiff ◽  
Posterior Portion ◽  
Hepatic Congestion ◽  
Phoma Herbarum

In this study, spontaneous swim bladder mycosis was documented in a farmed fingerling rainbow trout from a raceway culture system. At necropsy, the gross lesions included a thickened swim bladder wall, and the posterior portion of the swim bladder was enlarged due to massive hyperplasia of muscle. A microscopic wet mount examination of the swim bladder contents revealed abundant septate hyphae, and histopathological examination showed periodic acid-Schiff-positive mycelia in the lumen and wall of the swim bladder. Histopathological examination of the thickened posterior swim bladder revealed muscle hyperplasia with expansion by inflammatory cells. The causative agent was identified as Phoma herbarum through morphological analysis and DNA sequencing. The disease was reproduced in rainbow trout fingerlings using intraperitoneal injection of a spore suspension. Necropsy in dead and moribund fish revealed extensive congestion and haemorrhages in the serosa of visceral organs and in liver and abdominal serosanguinous fluid. Histopathological examination showed severe hepatic congestion, sinusoidal dilatation, Kupffer cell reactivity, leukostasis and degenerative changes. Fungi were disseminated to the liver, pyloric caeca, kidney, spleen and heart. Although infections caused by Phoma spp. have been repeatedly reported in fish, species identification has been hampered by extensive taxonomic changes. The results of this study confirmed the pathogenicity of P. herbarum in salmonids by using a reliably identified strain during experimental fish infection and provides new knowledge regarding the course of infection.

Erdheim-Chester Disease Presenting with Histiocytic Colitis and Cytokine Storm

2017 ◽  
Vol 26 (2) ◽  
pp. 183-187
Author(s):  
George P. Christophi ◽  
Yeshika Sharma ◽  
Quader Farhan ◽  
Umang Jain ◽  
Ted Walker ◽  
...  
Keyword(s):  
Periodic Acid ◽  
Poor Response ◽  
Rare Type ◽  
Periodic Acid Schiff ◽  
Hematopoietic Stem ◽  
Hemodynamic Compromise ◽  
Erdheim Chester Disease ◽  
Erdheim Chester ◽  
Chester Disease ◽  
Segmental Colitis

Background: Non-Langerhans histiocytosis is a group of inflammatory lymphoproliferative disorders originating from non-clonal expansion of hematopoietic stem cells into cytokine-secreting dendritic cells or macrophages. Erdheim-Chester Disease (ECD) is a rare type of non-Langerhans cell histiocytosis characterized by tissue inflammation and injury caused by macrophage infiltration and histologic findings of foamy histiocytes. Often ECD involves the skeleton, retroperitoneum and the orbits. This is the first report documenting ECD manifesting as segmental colitis and causing cytokine-release syndrome.Case presentation: A 68-year old woman presented with persistent fever without infectious etiology and hematochezia. Endoscopy showed segmental colitis and pathology revealed infiltration of large foamy histiocytes CD3-/CD20-/CD68+/CD163+/S100- consistent with ECD. The patient was empirically treated with steroids but continued to have fever and developed progressive distributive shock.Conclusion: This case report describes the differential diagnosis of infectious and immune-mediated inflammatory and rheumatologic segmental colitis. Non-Langerhans histiocytosis and ECD are rare causes of gastrointestinal inflammation. Prompt diagnosis is imperative for the appropriate treatment to prevent hemodynamic compromise due to distributive shock or gastrointestinal bleeding. Importantly, gastrointestinal ECD might exhibit poor response to steroid treatment and other potential treatments including chemotherapy, and biologic treatments targeting IL-1 and TNF-alpha signaling should be considered.Abbreviations: AFB: acid-fast bacilli; ECD: Erdheim-Chester Disease; IBD: inflammatory bowel disease; PASD: periodic acid-Schiff with diastase; TB: tuberculosis

Analysing Mechanical Systems in Domestic and Foreign CAD Systems

2018 ◽  
pp. 10-17
Author(s):  
V. A. Martynyuk ◽  
V. A. Trudonoshin ◽  
V. G. Fedoruk
Keyword(s):  
Sheet Material ◽  
The Finite Element Method ◽  
Cad Systems ◽  
Cad System ◽  
Software Products ◽  
Foreign Products ◽  
Nonlinear Algebraic Systems ◽  
Software Product ◽  
Pipeline Design ◽  
The Mathematical Model

The article considers applications of foreign CAD-systems in creating the challenging projects at domestic enterprises and design bureaus. As stated in the article "... presently, there is no domestic CAD-system that could completely replace such foreign products as NX, CATIA, Credo". Besides, due to international cooperation in creating the challenging projects (for example, the project to create a modern wide-body aircraft, proposed jointly with China), it makes sense to use the worldwide known and popular CAD systems (the aforementioned NX, CATIA, Credo). Therefore, in the foreseeable future, we will still have to use foreign software products. Of course, there always remains a question of the reliability of the results obtained. Actually, this question is always open regardless of what software product is used - domestic or foreign. This question has been haunting both developers and users of CAD systems for the last 30 to 40 years. But with using domestic systems, it is much easier to identify the cause of inaccurate results and correct the mathematical models used, the methods of numerical integration applied, and the solution of systems of nonlinear algebraic systems. Everything is much more complicated if we use a foreign software product. All advertising conversations that there is a tool to make the detected errors available to the developers, remain only conversations in the real world. It is easily understandable to domestic users, and, especially, to domestic developers of similar software products. The existing development rates and competition for potential buyers dictate a rigid framework of deadlines for releasing all new versions of the product and introducing the latest developments into commercial product, etc. As a result, the known errors migrate from version to version, and many users have accepted it long ago. Especially, this concerns the less popular tools rather than the most popular applications (modules) of a CAD system. For example, in CAD systems, the "Modeling" module where geometric models of designed parts and assembly units are created has been repeatedly crosschecked. But most of the errors are hidden in applications related to the design of parts from sheet material and to the pipeline design, as well as in applications related to the analysis of moving mechanisms and to the strength or gas dynamic analysis by the finite element method.The article gives a concrete example of a moving mechanism in the analysis of which an error was detected using the mathematical model of external influence (a source of speed) in the NX 10.0 system of Siemens.

Analysis of Feature Reduction Techniques for Online News Popularity Prediction

2018 ◽  
Vol 4 (10) ◽  
pp. 6
Author(s):  
Shivangi Bhargava ◽  
Dr. Shivnath Ghosh
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Naive Bayes ◽  
Particle Swarm ◽  
Naïve Bayes ◽  
Online News ◽  
Feature Reduction ◽  
Support Vector ◽  
Swarm Optimization

News popularity is the maximum growth of attention given for particular news article. The popularity of online news depends on various factors such as the number of social media, the number of visitor comments, the number of Likes, etc. It is therefore necessary to build an automatic decision support system to predict the popularity of the news as it will help in business intelligence too. The work presented in this study aims to find the best model to predict the popularity of online news using machine learning methods. In this work, the result analysis is performed by applying Co-relation algorithm, particle swarm optimization and principal component analysis. For performance evaluation support vector machine, naïve bayes, k-nearest neighbor and neural network classifiers are used to classify the popular and unpopular data. From the experimental results, it is observed that support vector machine and naïve bayes outperforms better with co-relation algorithm as well as k-NN and neural network outperforms better with particle swarm optimization.

scholarly journals Ectopic atrial arrhythmias arising from canine thoracic veins during in vivo stellate ganglia stimulation

2008 ◽  
Vol 295 (2) ◽  
pp. H691-H698 ◽  
Author(s):  
Alex Y. Tan ◽  
Shengmei Zhou ◽  
Byung Chun Jung ◽  
Masahiro Ogawa ◽  
Lan S. Chen ◽  
...  
Keyword(s):  
Pulmonary Vein ◽  
Sinus Node ◽  
Periodic Acid ◽  
Sympathetic Innervation ◽  
Sympathetic Nerves ◽  
Atrial Arrhythmias ◽  
Periodic Acid Schiff ◽  
Stellate Ganglia ◽  
Ectopic Beats

The purpose of the present study was to determine whether thoracic veins may act as ectopic pacemakers and whether nodelike cells and rich sympathetic innervation are present at the ectopic sites. We used a 1,792-electrode mapping system with 1-mm resolution to map ectopic atrial arrhythmias in eight normal dogs during in vivo right and left stellate ganglia (SG) stimulation before and after sinus node crushing. SG stimulation triggered significant elevations of transcardiac norepinephrine levels, sinus tachycardia in all dogs, and atrial tachycardia in two of eight dogs. Sinus node crushing resulted in a slow junctional rhythm (51 ± 6 beats/min). Subsequent SG stimulation induced 20 episodes of ectopic beats in seven dogs and seven episodes of pulmonary vein tachycardia in three dogs (cycle length 273 ± 35 ms, duration 16 ± 4 s). The ectopic beats arose from the pulmonary vein ( n = 11), right atrium ( n = 5), left atrium ( n = 2), and the vein of Marshall ( n = 2). There was no difference in arrhythmogenic effects of left vs. right SG stimulation (13/29 vs. 16/29 episodes, P = nonsignificant). There was a greater density of periodic acid Schiff-positive cells ( P < 0.05) and sympathetic nerves ( P < 0.05) at the ectopic sites compared with other nonectopic atrial sites. We conclude that, in the absence of a sinus node, thoracic veins may function as subsidiary pacemakers under heightened sympathetic tone, becoming the dominant sites of initiation of focal atrial arrhythmias that arise from sites with abundant sympathetic nerves and periodic acid Schiff-positive cells.

scholarly journals The potential renal toxicity of silver nanoparticles after repeated oral exposure and its underlying mechanisms

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Hamed Nosrati ◽  
Manijeh Hamzepoor ◽  
Maryam Sohrabi ◽  
Massoud Saidijam ◽  
Mohammad Javad Assari ◽  
...  
Keyword(s):  
Silver Nanoparticles ◽  
Molecular Mechanisms ◽  
Renal Toxicity ◽  
Periodic Acid ◽  
Critical Role ◽  
Oral Exposure ◽  
Control Group ◽  
Rt Pcr ◽  
Periodic Acid Schiff

Abstract Background Silver nanoparticles (AgNPs) can accumulate in various organs after oral exposure. The main objective of the current study is to evaluate the renal toxicity induced by AgNPs after repeated oral exposure and to determine the relevant molecular mechanisms. Methods In this study, 40 male Wistar rats were treated with solutions containing 30, 125, 300, and 700 mg/kg of AgNPs. After 28 days of exposure, histopathological changes were assessed using hematoxylin-eosin (H&E), Masson’s trichrome, and periodic acid-Schiff (PAS) staining. Apoptosis was quantified by TUNEL and immunohistochemistry of caspase-3, and the level of expression of the mRNAs of growth factors was determined using RT-PCR. Results Histopathologic examination revealed degenerative changes in the glomeruli, loss of tubular architecture, loss of brush border, and interrupted tubular basal laminae. These changes were more noticeable in groups treated with 30 and 125 mg/kg. The collagen intensity increased in the group treated with 30 mg/kg in both the cortex and the medulla. Apoptosis was much more evident in middle-dose groups (i.e., 125 and 300 mg/kg). The results of RT-PCR indicated that Bcl-2 and Bax mRNAs upregulated in the treated groups (p < 0.05). Moreover, the data related to EGF, TNF-α, and TGF-β1 revealed that AgNPs induced significant changes in gene expression in the groups treated with 30 and 700 mg/kg compared to the control group. Conclusion Our observations showed that AgNPs played a critical role in in vivo renal toxicity.

Sign in / Sign up

Export Citation Format

Share Document