scholarly journals VISTA: Virtual ImmunoSTAining for pancreatic disease quantification in murine cohorts

2020 ◽  
Author(s):  
Luke Ternes ◽  
Ge Huang ◽  
Christian Lanciault ◽  
Guillaume Thibault ◽  
Rachelle Riggers ◽  
...  
Keyword(s):  
Disease Progression ◽  
Animal Studies ◽  
Semantic Segmentation ◽  
Pancreatic Disease ◽  
Poor Quality ◽  
Pancreatic Tissue ◽  
Cancer Evolution ◽  
Histologic Feature ◽  
Stromal Compartment ◽  
Automated Platform

AbstractMechanistic studies of pancreatic disease progression using animal models require objective and quantifiable assessment of tissue changes among animal cohorts. Disease state quantification, however, relies heavily on tissue immunostaining, which can be expensive, labor- and time-intensive, and all too often produces uneven staining that is prone to variable interpretation between experts and inaccurate quantification. Here we develop a fully automated semantic segmentation tool using deep learning for the rapid and objective quantification of histologic features using hematoxylin and eosin (H&E) stained pancreatic tissue sections acquired from murine pancreatic cancer models. The tool was successfully trained to segment and quantify multiple histopathologic features of pancreatic pre-cancer evolution, including normal acinar structures, the ductal phenotype of acinar-to ductal metaplasia (ADM), dysplasia, and the expanding stromal compartment. Disease quantifications produced by our computational tool were highly correlated to the results obtained by immunostaining markers of normal and diseased tissue (DAPI, amylase, and cytokeratins; correlation score= 0.9, 0.95, and 0.91, respectively) and were able to accurately reproduce immunostain patterns. Moreover, our tool was able to distinguish ADM from dysplasia, which are not reliably distinguished by immunostaining, and avoid the pitfalls of uneven or poor-quality staining. Using this tool, we quantified the changes in histologic feature abundance for murine cohorts with oncogenic Kras-driven disease at 2 months and 5 months of age (n=12, n=13). The calculated changes in histologic feature abundance were consistent with biological expectations, showing an expansion of the stromal compartment, a reduction of normal acinar tissue, and an increase in both ADM and dysplasia as disease progresses (p= 2e-6, 6e-7, 4e-4, and 3e-5, respectively). These results demonstrate the tool’s efficacy for accurate and rapid quantification of multiple histologic features using an objective and automated platform. Our tool promises to rapidly accelerate and improve the quantification of altered pancreatic disease progression in animal studies.

scholarly journals VISTA: VIsual Semantic Tissue Analysis for pancreatic disease quantification in murine cohorts

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Luke Ternes ◽  
Ge Huang ◽  
Christian Lanciault ◽  
Guillaume Thibault ◽  
Rachelle Riggers ◽  
...  
Keyword(s):  
Animal Studies ◽  
Structural Similarity ◽  
Semantic Segmentation ◽  
Pancreatic Disease ◽  
Pancreatic Tissue ◽  
Investigator Bias ◽  
Acinar To Ductal Metaplasia ◽  
Staining Methods ◽  
Acinar Tissue ◽  
Disease Quantification

AbstractMechanistic disease progression studies using animal models require objective and quantifiable assessment of tissue pathology. Currently quantification relies heavily on staining methods which can be expensive, labor/time-intensive, inconsistent across laboratories and batch, and produce uneven staining that is prone to misinterpretation and investigator bias. We developed an automated semantic segmentation tool utilizing deep learning for rapid and objective quantification of histologic features relying solely on hematoxylin and eosin stained pancreatic tissue sections. The tool segments normal acinar structures, the ductal phenotype of acinar-to-ductal metaplasia (ADM), and dysplasia with Dice coefficients of 0.79, 0.70, and 0.79, respectively. To deal with inaccurate pixelwise manual annotations, prediction accuracy was also evaluated against biological truth using immunostaining mean structural similarity indexes (SSIM) of 0.925 and 0.920 for amylase and pan-keratin respectively. Our tool’s disease area quantifications were correlated to the quantifications of immunostaining markers (DAPI, amylase, and cytokeratins; Spearman correlation score = 0.86, 0.97, and 0.92) in unseen dataset (n = 25). Moreover, our tool distinguishes ADM from dysplasia, which are not reliably distinguished with immunostaining, and demonstrates generalizability across murine cohorts with pancreatic disease. We quantified the changes in histologic feature abundance for murine cohorts with oncogenic Kras-driven disease, and the predictions fit biological expectations, showing stromal expansion, a reduction of normal acinar tissue, and an increase in both ADM and dysplasia as disease progresses. Our tool promises to accelerate and improve the quantification of pancreatic disease in animal studies and become a unifying quantification tool across laboratories.

Comparison of Endoscopic Retrograde Pancreatography with Functional and Histologic Changes in Chronic Pancreatitis

1987 ◽  
Vol 28 (3) ◽  
pp. 289-293 ◽  
Author(s):  
H. A. Heij ◽  
H. Obertop ◽  
M. van Blankenstein ◽  
G. A. J. J. Nix ◽  
D. L. Westbroek
Keyword(s):  
Chronic Pancreatitis ◽  
Discriminant Analysis ◽  
Test Data ◽  
Pancreatic Surgery ◽  
Pancreatic Disease ◽  
Pancreatic Tissue ◽  
Endoscopic Retrograde Pancreatography ◽  
Endoscopic Retrograde ◽  
The Relationship ◽  
Histologic Changes

The findings from endoscopic retrograde pancreatography (ERP) and secretin-CCK test data were compared in 69 patients: 36 with chronic pancreatitis, 9 with possible chronic pancreatitis, and 24 without chronic pancreatic disease. The ERP findings were also compared with the histologic changes in pancreatic tissue in 18 patients who underwent pancreatic surgery for chronic pancreatitis. ERP films were reviewed according to the criteria proposed by Kasugai et coll. (8) with special attention paid to the side branches. Secretin-CCK test data were interpreted using the discriminant analysis. A good correlation between bicarbonate and chymotrypsin output and ductular changes at ERP was found. The results of ERP and the secretin-CCK test were compatible in 86 per cent of the patients. The relationship between ERP findings and histologic changes was not straightforward. It was concluded that ERP and the secretin-CCK test are complementary in the diagnosis of chronic pancreatitis. ERP does not necessarily represent the histology in chronic pancreatitis.

scholarly journals Computational disease progression modeling can provide insights into cancer evolution

Oncoscience ◽  
2020 ◽  
Vol 7 (3-4) ◽  
pp. 21-22
Author(s):  
Steve Goodison ◽  
Mark E. Sherman ◽  
Yijun Sun
Keyword(s):  
Disease Progression ◽  
Cancer Evolution ◽  
Disease Progression Modeling

scholarly journals Can prospective systematic reviews of animal studies improve clinical translation?

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Pandora Pound ◽  
Merel Ritskes-Hoitinga
Keyword(s):  
Clinical Trials ◽  
Systematic Reviews ◽  
Animal Studies ◽  
Poor Quality ◽  
Human Studies ◽  
Clinical Knowledge ◽  
Safety And Efficacy ◽  
High Quality Evidence ◽  
Animal Data

AbstractSystematic reviews are powerful tools with the potential to generate high quality evidence. Their application to animal studies has been instrumental in exposing the poor quality of these studies, as well as a catalyst for improvements in study design, conduct and reporting. It has been suggested that prospective systematic reviews of animal studies (i.e. systematic reviews conducted prior to clinical trials) would allow scrutiny of the preclinical evidence, providing valuable information on safety and efficacy, and helping to determine whether clinical trials should proceed. However, while prospective systematic reviews allow valuable scrutiny of the preclinical animal data, they are not necessarily able to reliably predict the safety and efficacy of an intervention when trialled in humans. Consequently, they may not reliably safeguard humans participating in clinical trials and might potentially result in lost opportunities for beneficial clinical treatments. Furthermore, animal and human studies are often conducted concurrently, which not only makes prospective systematic reviews of animal studies impossible, but suggests that animal studies do not inform human studies in the manner presumed. We suggest that this points to a confused attitude regarding animal studies, whereby tradition demands that they precede human studies but practice indicates that their findings are often ignored. We argue that it is time to assess the relative contributions of animal and human research in order to better understand how clinical knowledge is actually produced.

scholarly journals Oxytocin and Naltrexone Successfully Treat Hypothalamic Obesity in a Boy Post-Craniopharyngioma Resection

2017 ◽  
Vol 103 (2) ◽  
pp. 370-375 ◽  
Author(s):  
Eugenie A Hsu ◽  
Jennifer L Miller ◽  
Francisco A Perez ◽  
Christian L Roth
Keyword(s):  
Parental Monitoring ◽  
Animal Studies ◽  
Phase 1 ◽  
Poor Quality ◽  
Free Access ◽  
Phase 2 ◽  
Z Score ◽  
Hypothalamic Obesity ◽  
Food Seeking

Abstract Context Hypothalamic obesity, a treatment-resistant condition common to survivors of craniopharyngioma (CP), is strongly associated with a poor quality of life in this population. Oxytocin (OT), a hypothalamic neuropeptide, has been shown to play a role in the regulation of energy balance and to have anorexigenic effects in animal studies. Naltrexone (NAL), an opiate antagonist, has been shown to deter hedonic eating and to potentiate OT’s effects. Design In this parent-observed study, we tested the administration of intranasal OT for 10 weeks (phase 1), followed by a combination of intranasal OT and NAL for 38 weeks (phase 2) in a 13-year-old male with confirmed hypothalamic obesity and hyperphagia post-CP resection. Treatment resulted in 1) reduction in body mass index (BMI) z score from 1.77 to 1.49 over 10 weeks during phase 1; 2) reduction in BMI z score from 1.49 to 0.82 over 38 weeks during phase 2; 3) reduced hyperphagia during phases 1 and 2; 4) continued hedonic high-carbohydrate food-seeking in the absence of hunger during phases 1 and 2; and 5) sustained weight reduction during decreased parental monitoring and free access to unlocked food in the home during the last 10 weeks of phase 2. Conclusion This successful intervention of CP-related hypothalamic obesity and hyperphagia by OT alone and in combination with NAL is promising for conducting future studies of this treatment-recalcitrant form of obesity.

scholarly journals Important role of fat tissue hormones in development of comorbid chronic pancreatitis and obesity

2017 ◽  
Vol 37 (3) ◽  
pp. 30-35
Author(s):  
T. N. Hristich
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Adipose Tissue ◽  
Chronic Pancreatitis ◽  
Pancreatic Disease ◽  
Pancreatic Tissue ◽  
Visceral Adipose

Aim of this paper is to consider the role of hormones of the adipose tissue in mechanisms of obesity, metabolic syndrome, type 2 diabetes mellitus upon chronic pancreatitis. Materials and methods. The literature review indicates the value of visceral fat in the development of insulin resistance, dyslipidemia, including atherogenic one, taking into account the possible infiltration of pancreatic tissue by adipocytes. Participation of some adipocytokines of adipose tissue in the development of obesity upon chronic pancreatitis is highlighted. It is shown that in some cases the hormones of visceral adipose tissue, penetrating through the portal vein to the liver and then to the pancreas, aggravated the course of systemic chronic inflammation of the inherent chronic pancreatitis, promote steatosis and development of fatty pancreatic disease. Conclusion. Literary sources indicate the leading role of visceral adipose tissue and its hormones in the formation of obesity in chronic pancreatitis. Due to the infiltration of the pancreatic tissue by adipocytes, lipoidosis and steatosis develop. With the progression of the process type 2 diabetes mellitus, fatty liver or pancreatic disease, or cancer of these orhans. Consequently, there is a need for serious differentiated preventive and curative measures aimed at promoting a healthy lifestyle to improve the quality of life of patients suffering from chronic pancreatitis.

scholarly journals Significant role of fat tissue hormones in development of comorbid chronic pancreatitis and obesity

2018 ◽  
Vol 39 (1) ◽  
pp. 4-9
Author(s):  
T. N. Hristich
Keyword(s):  
Type 2 Diabetes ◽  
Adipose Tissue ◽  
Chronic Pancreatitis ◽  
Visceral Adipose Tissue ◽  
Healthy Lifestyle ◽  
Pancreatic Disease ◽  
Pancreatic Tissue ◽  
Visceral Adipose

Aim is to consider the role of hormones in the adipose tissue of obesity mechanisms of metabolic syndrome, type 2 diabetes mellitus in chronic pancreatitis. Materials and methods. Literature review indicates the value of visceral fat in the development of insulin resistance, dyslipidemia, including atherogenic one, taking into account the possible infiltration of pancreatic tissue by adipocytes. Participation of some adipocytokines of adipose tissue in the development of obesity in chronic pancreatitis is highlighted. It is shown that in some cases the hormones of visceral adipose tissue, penetrating through the portal vein to the liver and then to the pancreas, aggravated the course of systemic chronic inflammation typical for the inherent chronic pancreatitis, formed steatosis and promoted development of fatty disease of the pancreas. Conclusion. Literary sources show the leading role of visceral adipose tissue and its hormones in the formation of obesity in chronic pancreatitis. Lipoidosis or steatosis develop due to the infiltration of the liver and pancreatic tissue by adipocytes. Upon the progression of the type 2 diabetes, fatty liver or pancreatic disease, or cancer of these organs may develop. Consequently, there is a strong need for a serious differentiated preventive and curative measures aimed at promoting a healthy lifestyle to improve the quality of life of patients suffering from chronic pancreatitis.

scholarly journals Boosting Multilabel Semantic Segmentation for Somata and Vessels in Mouse Brain

2021 ◽  
Vol 15 ◽  
Author(s):  
Xinglong Wu ◽  
Yuhang Tao ◽  
Guangzhi He ◽  
Dun Liu ◽  
Meiling Fan ◽  
...  
Keyword(s):  
Neural Networks ◽  
Mouse Brain ◽  
Light And Electron Microscopy ◽  
Three Dimensional ◽  
Image Data ◽  
Semantic Segmentation ◽  
Poor Quality ◽  
Deep Convolutional Neural Networks ◽  
Segmentation Task

Deep convolutional neural networks (DCNNs) are widely utilized for the semantic segmentation of dense nerve tissues from light and electron microscopy (EM) image data; the goal of this technique is to achieve efficient and accurate three-dimensional reconstruction of the vasculature and neural networks in the brain. The success of these tasks heavily depends on the amount, and especially the quality, of the human-annotated labels fed into DCNNs. However, it is often difficult to acquire the gold standard of human-annotated labels for dense nerve tissues; human annotations inevitably contain discrepancies or even errors, which substantially impact the performance of DCNNs. Thus, a novel boosting framework consisting of a DCNN for multilabel semantic segmentation with a customized Dice-logarithmic loss function, a fusion module combining the annotated labels and the corresponding predictions from the DCNN, and a boosting algorithm to sequentially update the sample weights during network training iterations was proposed to systematically improve the quality of the annotated labels; this framework eventually resulted in improved segmentation task performance. The microoptical sectioning tomography (MOST) dataset was then employed to assess the effectiveness of the proposed framework. The result indicated that the framework, even trained with a dataset including some poor-quality human-annotated labels, achieved state-of-the-art performance in the segmentation of somata and vessels in the mouse brain. Thus, the proposed technique of artificial intelligence could advance neuroscience research.

scholarly journals A supervised machine learning semantic segmentation approach for detecting artifacts in plethysmography signals from wearables

2021 ◽  
Author(s):  
Zhicheng Guo ◽  
Cheng Ding ◽  
Xiao Hu ◽  
Cynthia Rudin
Keyword(s):  
Binary Classification ◽  
Low Cost ◽  
Semantic Segmentation ◽  
Poor Quality ◽  
Supervised Machine Learning ◽  
Accuracy Evaluation ◽  
Design Of Algorithms ◽  
Artifact Detection ◽  
Segmentation Approach ◽  
Testing Set

Abstract Objective. Wearable devices equipped with plethysmography (PPG) sensors provided a low-cost, long-term solution to early diagnosis and continuous screening of heart conditions. However PPG signals collected from such devices often suffer from corruption caused by artifacts. The objective of this study is to develop an effective supervised algorithm to locate the regions of artifacts within PPG signals. Approach. We treat artifact detection as a 1D segmentation problem. We solve it via a novel combination of an active-contour-based loss and an adapted U-Net architecture. The proposed algorithm was trained on the PPG DaLiA training set, and further evaluated on the PPG DaLiA testing set, WESAD dataset and TROIKA dataset. Main results. We evaluated with the DICE score, a well-established metric for segmentation accuracy evaluation in the field of computer vision. The proposed method outperforms baseline methods on all three datasets by a large margin (≈ 7 percentage points above the next best method). On the PPG DaLiA testing set, WESAD dataset and TROIKA dataset, the proposed method achieved 0.8734±0.0018, 0.9114±0.0033 and 0.8050±0.0116 respectively. The next best method only achieved 0.8068±0.0014, 0.8446±0.0013 and 0.7247±0.0050. Significance. The proposed method is able to pinpoint exact locations of artifacts with high precision; in the past, we had only a binary classification of whether a PPG signal has good or poor quality. This more nuanced information will be critical to further inform the design of algorithms to detect cardiac arrhythmia.

scholarly journals Subnetwork-based analysis of chronic lymphocytic leukemia identifies pathways that associate with disease progression

Blood ◽  
2012 ◽  
Vol 120 (13) ◽  
pp. 2639-2649 ◽  
Author(s):  
Han-Yu Chuang ◽  
Laura Rassenti ◽  
Michelle Salcedo ◽  
Kate Licon ◽  
Alexander Kohlmann ◽  
...  
Keyword(s):  
Gene Expression ◽  
Chronic Lymphocytic Leukemia ◽  
Disease Progression ◽  
Expression Profiles ◽  
Treatment Strategies ◽  
Gene Expression Profiles ◽  
Lymphocytic Leukemia ◽  
Cancer Evolution ◽  
Sample Collection ◽  
Over Time

Abstract The clinical course of patients with chronic lymphocytic leukemia (CLL) is heterogeneous. Several prognostic factors have been identified that can stratify patients into groups that differ in their relative tendency for disease progression and/or survival. Here, we pursued a subnetwork-based analysis of gene expression profiles to discriminate between groups of patients with disparate risks for CLL progression. From an initial cohort of 130 patients, we identified 38 prognostic subnetworks that could predict the relative risk for disease progression requiring therapy from the time of sample collection, more accurately than established markers. The prognostic power of these subnetworks then was validated on 2 other cohorts of patients. We noted reduced divergence in gene expression between leukemia cells of CLL patients classified at diagnosis with aggressive versus indolent disease over time. The predictive subnetworks vary in levels of expression over time but exhibit increased similarity at later time points before therapy, suggesting that degenerate pathways apparently converge into common pathways that are associated with disease progression. As such, these results have implications for understanding cancer evolution and for the development of novel treatment strategies for patients with CLL.

Sign in / Sign up

Export Citation Format

Share Document