scholarly journals Design and Development of AI based Approach for Histopathology Cancer Screening and Identification

2022 ◽  
pp. 104-115
Author(s):  
Chetan Gedam
Keyword(s):  
Multiple Time ◽  
Clinical Images ◽  
Deep Feature ◽  
Universal Approach ◽  
Screening And Identification ◽  
Diagnosis Of Cancer ◽  
Cancer Types ◽  
Malignant Lesions ◽  
Multiple Time Points ◽  
Deep Feature Extraction

Cancer is a heterogeneous disorder comprising various types and sub-types. Early detection, screening, and diagnosis of cancer types are necessary for facilitating cancer research in early diagnosis, management, and the evolution of successful therapies. Existing methodologies were only able to classify and diagnose a single variety of cancer based on a homogeneous dataset but more focused on predicting patient survivability then cure. This research defines a machine learning-based methodology to develop an universal approach in diagnosis, detection, symptoms-based prediction, and screening of histopathology cancer, their types, and sub types using a heterogeneous dataset based on images and scans. In this architecture, we use VGG-19 based 3D-Convolutional Neural Network for deep feature extraction and later perform regression using a random forest algorithm. We create a heterogeneous dataset consisting of results from laboratory tests, imaging tests and biopsy reports, not only relying on clinical images. Initially, we categorize tumors and lesions as benign or malignant and classify the malignant lesions into their sub-types, detecting their severity and growth rate. Our system is designed to predict risk at multiple time-points, leverage optional risk factors if they are available and produce predictions that are consistent across mammography machines. We found the classification accuracy for categorizing tumors as cancerous to be 95% whereas the accuracy for classification of malignant lesions into their sub-types to be 94%..

scholarly journals Comprehensive characterization of 536 patient-derived xenograft models prioritizes candidates for targeted treatment

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Hua Sun ◽  
Song Cao ◽  
R. Jay Mashl ◽  
Chia-Kuei Mo ◽  
Simone Zaccaria ◽  
...  
Keyword(s):  
Human Tumors ◽  
Multiple Time ◽  
Cancer Treatments ◽  
Whole Genome Duplications ◽  
Patient Derived Xenograft ◽  
Genome Duplications ◽  
Genomic Characterization ◽  
Cancer Types ◽  
Multiple Time Points ◽  
Pdx Models

AbstractDevelopment of candidate cancer treatments is a resource-intensive process, with the research community continuing to investigate options beyond static genomic characterization. Toward this goal, we have established the genomic landscapes of 536 patient-derived xenograft (PDX) models across 25 cancer types, together with mutation, copy number, fusion, transcriptomic profiles, and NCI-MATCH arms. Compared with human tumors, PDXs typically have higher purity and fit to investigate dynamic driver events and molecular properties via multiple time points from same case PDXs. Here, we report on dynamic genomic landscapes and pharmacogenomic associations, including associations between activating oncogenic events and drugs, correlations between whole-genome duplications and subclone events, and the potential PDX models for NCI-MATCH trials. Lastly, we provide a web portal having comprehensive pan-cancer PDX genomic profiles and source code to facilitate identification of more druggable events and further insights into PDXs’ recapitulation of human tumors.

scholarly journals Physical activity levels among ovarian cancer survivors: a prospective longitudinal cohort study

2021 ◽  
pp. ijgc-2020-002107
Author(s):  
Tamara Jones ◽  
Carolina Sandler ◽  
Dimitrios Vagenas ◽  
Monika Janda ◽  
Andreas Obermair ◽  
...  
Keyword(s):  
Physical Activity ◽  
Ovarian Cancer ◽  
Stage Iv ◽  
Multiple Time ◽  
Activity Levels ◽  
Prospective Longitudinal Study ◽  
Physical Activity Advice ◽  
Physical Activity Levels ◽  
Multiple Time Points ◽  
Prospective Longitudinal

ObjectivePhysical activity following cancer diagnosis is associated with improved outcomes, including potential survival benefits, yet physical activity levels among common cancer types tend to decrease following diagnosis and remain low. Physical activity levels following diagnosis of less common cancers, such as ovarian cancer, are less known. The objectives of this study were to describe physical activity levels and to explore characteristics associated with physical activity levels in women with ovarian cancer from pre-diagnosis to 2 years post-diagnosis.MethodsAs part of a prospective longitudinal study, physical activity levels of women with ovarian cancer were assessed at multiple time points between pre-diagnosis and 2 years post-diagnosis. Physical activity levels and change in physical activity were described using metabolic equivalent task hours and minutes per week, and categorically (sedentary, insufficiently, or sufficiently active). Generalized Estimating Equations were used to explore whether participant characteristics were related to physical activity levels.ResultsA total of 110 women with ovarian cancer with a median age of 62 years (range 33–88) at diagnosis were included. 53–57% of the women were sufficiently active post-diagnosis, although average physical activity levels for the cohort were below recommended levels throughout the 2-year follow-up period (120–142.5min/week). A decrease or no change in post-diagnosis physical activity was reported by 44–60% of women compared with pre-diagnosis physical activity levels. Women diagnosed with stage IV disease, those earning a lower income, those receiving chemotherapy, and those currently smoking or working were more likely to report lower physical activity levels and had increased odds of being insufficiently active or sedentary.ConclusionsInterventions providing patients with appropriate physical activity advice and support for behavior change could potentially improve physical activity levels and health outcomes.

scholarly journals The molecular make up of smoldering myeloma highlights the evolutionary pathways leading to multiple myeloma

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Eileen M. Boyle ◽  
Shayu Deshpande ◽  
Ruslana Tytarenko ◽  
Cody Ashby ◽  
Yan Wang ◽  
...  
Keyword(s):  
Tumour Suppressor Genes ◽  
Multiple Time ◽  
Clonal Structure ◽  
Time To Progression ◽  
Novel Mutations ◽  
Evolutionary Patterns ◽  
Risk Of Progression ◽  
Multiple Time Points ◽  
Smoldering Myeloma ◽  
Copy Number Changes

AbstractSmoldering myeloma (SMM) is associated with a high-risk of progression to myeloma (MM). We report the results of a study of 82 patients with both targeted sequencing that included a capture of the immunoglobulin and MYC regions. By comparing these results to newly diagnosed myeloma (MM) we show fewer NRAS and FAM46C mutations together with fewer adverse translocations, del(1p), del(14q), del(16q), and del(17p) in SMM consistent with their role as drivers of the transition to MM. KRAS mutations are associated with a shorter time to progression (HR 3.5 (1.5–8.1), p = 0.001). In an analysis of change in clonal structure over time we studied 53 samples from nine patients at multiple time points. Branching evolutionary patterns, novel mutations, biallelic hits in crucial tumour suppressor genes, and segmental copy number changes are key mechanisms underlying the transition to MM, which can precede progression and be used to guide early intervention strategies.

Towards Robust Localization Deep Feature Extraction by CNN

2020 ◽  
Author(s):  
Erik Carlbaum ◽  
Sina Sharif Mansouri ◽  
Christoforos Kanellakis ◽  
Anton Koval ◽  
George Nikolakopoulos
Keyword(s):  
Feature Extraction ◽  
Deep Feature ◽  
Robust Localization ◽  
Deep Feature Extraction

scholarly journals Use of TanDEM-X and SRTM-C Data for Detection of Deforestation Caused by Bark Beetle in Central European Mountains

2021 ◽  
Vol 13 (15) ◽  
pp. 3042
Author(s):  
Kateřina Gdulová ◽  
Jana Marešová ◽  
Vojtěch Barták ◽  
Marta Szostak ◽  
Jaroslav Červenka ◽  
...  
Keyword(s):  
Bark Beetle ◽  
Synergistic Effects ◽  
Canopy Height ◽  
Surface Model ◽  
Multiple Time ◽  
Central European ◽  
Time Points ◽  
Bohemian Forest ◽  
Multiple Time Points ◽  
Surrounding Areas

The availability of global digital elevation models (DEMs) from multiple time points allows their combination for analysing vegetation changes. The combination of models (e.g., SRTM and TanDEM-X) can contain errors, which can, due to their synergistic effects, yield incorrect results. We used a high-resolution LiDAR-derived digital surface model (DSM) to evaluate the accuracy of canopy height estimates of the aforementioned global DEMs. In addition, we subtracted SRTM and TanDEM-X data at 90 and 30 m resolutions, respectively, to detect deforestation caused by bark beetle disturbance and evaluated the associations of their difference with terrain characteristics. The study areas covered three Central European mountain ranges and their surrounding areas: Bohemian Forest, Erzgebirge, and Giant Mountains. We found that vertical bias of SRTM and TanDEM-X, relative to the canopy height, is similar with negative values of up to −2.5 m and LE90s below 7.8 m in non-forest areas. In forests, the vertical bias of SRTM and TanDEM-X ranged from −0.5 to 4.1 m and LE90s from 7.2 to 11.0 m, respectively. The height differences between SRTM and TanDEM-X show moderate dependence on the slope and its orientation. LE90s for TDX-SRTM differences tended to be smaller for east-facing than for west-facing slopes, and varied, with aspect, by up to 1.5 m in non-forest areas and 3 m in forests, respectively. Finally, subtracting SRTM and NASA DEMs from TanDEM-X and Copernicus DEMs, respectively, successfully identified large areas of deforestation caused by hurricane Kyril in 2007 and a subsequent bark beetle disturbance in the Bohemian Forest. However, local errors in TanDEM-X, associated mainly with forest-covered west-facing slopes, resulted in erroneous identification of deforestation. Therefore, caution is needed when combining SRTM and TanDEM-X data in multitemporal studies in a mountain environment. Still, we can conclude that SRTM and TanDEM-X data represent suitable near global sources for the identification of deforestation in the period between the time points of their acquisition.

scholarly journals Associations of Binge Drinking With Vascular Brain Injury and Atrophy in Older American Indians: The Strong Heart Study

2021 ◽  
Vol 33 (7-8_suppl) ◽  
pp. 51S-59S
Author(s):  
Jordan P. Lewis ◽  
Astrid M. Suchy-Dicey ◽  
Carolyn Noonan ◽  
Valarie Blue Bird Jernigan ◽  
Jason G. Umans ◽  
...  
Keyword(s):  
Brain Injury ◽  
Binge Drinking ◽  
American Indians ◽  
Multiple Time ◽  
Heart Study ◽  
Neurological Risk ◽  
The Us ◽  
Large Cohort Study ◽  
Magnetic Resonance Imaging Mri ◽  
Multiple Time Points

Objectives: American Indians (AIs) generally consume less alcohol than the US general population; however, the prevalence of alcohol use disorder is higher. This is the first large cohort study to examine binge drinking as a risk factor for vascular brain injury (VBI). Methods: We used linear and Poisson regression to examine the association of self-reported binge drinking with VBI, measured via magnetic resonance imaging (MRI), in 817 older AIs who participated in the Strong Heart and Cerebrovascular Disease and Its Consequences in American Indians studies. Results: Any binge drinking at multiple time-points was associated with increased sulcal (β = 0.360, 95% CI [0.079, 0.641]) and ventricle dilatation (β = 0.512, 95% CI [0.174, 0.850]) compared to no binge drinking. Discussion: These observed associations are consistent with previous findings. Identifying how binge drinking may contribute to VBI in older AIs may suggest modifiable health behaviors for neurological risk reduction and disease prevention.

Smart paddy field monitoring system using deep learning and IoT

2021 ◽  
pp. 1063293X2198894
Author(s):  
Prabira Kumar Sethy ◽  
Santi Kumari Behera ◽  
Nithiyakanthan Kannan ◽  
Sridevi Narayanan ◽  
Chanki Pandey
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Transfer Learning ◽  
Paddy Field ◽  
New Technology ◽  
Support Vector ◽  
Nitrogen Status ◽  
Deep Feature ◽  
Per Capita ◽  
Deep Feature Extraction

Paddy is an essential nutrient worldwide. Rice gives 21% of worldwide human per capita energy and 15% of per capita protein. Asia represented 60% of the worldwide populace, about 92% of the world’s rice creation, and 90% of worldwide rice utilization. With the increase in population, the demand for rice is increased. So, the productivity of farming is needed to be enhanced by introducing new technology. Deep learning and IoT are hot topics for research in various fields. This paper suggested a setup comprising deep learning and IoT for monitoring of paddy field remotely. The vgg16 pre-trained network is considered for the identification of paddy leaf diseases and nitrogen status estimation. Here, two strategies are carried out to identify images: transfer learning and deep feature extraction. The deep feature extraction approach is combined with a support vector machine (SVM) to classify images. The transfer learning approach of vgg16 for identifying four types of leaf diseases and prediction of nitrogen status results in 79.86% and 84.88% accuracy. Again, the deep features of Vgg16 and SVM results for identifying four types of leaf diseases and prediction of nitrogen status have achieved an accuracy of 97.31% and 99.02%, respectively. Besides, a framework is suggested for monitoring of paddy field remotely based on IoT and deep learning. The suggested prototype’s superiority is that it controls temperature and humidity like the state-of-the-art and can monitor the additional two aspects, such as detecting nitrogen status and diseases.

scholarly journals Inferring time series chromatin states for promoter-enhancer pairs based on Hi-C data

BMC Genomics ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Henriette Miko ◽  
Yunjiang Qiu ◽  
Bjoern Gaertner ◽  
Maike Sander ◽  
Uwe Ohler
Keyword(s):  
Time Series ◽  
Histone Modifications ◽  
Gene Activation ◽  
Expectation Maximization Algorithm ◽  
Chromatin State ◽  
Open Chromatin ◽  
Multiple Time ◽  
Enhancer Activity ◽  
Chromatin States ◽  
Multiple Time Points

Abstract Background Co-localized combinations of histone modifications (“chromatin states”) have been shown to correlate with promoter and enhancer activity. Changes in chromatin states over multiple time points (“chromatin state trajectories”) have previously been analyzed at promoter and enhancers separately. With the advent of time series Hi-C data it is now possible to connect promoters and enhancers and to analyze chromatin state trajectories at promoter-enhancer pairs. Results We present TimelessFlex, a framework for investigating chromatin state trajectories at promoters and enhancers and at promoter-enhancer pairs based on Hi-C information. TimelessFlex extends our previous approach Timeless, a Bayesian network for clustering multiple histone modification data sets at promoter and enhancer feature regions. We utilize time series ATAC-seq data measuring open chromatin to define promoters and enhancer candidates. We developed an expectation-maximization algorithm to assign promoters and enhancers to each other based on Hi-C interactions and jointly cluster their feature regions into paired chromatin state trajectories. We find jointly clustered promoter-enhancer pairs showing the same activation patterns on both sides but with a stronger trend at the enhancer side. While the promoter side remains accessible across the time series, the enhancer side becomes dynamically more open towards the gene activation time point. Promoter cluster patterns show strong correlations with gene expression signals, whereas Hi-C signals get only slightly stronger towards activation. The code of the framework is available at https://github.com/henriettemiko/TimelessFlex. Conclusions TimelessFlex clusters time series histone modifications at promoter-enhancer pairs based on Hi-C and it can identify distinct chromatin states at promoter and enhancer feature regions and their changes over time.

Sign in / Sign up

Export Citation Format

Share Document