scholarly journals NEW APPROACH TO DETECTION OF ABNORMAL CERVICAL CELLS

2019 ◽  
Vol 10 (2) ◽  
Author(s):  
Branislava Jeftić ◽  
Lidija Matija ◽  
Đuro Koruga
Keyword(s):  
Binary Classification ◽  
Imaging Spectroscopy ◽  
Classification Model ◽  
Cancer Tissue ◽  
Random Forest Classification ◽  
Screening Programs ◽  
Forest Classification ◽  
Papanicolaou Smears ◽  
Cervical Cells

Optomagnetic Imaging Spectroscopy demonstrated high percentages of accuracy in biological sample classification, namely cervical, oral and colon samples. It enables detection of abnormal tissue and cells, and thus can be used as a diagnostic tool in screening programs. Papanicolaou smears and liquid based cytology samples were analysed in previous studies on cervical cancer detection by Optomagnetic Imaging Spectroscopy and it was shown that this method can diferentiate normal healthy tissue from the cancer tissue. So far, only binary classification of the cervical samples was performed based on optomagnetic spectra of the samples. In this paper, classification of the Papanicolaou smears into four groups (II, III, IV and V Papanicolaou groups) was tested with the Random Forest classification model that demonstrated interclass sensitivity of 49.25%, 58.97%, 50%, 44.44% for II, III, IV and V Papanicolaou group respectively, and specificity of 65.26%, 54.76%, 98.70% and 98.69% for II, III, IV and V Papanicolaou group respectively.

scholarly journals Fully Automated Detection of Paramagnetic Rims in Multiple Sclerosis Lesions on 3T Susceptibility-Based MR Imaging

2020 ◽  
Author(s):  
Carolyn Lou ◽  
Pascal Sati ◽  
Martina Absinta ◽  
Kelly Clark ◽  
Jordan D. Dworkin ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Severe Disease ◽  
Area Under The Curve ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
List Type ◽  
Training Set ◽  
Random Forest Classification ◽  
Automated Method ◽  
Forest Classification

AbstractBackground and PurposeThe presence of a paramagnetic rim around a white matter lesion has recently been shown to be a hallmark of a particular pathological type of multiple sclerosis (MS) lesion. Increased prevalence of these paramagnetic rim lesions (PRLs) is associated with a more severe disease course in MS. The identification of these lesions is time-consuming to perform manually. We present a method to automatically detect PRLs on 3T T2*-phase images.MethodsT1-weighted, T2-FLAIR, and T2*-phase MRI of the brain were collected at 3T for 19 subjects with MS. The images were then processed with lesion segmentation, lesion center detection, lesion labelling, and lesion-level radiomic feature extraction. A total of 877 lesions were identified, 118 (13%) of which contained a paramagnetic rim. We divided our data into a training set (15 patients, 673 lesions) and a testing set (4 patients, 204 lesions). We fit a random forest classification model on the training set and assessed our ability to classify lesions as PRL on the test set.ResultsThe number of PRLs per subject identified via our automated lesion labelling method was highly correlated with the gold standard count of PRLs per subject, r = 0.91 (95% CI [0.79, 0.97]). The classification algorithm using radiomic features can classify a lesion as PRL or not with an area under the curve of 0.80 (95% CI [0.67, 0.86]).ConclusionThis study develops a fully automated technique for the detection of paramagnetic rim lesions using standard T1 and FLAIR sequences and a T2*phase sequence obtained on 3T MR images.HighlightsA fully automated method for both the identification and classification of paramagnetic rim lesions is proposed.Radiomic features in conjunction with machine learning algorithms can accurately classify paramagnetic rim lesions.Challenges for classification are largely driven by heterogeneity between lesions, including equivocal rim signatures and lesion location.

Random forest classification of crop type using multi-temporal TerraSAR-X dual-polarimetric data

2014 ◽  
Vol 5 (2) ◽  
pp. 157-164 ◽  
Author(s):  
Rei Sonobe ◽  
Hiroshi Tani ◽  
Xiufeng Wang ◽  
Nobuyuki Kobayashi ◽  
Hideki Shimamura
Keyword(s):  
Random Forest ◽  
Random Forest Classification ◽  
Forest Classification ◽  
Crop Type ◽  
Multi Temporal

scholarly journals CLASSIFICATION MODEL FOR LEARNING DISABILITIES IN ELEMENTARY SCHOOL PUPILS

2019 ◽  
Vol 17 (1) ◽  
pp. 9-20
Author(s):  
I. O. AWOYELU ◽  
I. A. AGBOOLA
Keyword(s):  
Learning Disabilities ◽  
Learning Disability ◽  
Primary Schools ◽  
Binary Classification ◽  
Back Propagation ◽  
Principal Component ◽  
General Term ◽  
Classification Model ◽  
Back Propagation Algorithm

Learning disability is a general term that describes specific kinds of learning problems.  Although, Learning Disability cannot be cured medically, there exist several methods for detecting learning disabilities in a child. Existing methods of classification of learning disabilities in children are binary classification – either a child is normal or learning disabled. The focus of this paper is to extend the binary classification to multi-label classification of learning disabilities. This paper formulated and simulated a classification model for learning disabilities in primary school pupils. Information containing the symptoms of learning disabilities in pupils were elicited by administering five hundred (500) questionnaire to teachers of Primary One to Four pupils in fifteen government owned elementary schools within Ife Central Local Government Area, Ile-Ife of Osun State. The classification model was formulated using Principal Component Analysis, rule based system and back propagation algorithm. The formulated model was simulated using Waikatto Environment for Knowledge Analysis (WEKA) version 3.7.2. The performance of the model was evaluated using precision and accuracy. The classification model of primary one, primary two, primary three and primary four yielded precision rate of 95%, 91.18%, 93.10% and 93.60% respectively while the accuracy results were 95.00%, 91.18%, 93.10% and 93.60% respectively. The results obtained showed that the developed model proved to be accurate and precise in classifying pupils with learning disabilities in primary schools. The model can be adopted for the management of pupils with learning disabilities.  

scholarly journals Epigenetic Analyses of Alcohol Consumption in Combustible and Non-Combustible Nicotine Product Users

Epigenomes ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 18
Author(s):  
Kelsey Dawes ◽  
Luke Sampson ◽  
Rachel Reimer ◽  
Shelly Miller ◽  
Robert Philibert ◽  
...  
Keyword(s):  
Alcohol Consumption ◽  
Self Report ◽  
Classification Model ◽  
Public And Private ◽  
Random Forest Classification ◽  
Epigenetic Biomarkers ◽  
Forest Classification ◽  
Heavy Alcohol Consumption ◽  
Relationship Of ◽  
The Relationship

Alcohol and tobacco use are highly comorbid and exacerbate the associated morbidity and mortality of either substance alone. However, the relationship of alcohol consumption to the various forms of nicotine-containing products is not well understood. To improve this understanding, we examined the relationship of alcohol consumption to nicotine product use using self-report, cotinine, and two epigenetic biomarkers specific for smoking (cg05575921) and drinking (Alcohol T Scores (ATS)) in n = 424 subjects. Cigarette users had significantly higher ATS values than the other groups (p < 2.2 × 10−16). Using the objective biomarkers, the intensity of nicotine and alcohol consumption was correlated in both the cigarette and smokeless users (R = −0.66, p = 3.1 × 10−14; R2 = 0.61, p = 1.97 × 10−4). Building upon this idea, we used the objective nicotine biomarkers and age to build and test a Balanced Random Forest classification model for heavy alcohol consumption (ATS > 2.35). The model performed well with an AUC of 0.962, 89.3% sensitivity, and 85% specificity. We conclude that those who use non-combustible nicotine products drink significantly less than smokers, and cigarette and smokeless users drink more with heavier nicotine use. These findings further highlight the lack of informativeness of self-reported alcohol consumption and suggest given the public and private health burden of alcoholism, further research into whether using non-combustible nicotine products as a mode of treatment for dual users should be considered.

scholarly journals Calcium Spark Detection and Event-Based Classification of Single Cardiomyocyte Using Deep Learning

2021 ◽  
Vol 12 ◽  
Author(s):  
Shengqi Yang ◽  
Ran Li ◽  
Jiliang Chen ◽  
Zhen Li ◽  
Zhangqin Huang ◽  
...  
Keyword(s):  
Binary Classification ◽  
Detection Algorithm ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Detection Methods ◽  
Cardiac Pathology ◽  
Powerful Approach ◽  
Whole Heart ◽  
Event Based

Ca2+ sparks are the elementary Ca2+ release events in cardiomyocytes, altered properties of which lead to impaired Ca2+ handling and finally contribute to cardiac pathology under various diseases. Despite increasing use of machine-learning algorithms in deciphering the content of biological and medical data, Ca2+ spark images and data are yet to be deeply learnt and analyzed. In the present study, we developed a deep residual convolutional neural network method to detect Ca2+ sparks. Compared to traditional detection methods with arbitrarily defined thresholds to distinguish signals from noises, our new method detected more Ca2+ sparks with lower amplitudes but similar spatiotemporal distributions, thereby indicating that our new algorithm detected many very weak events that are usually omitted when using traditional detection methods. Furthermore, we proposed an event-based logistic regression and binary classification model to classify single cardiomyocytes using Ca2+ spark characteristics, which to date have generally been used only for simple statistical analyses and comparison between normal and diseased groups. Using this new detection algorithm and classification model, we succeeded in distinguishing wild type (WT) vs RyR2-R2474S± cardiomyocytes with 100% accuracy, and vehicle vs isoprenaline-insulted WT cardiomyocytes with 95.6% accuracy. The model can be extended to judge whether a small number of cardiomyocytes (and so the whole heart) are under a specific cardiac disease. Thus, this study provides a novel and powerful approach for the research and application of calcium signaling in cardiac diseases.

scholarly journals Keeping it classy: classification of live fish and ghost PIT tags detected with a mobile PIT tag interrogation system using an innovative analytical approach

2020 ◽  
Vol 77 (9) ◽  
pp. 1564-1573
Author(s):  
J. Benjamin Stout ◽  
Mary Conner ◽  
Phaedra Budy ◽  
Peter Mackinnon ◽  
Mark McKinstry
Keyword(s):  
Error Rate ◽  
Classification Model ◽  
Parameter Estimates ◽  
Pit Tag ◽  
Endangered Fish ◽  
Random Forest Classification ◽  
Management Actions ◽  
Live Fish ◽  
Forest Classification ◽  
Input Structure

The ability of passive integrated transponder (PIT) tag data to improve demographic parameter estimates has led to the rapid advancement of PIT tag systems. However, ghost tags create uncertainty about detected tag status (i.e., live fish or ghost tag) when using mobile interrogation systems. We developed a method to differentiate between live fish and ghost tags using a random forest classification model with a novel data input structure based on known fate PIT tag detections in the San Juan River (New Mexico, Colorado, and Utah, USA). We used our model to classify detected tags with an overall error rate of 6.8% (1.6% ghost tags error rate and 21.8% live fish error rate). The important variables for classification were related to distance moved and response to monsoonal flood flows; however, habitat variables did not appear to influence model accuracy. Our results and approach allow the use of mobile detection data with confidence and allow for greater accuracy in movement, distribution, and habitat use studies, potentially helping identify influential management actions that would improve our ability to conserve and recover endangered fish.

scholarly journals Identifying new X-ray binary candidates in M31 using random forest classification

2020 ◽  
Vol 492 (4) ◽  
pp. 5075-5088 ◽  
Author(s):  
R M Arnason ◽  
P Barmby ◽  
N Vulic
Keyword(s):  
Random Forest ◽  
High Probability ◽  
Binary Classification ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Photon Flux ◽  
X Ray ◽  
Random Forest Classification ◽  
Forest Classification ◽  
Cent Level

ABSTRACT Identifying X-ray binary (XRB) candidates in nearby galaxies requires distinguishing them from possible contaminants including foreground stars and background active galactic nuclei. This work investigates the use of supervised machine learning algorithms to identify high-probability XRB candidates. Using a catalogue of 943 Chandra X-ray sources in the Andromeda galaxy, we trained and tested several classification algorithms using the X-ray properties of 163 sources with previously known types. Amongst the algorithms tested, we find that random forest classifiers give the best performance and work better in a binary classification (XRB/non-XRB) context compared to the use of multiple classes. Evaluating our method by comparing with classifications from visible-light and hard X-ray observations as part of the Panchromatic Hubble Andromeda Treasury, we find compatibility at the 90 per cent level, although we caution that the number of source in common is rather small. The estimated probability that an object is an XRB agrees well between the random forest binary and multiclass approaches and we find that the classifications with the highest confidence are in the XRB class. The most discriminating X-ray bands for classification are the 1.7–2.8, 0.5–1.0, 2.0–4.0, and 2.0–7.0 keV photon flux ratios. Of the 780 unclassified sources in the Andromeda catalogue, we identify 16 new high-probability XRB candidates and tabulate their properties for follow-up.

Sign in / Sign up

Export Citation Format

Share Document