scholarly journals Deep learning for intelligent diagnosis in thyroid scintigraphy

2021 ◽  
Vol 49 (1) ◽  
pp. 030006052098284
Author(s):  
Tingting Qiao ◽  
Simin Liu ◽  
Zhijun Cui ◽  
Xiaqing Yu ◽  
Haidong Cai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Disease Diagnosis ◽  
Kappa Coefficient ◽  
Diagnostic Assessment ◽  
First Year ◽  
Thyroid Scintigraphy ◽  
Diagnostic Ability ◽  
The Third ◽  
Classification Time ◽  
Better Than

Objective To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy. Methods We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model’s performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents. Results The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided “diagnostic assistance” to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents. Conclusion DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves’ disease and subacute thyroiditis.

scholarly journals STUDY ON THE WATER BODY EXTRACTION USING GF-1 DATA BASED ON ADABOOST INTEGRATED LEARNING ALGORITHM

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 641-648
Author(s):  
J. Y. Sun ◽  
G. Z. Wang ◽  
G. J. He ◽  
D. C. Pu ◽  
W. Jiang ◽  
...  
Keyword(s):  
Surface Water ◽  
Water Body ◽  
Rapid Development ◽  
Kappa Coefficient ◽  
Water Bodies ◽  
Integrated Learning ◽  
Visual Interpretation ◽  
Adaboost Algorithm ◽  
Classification Time ◽  
Better Than

Abstract. Surface water system is an important part of global ecosystem, and the changes in surface water may lead to disasters, such as drought, waterlog, and water-borne diseases. The rapid development of remote sensing technology has supplied better strategies for water bodies extraction and further monitoring. In this study, AdaBoost and Random Forest (RF), two typical algorithms in integrated learning, were applied to extract water bodies in Chaozhou area (mainly located in Guangzhou Province, China) based on GF-1 data, and the Decision Tree (DT) was used for comparative tests to comprehensively evaluate the performance of classification algorithms listed above for surface water body extraction. The results showed that: (1) Compared with visual interpretation, AdaBoost performed better than RF in the extraction of several typical water bodies, such as rivers, lakes and ponds Moreover, the water extraction results of the strong classifiers using AdaBoost or RF were better than the weak basic classifiers. (2) For the quantitative accuracy statistics, the overall accuracy (96.5%) and kappa coefficient (93%) using AdaBoost exceeded those using RF (5.3% and 10.6%), respectively. The classification time of AdaBoost increased by 403 seconds and 918 seconds relative to RF and DT methods. However, in terms of visual interpretation, quantitative statistical accuracy and classification time, AdaBoost algorithm was more suitable for the water body extraction. (3) For the sample proportion comparison experiment of AdaBoost, four sampling proportions (0.1%, 0.2%, 1% and 2%) were chosen and 0.1% sampling proportion reached the optimum classification accuracy (93.9%) and kappa coefficient (87.8%).

scholarly journals Heart Diseases Diagnose via Mobile Application

2021 ◽  
Vol 11 (5) ◽  
pp. 2430
Author(s):  
Mesut Güven ◽  
Fırat Hardalaç ◽  
Kanat Özışık ◽  
Funda Tuna
Keyword(s):  
Artificial Intelligence ◽  
Mobile Application ◽  
Heart Diseases ◽  
Disease Diagnosis ◽  
Heart Sounds ◽  
Diagnostic Ability ◽  
Heart Abnormalities ◽  
Heart Disease Diagnosis ◽  
Clinical Experiments ◽  
Better Than

One of the oldest and most common methods of diagnosing heart abnormalities is auscultation. Even for experienced medical doctors, it is not an easy task to detect abnormal patterns in the heart sounds. Most digital stethoscopes are now capable of recording and transferring heart sounds. Moreover, it is proven that auscultation records can be classified as healthy or unhealthy via artificial intelligence techniques. In this work, an artificial intelligence-powered mobile application that works in a connectionless fashion is presented. According to the clinical experiments, the mobile application can detect heart abnormalities with approximately 92% accuracy, which is comparable to if not better than humans since only a small number of well-trained cardiologists can analyze auscultation records better than artificial intelligence. Using the diagnostic ability of artificial intelligence in a mobile application would change the classical way of auscultation for heart disease diagnosis.

scholarly journals Heart Diseases Diagnose via Artificial Intelligence-Powered Mobile Application

2021 ◽  
Author(s):  
Mesut Guven ◽  
Firat Hardalac ◽  
Kanat Ozisik ◽  
Funda Tuna
Keyword(s):  
Artificial Intelligence ◽  
Mobile Application ◽  
Heart Diseases ◽  
Disease Diagnosis ◽  
Heart Sounds ◽  
Diagnostic Ability ◽  
Heart Abnormalities ◽  
Heart Disease Diagnosis ◽  
Clinical Experiments ◽  
Better Than

One of the oldest and common methods of diagnosing heart abnormalities is auscultation. Even for experienced medical doctors, it is not an easy task to detect abnormal patterns in the heart sounds. Most of the digital stethoscopes are now capable of recording and transferring the heart sounds. Moreover, it is proven that auscultation records can be classified as healthy or unhealthy via artificial intelligence techniques. In this work, an artificial intelligence-powered mobile application that works in a connectionless fashion is presented. According to the clinical experiments, the mobile application can detect heart abnormalities with approximately 92% accuracy which is comparable if not better than humans since only a small number of well-trained cardiologists can analyze auscultation records better than artificial intelligence. Using the diagnostic ability of artificial intelligence in a mobile application would change the classical way of auscultation for heart disease diagnosis.

A Developmental Study of Intonation Recognition

1968 ◽  
Vol 11 (4) ◽  
pp. 825-832 ◽  
Author(s):  
Marilyn M. Corlew
Keyword(s):  
Significant Interaction ◽  
Multiple Choice ◽  
Semantic Content ◽  
First Grade ◽  
Choice Test ◽  
Developmental Study ◽  
Multiple Choice Test ◽  
The Third ◽  
Matching Test ◽  
Better Than

Two experiments investigated the information conveyed by intonation from speaker to listener. A multiple-choice test was devised to test the ability of 48 adults to recognize and label intonation when it was separated from all other meaning. Nine intonation contours whose labels were most agreed upon by adults were each matched with two English sentences (one with appropriate and one with inappropriate intonation and semantic content) to make a matching-test for children. The matching-test was tape-recorded and given to children in the first, third, and fifth grades (32 subjects in each grade). The first-grade children matched the intonations with significantly greater agreement than chance; but they agreed upon significantly fewer sentences than either the third or fifth graders. Some intonation contours were matched with significantly greater frequency than others. The performance of the girls was better than that of the boys on an impatient question and a simple command which indicates that there was a significant interaction between sex and intonation.

Using Connectionist Modules for Decision Support

1990 ◽  
Vol 29 (03) ◽  
pp. 167-181 ◽  
Author(s):  
G. Hripcsak
Keyword(s):  
Decision Support ◽  
Standard Deviation ◽  
Confidence Interval ◽  
Posterior Probability ◽  
Back Propagation ◽  
Connectionist Model ◽  
Test Set ◽  
The Third ◽  
Independent Test ◽  
Better Than

AbstractA connectionist model for decision support was constructed out of several back-propagation modules. Manifestations serve as input to the model; they may be real-valued, and the confidence in their measurement may be specified. The model produces as its output the posterior probability of disease. The model was trained on 1,000 cases taken from a simulated underlying population with three conditionally independent manifestations. The first manifestation had a linear relationship between value and posterior probability of disease, the second had a stepped relationship, and the third was normally distributed. An independent test set of 30,000 cases showed that the model was better able to estimate the posterior probability of disease (the standard deviation of residuals was 0.046, with a 95% confidence interval of 0.046-0.047) than a model constructed using logistic regression (with a standard deviation of residuals of 0.062, with a 95% confidence interval of 0.062-0.063). The model fitted the normal and stepped manifestations better than the linear one. It accommodated intermediate levels of confidence well.

Deep Learning in Disease Diagnosis: Models and Datasets

2020 ◽  
Vol 15 ◽  
Author(s):  
Deeksha Saxena ◽  
Mohammed Haris Siddiqui ◽  
Rajnish Kumar
Keyword(s):  
Biological Sciences ◽  
Machine Learning ◽  
Deep Learning ◽  
Disease Diagnosis ◽  
Learning Models ◽  
Data Types ◽  
Related Data ◽  
Abstract Level ◽  
Experimental Validations ◽  
Selection Of

Background: Deep learning (DL) is an Artificial neural network-driven framework with multiple levels of representation for which non-linear modules combined in such a way that the levels of representation can be enhanced from lower to a much abstract level. Though DL is used widely in almost every field, it has largely brought a breakthrough in biological sciences as it is used in disease diagnosis and clinical trials. DL can be clubbed with machine learning, but at times both are used individually as well. DL seems to be a better platform than machine learning as the former does not require an intermediate feature extraction and works well with larger datasets. DL is one of the most discussed fields among the scientists and researchers these days for diagnosing and solving various biological problems. However, deep learning models need some improvisation and experimental validations to be more productive. Objective: To review the available DL models and datasets that are used in disease diagnosis. Methods: Available DL models and their applications in disease diagnosis were reviewed discussed and tabulated. Types of datasets and some of the popular disease related data sources for DL were highlighted. Results: We have analyzed the frequently used DL methods, data types and discussed some of the recent deep learning models used for solving different biological problems. Conclusion: The review presents useful insights about DL methods, data types, selection of DL models for the disease diagnosis.

A Cohort study to compare Admission criteria and Academic performance among preclinical students at The Copperbelt University School of Medicine: complete enumeration (Preprint)

2019 ◽  
Author(s):  
Andrew Mwila
Keyword(s):  
Academic Performance ◽  
Cohort Study ◽  
Clinical Medicine ◽  
Average Score ◽  
First Year ◽  
Admission Criteria ◽  
Biomedical Sciences ◽  
Dental Surgery ◽  
School Of Medicine ◽  
Better Than

BACKGROUND The Copperbelt University is the second public University in Zambia. The School of Medicine has four major programs namely; Bachelor of Medicine and Surgery, Bachelor of Dental Surgery, Bachelor of Clinical Medicine and Bachelor of Biomedical sciences. The Copperbelt University School of Medicine runs a five-year training program for both the BDS and the MBCHB programs. Students are admitted into the Medical school after successfully completing their first year at the Main campus in the School of Natural Sciences with an average of 4 B grades or higher (B grade is a mark of 65 to 74%). OBJECTIVE The study was done to determine the association between admission criteria and academic performance among preclinical students. Hence, the study compares the academic performance among preclinical students admitted into the Bachelor of Dental Surgery and Bachelor of Medicine and Surgery at the Copperbelt University School of Medicine. METHODS This is a retrospective cohort study conducted at Michael Chilufya Sata School of medicine Campus. A pilot study was conducted with 30 BDS and 30 MBCHB students and the obtained information helped determine the sample size. SPSS was used to analyze the data. The study period lasted approximately 7 weeks at a cost of K1621. RESULTS In 2014, there was an improvement in average performance between 2nd and 3rd year for each program. An average score of 15.4 (SD 4.2) was obtained in 3rd year compared to 12.8 (SD 4.9) in 2nd year (p<0.001). Meanwhile, 3rd MB ChB mean score was 12.6 (SD 3.7) compared to 10.7 (SD 3.6) in 2nd years (p<0.05). However, in 2016, both programs, 3rd year mean scores were lower than 2nd year (MB ChB 2nd year mean score was 12.0 (SD 4.3) compared to 3rd year with a mean score of 9.5 (SD 4.5), p<0.001; BDS 2nd year mean score was 10.6 (SD 4.0) compared to 3rd year mean score of 8.2 (SD 3.4), p<0.01. On average MB ChB students performed better than BDS students in all the years (p<0.05), except in 2016 when the results were comparable. CONCLUSIONS Results from the study shows that entry criteria has a correlation to academic performance as students admitted with higher grades perform much better than those with lower grades.

1702–1703

2017 ◽  
Author(s):  
Frances Harris
Keyword(s):  
First Year ◽  
The Third

The third chapter traces the beginning of the partnership through the first year of Queen Anne’s reign, as Marlborough persuades Godolphin to return to office as Lord Treasurer and his ministerial partner, with the declared aim of ‘moderation’, that is, holding the balance between the Tories and Whigs on the basis of their support of the war. The role of Queen Anne’s husband Prince George is examined and Marlborough’s and Godolphin’s separate roles are explored, along with the significance of their extensive correspondence. Marlborough is unexpectedly successful in his first campaign, but his determination to obtain a grant from Parliament to support his dukedom jeopardizes Godolphin’s project for war-supply, and their rival Rochester contests control of the Treasury and therefore the war. Marlborough forces Rochester’s resignation and the partnership is confirmed when Marlborough’s only son dies shortly before he leaves for the Continent and he adopts Godolphin’s son as his heir.

scholarly journals Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Crouzet ◽  
Gwangjin Jeong ◽  
Rachel H. Chae ◽  
Krystal T. LoPresti ◽  
Cody E. Dunn ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prussian Blue ◽  
Processing Speed ◽  
Digital Pathology ◽  
Ground Truth ◽  
Individual Variability ◽  
Rgb Images ◽  
Cerebral Microhemorrhages ◽  
Phasor Analysis ◽  
Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Sign in / Sign up

Export Citation Format

Share Document