Machine learning helps improve diagnostic ability of subclinical keratoconus using Scheimpflug and OCT imaging modalities

Abstract Purpose To develop an automated classification system using a machine learning classifier to distinguish clinically unaffected eyes in patients with keratoconus from a normal control population based on a combination of Scheimpflug camera images and ultra-high-resolution optical coherence tomography (UHR-OCT) imaging data. Methods A total of 121 eyes from 121 participants were classified by 2 cornea experts into 3 groups: normal (50 eyes), with keratoconus (38 eyes) or with subclinical keratoconus (33 eyes). All eyes were imaged with a Scheimpflug camera and UHR-OCT. Corneal morphological features were extracted from the imaging data. A neural network was used to train a model based on these features to distinguish the eyes with subclinical keratoconus from normal eyes. Fisher’s score was used to rank the differentiable power of each feature. The receiver operating characteristic (ROC) curves were calculated to obtain the area under the ROC curves (AUCs). Results The developed classification model used to combine all features from the Scheimpflug camera and UHR-OCT dramatically improved the differentiable power to discriminate between normal eyes and eyes with subclinical keratoconus (AUC = 0.93). The variation in the thickness profile within each individual in the corneal epithelium extracted from UHR-OCT imaging ranked the highest in differentiating eyes with subclinical keratoconus from normal eyes. Conclusion The automated classification system using machine learning based on the combination of Scheimpflug camera data and UHR-OCT imaging data showed excellent performance in discriminating eyes with subclinical keratoconus from normal eyes. The epithelial features extracted from the OCT images were the most valuable in the discrimination process. This classification system has the potential to improve the differentiable power of subclinical keratoconus and the efficiency of keratoconus screening.

Download Full-text

Automatic classification of older electronic texts into the Universal Decimal Classification–UDC

Journal of Documentation ◽

10.1108/jd-06-2020-0092 ◽

2020 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Matjaž Kragelj ◽

Mirjana Kljajić Borštnar

Keyword(s):

Machine Learning ◽

Digital Libraries ◽

Classification Model ◽

Research Approach ◽

Automated Classification ◽

Content Type ◽

Machine Learning Classification ◽

Universal Decimal Classification ◽

Decimal Classification

PurposeThe purpose of this study is to develop a model for automated classification of old digitised texts to the Universal Decimal Classification (UDC), using machine-learning methods.Design/methodology/approachThe general research approach is inherent to design science research, in which the problem of UDC assignment of the old, digitised texts is addressed by developing a machine-learning classification model. A corpus of 70,000 scholarly texts, fully bibliographically processed by librarians, was used to train and test the model, which was used for classification of old texts on a corpus of 200,000 items. Human experts evaluated the performance of the model.FindingsResults suggest that machine-learning models can correctly assign the UDC at some level for almost any scholarly text. Furthermore, the model can be recommended for the UDC assignment of older texts. Ten librarians corroborated this on 150 randomly selected texts.Research limitations/implicationsThe main limitations of this study were unavailability of labelled older texts and the limited availability of librarians.Practical implicationsThe classification model can provide a recommendation to the librarians during their classification work; furthermore, it can be implemented as an add-on to full-text search in the library databases.Social implicationsThe proposed methodology supports librarians by recommending UDC classifiers, thus saving time in their daily work. By automatically classifying older texts, digital libraries can provide a better user experience by enabling structured searches. These contribute to making knowledge more widely available and useable.Originality/valueThese findings contribute to the field of automated classification of bibliographical information with the usage of full texts, especially in cases in which the texts are old, unstructured and in which archaic language and vocabulary are used.

Download Full-text

AUTOMATED SEGMENTATION OF HEEL FISSURES BASED ON THERMAL IMAGE PROCESSING AND CLASSIFICATION BASED ON MACHINE LEARNING ALGORITHMS

Biomedical Engineering Applications Basis and Communications ◽

10.4015/s1016237221500320 ◽

2021 ◽

pp. 2150032

Author(s):

Bhargavee Guhan ◽

S. Sowmiya ◽

U. Snekhalatha ◽

T. Rajalakshmi

Keyword(s):

Machine Learning ◽

Roc Curves ◽

Normal Subjects ◽

Machine Learning Algorithms ◽

Confidence Levels ◽

Learning Classifier ◽

Before And After ◽

Life Threatening ◽

The Right ◽

Simple Logistic

Heel fissures are cracks in the skin over the heels that lead to pain, discomfort and decreased confidence levels. If left untreated, they may also lead to infections and in rare cases, become life-threatening. Therefore, people with heel fissures generally try to find some remedy to relieve their symptoms. The objectives of this study are as follows: (1) To use thermal imaging to determine whether a characteristic difference in temperature exists in the heel fissure regions before and after performing heel therapy; (2) To segment the images and extract the features using [Formula: see text]-means, GLCM and SURF methods, respectively; (3) To implement machine learning classifier for classification on normal heel and fissured heel. A number of 30 heel fissure and 30 normal subjects were considered for this study. All the candidates were from the age group of 35–55 years. Thermography was used to acquire the images of heel regions, and the thermographs were analyzed for feature extraction. Naïve Bayes, Bagging, Random Forest, LMT and Simple Logistic classifiers were used for classification of the thermograms. After heel therapy, a 2.2% and 2.6% decrease in temperature was observed in the right and left heel, respectively. The GLCM mean is increased by 6% and 4.3% in the right and left heel, respectively. A considerable decrease in variance in the fissure regions after therapy has also been observed. All three classifiers were shown to be efficient, with Nave Bayes and Bagging classifier both showing accuracy of 89%. The ROC curves have also been obtained, with an area under curve equal to 0.97.

Download Full-text

Plant Leaf Classification and Comparative Analysis of Combined Feature Set Using Machine Learning Techniques

Traitement du signal ◽

10.18280/ts.380603 ◽

2021 ◽

Vol 38 (6) ◽

pp. 1587-1598

Author(s):

Sujith Ariyapadath

Keyword(s):

Machine Learning ◽

Classification System ◽

Research Work ◽

Evaluation Process ◽

Extraction Methods ◽

Classification Model ◽

Machine Learning Techniques ◽

Experimental Comparison ◽

Analytical Instruments ◽

Optimal Feature

The main purpose of this research work is to apply machine learning and image processing techniques for plant classification efficiently. In the plant classification system, the conventional method is time-consuming and needs to apply expensive analytical instruments. The automated plant classification system helps to predict plant classes easily. The most challenging part of the automated plant classification research is to extract unique features of leaves. This paper proposes a plant classification model using an optimal feature set with combined features. The proposed model is used to extract features from leaf images and applied to image classification algorithms. After the evaluation process, it is found that GIST, Local Binary Pattern and Pyramid Histogram Oriented Gradient have better results than others in this particular application. Combined these three features extraction techniques and selected the optimal feature set through Neighbourhood Component Analysis. The optimal feature set helps classify plants with maximum accuracy in minimal time. Here performed an extensive experimental comparison of the proposed optimal feature set and other feature extraction methods using different classifiers and tested on different data sets (Swedish Leaves, Flavia, D-Leaf). The results confirm that this optimal feature set with NCA using ANN classifier leads to better classification achieved 98.99% accuracy in 353.39 seconds.

Download Full-text

Identification and prediction of ALS subgroups using machine learning

10.1101/2021.04.02.21254844 ◽

2021 ◽

Author(s):

Faraz Faghri ◽

Fabian Brunn ◽

Anant Dadu ◽

Elisabetta Zucchi ◽

Ilaria Martinelli ◽

...

Keyword(s):

Machine Learning ◽

Classification System ◽

Population Based ◽

Classification Systems ◽

Supervised Machine Learning ◽

Population Substructure ◽

Clinical Parameters ◽

Independent Population ◽

Als Patients ◽

Clinical Subtype

Background The disease entity known as amyotrophic lateral sclerosis (ALS) is now known to represent a collection of overlapping syndromes. A better understanding of this heterogeneity and the ability to distinguish ALS subtypes would improve the clinical care of patients and enhance our understanding of the disease. Subtype profiles could be incorporated into the clinical trial design to improve our ability to detect a therapeutic effect. A variety of classification systems have been proposed over the years based on empirical observations, but it is unclear to what extent they genuinely reflect ALS population substructure. Methods We applied machine learning algorithms to a prospective, population-based cohort consisting of 2,858 Italian patients diagnosed with ALS for whom detailed clinical phenotype data were available. We replicated our findings in an independent population-based cohort of 1,097 Italian ALS patients. Findings We found that semi-supervised machine learning based on UMAP applied to the output of a multi-layered perceptron neural network produced the optimum clustering of the ALS patients in the discovery cohort. These clusters roughly corresponded to the six clinical subtypes defined by the Chiò classification system (bulbar ALS, respiratory ALS, flail arm ALS, classical ALS, pyramidal ALS, and flail leg ALS). The same clusters were identified in the replication cohort. A supervised learning approach based on ensemble learning identified twelve clinical parameters that predicted ALS clinical subtype with high accuracy (area under the curve = 0.94). Interpretation Our data-driven study provides insight into the ALS population's substructure and demonstrates that the Chiò classification system robustly identifies ALS subtypes. We provide an interactive website (https://share.streamlit.io/anant-dadu/machinelearningforals/main) so that clinical researchers can predict the clinical subtype of an ALS patient based on a small number of clinical parameters. Funding National Institute on Aging and the Italian Ministry of Health.

Download Full-text

A methodology for part classification with supervised machine learning

Artificial intelligence for engineering design analysis and manufacturing ◽

10.1017/s0890060418000197 ◽

2018 ◽

Vol 33 (1) ◽

pp. 100-113 ◽

Cited By ~ 3

Author(s):

Matteo Rucco ◽

Franca Giannini ◽

Katia Lupinetti ◽

Marina Monti

Keyword(s):

Machine Learning ◽

Ad Hoc ◽

Roc Curves ◽

Learning System ◽

Supervised Machine Learning ◽

Automated Classification ◽

Similarity Coefficients ◽

Analysis Process ◽

Set Up

AbstractIn this paper, we report on a data analysis process for the automated classification of mechanical components. In particular, here, we describe, how to implement a machine learning system for the automated classification of parts belonging to several sub-categories. We collect models that are typically used in the mechanical industry, and then we represent each object by a collection of features. We illustrate how to set-up a supervised multi-layer artificial neural network with an ad-hoc classification schema. We test our solution on a dataset formed by 2354 elements described by 875 features and spanned among 15 sub-categories. We state the accuracy of classification in terms of average area under ROC curves and the ability to classify 606 unknown 3D objects by similarity coefficients. Our parts’ classification system outperforms a classifier based on the Light Field Descriptor, which, as far as we know, actually represents the gold standard for the identification of most types of 3D mechanical objects.

Download Full-text

Corn Classification System based on Computer Vision

Symmetry ◽

10.3390/sym11040591 ◽

2019 ◽

Vol 11 (4) ◽

pp. 591 ◽

Cited By ~ 8

Author(s):

Xiaoming Li ◽

Baisheng Dai ◽

Hongmin Sun ◽

Weina Li

Keyword(s):

Machine Learning ◽

Computer Vision ◽

Maximum Likelihood ◽

Classification System ◽

Automated Classification ◽

Shape Features ◽

Segmentation Method ◽

Likelihood Estimator ◽

Color Features

Automated classification of corn is important for corn sorting in intelligent agriculture. This paper presents a reliable corn classification method based on techniques of computer vision and machine learning. To discriminate different damaged types of corns, a line profile segmentation method is firstly used to segment and separate a group of touching corns. Then, twelve color features and five shape features are extracted for each individual corn object. Finally, a maximum likelihood estimator is trained to classify normal and damaged corns. To evaluate the performance of the proposed method, a private dataset consisting of images of normal corn and six kinds of damage corns, including heat-damaged, germ-damaged, cob-rot-damaged, blue eye mold-damaged, insect-damaged, and surface mold-damaged, were collected in this work. The proposed method achieved an accuracy of 96.67% for the classification between normal corns and the first four common damaged corns, and an accuracy of 74.76% was achieved for the classification between normal corns and six kinds of damaged corns. The experimental results demonstrated the effectiveness of the proposed corn classification system.

Download Full-text

Classification system for documents with mine surveying data

Journal Of Applied Informatics ◽

10.37791/2687-0649-2021-16-5-66-81 ◽

2021 ◽

Vol 16 (95) ◽

pp. 66-81

Author(s):

Vladimir V. Eremeev ◽

◽

Mariya S. Tsyganova ◽

Alexander G. Ivashko ◽

◽

...

Keyword(s):

Machine Learning ◽

Classification System ◽

Test Sample ◽

Classification Problem ◽

Machine Learning Algorithms ◽

Document Management ◽

Classification Model ◽

Text Documents ◽

The Stability ◽

Mine Surveying

All enterprises engaged in exploration activities on the territory of the Russian Federation, are facing the need to formulate tasks for the mine surveyor service and control their execution. It affects enterprise’s workflow process. Due to it, a problem of organization of efficient document processing in electronic document management systems (timely identification of documents containing mine surveying data) takes place. The article presents possible solution of this problem – automated document classification system into EDMS in the form of optional add-on for 1C:Document Management. Within the classification system creation a preprocessing script for primary document texts, including cleaning, lemmatization, stop words removing, as well as preparation of input features for the classifier were developed and implemented. Applicability of different machine learning algorithms to solution of considering classification problem was studied, the values of hyperparameters providing the highest value of the ROC AUC metric were determined. The quality of all obtained models was assessed using metrics Precision, Recall and F-measures, the stability of the classification quality to changes in the input data was investigated. The identified problem of instability of classification results was solved by building and implementing a machine learning model in the form of ensemble of classifiers. Classification model (an ensemble of clusters) was tested on the set of real documents of Gazprom nedra Ltd; classiffication quality on the test sample by ROC AUC metric was 0,91. Except the classification module itself, developed system contains the storage database for learning outcomes, function library for organization of work with the database and API interfaces allowing to process classification requests, coming from external systems. These API interfaces, in particular, implement the ability to load saved trained models, validate data coming from external systems, preprocess input text documents, train new models and assess their quality, save both trained models and the results of their testing. Also the possibility of the additional training of the models on a new data was realized.

Download Full-text

An Automated Classification System for the Differentiation of Obstructive Lung Diseases based on the Textural Analysis of HRCT images

Journal of the Korean Radiological Society ◽

10.3348/jkrs.2007.57.1.21 ◽

2007 ◽

Vol 57 (1) ◽

pp. 21

Author(s):

Seong Hoon Park ◽

Joon Beom Seo ◽

Namkug Kim ◽

June Goo Lee ◽

Young Kyung Lee ◽

...

Keyword(s):

Classification System ◽

Lung Diseases ◽

Textural Analysis ◽

Automated Classification ◽

Obstructive Lung Diseases

Download Full-text

A Review on Heart Disease Detection Techniques

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse/v7i7/0200 ◽

2017 ◽

Vol 7 (7) ◽

pp. 395

Author(s):

. Anika ◽

Navpreet Kaur

Keyword(s):

Machine Learning ◽

Heart Disease ◽

Review Paper ◽

Vascular Diseases ◽

Disease Detection ◽

Automated Classification ◽

Feature Extraction Method ◽

Detection Techniques ◽

Cardio Vascular ◽

Public Domain Software

The paper exhibits a formal audit on early detection of heart disease which are the major cause of death. Computational science has potential to detect disease in prior stages automatically. With this review paper we describe machine learning for disease detection. Machine learning is a method of data analysis that automates analytical model building.Various techniques develop to predict cardiac disease based on cases through MRI was developed. Automated classification using machine learning. Feature extraction method using Cell Profiler and GLCM. Cell Profiler a public domain software, freely available is flourished by the Broad Institute's Imaging Platform and Glcm is a statistical method of examining texture .Various techniques to detect cardio vascular diseases.

Download Full-text