CytoNet, a Versatile Web-Based System for Accessing Advisory Cytology Services

This article describes how the use of artificial intelligence applications as a consultation tool on a cytological laboratory’s daily routine has been suggested for several decades. In addition to the use of high-resolution thyroid ultrasonography and fine-needle aspiration cytology, a further reduction of the number of unnecessary thyroidectomies can be achieved through the access to such techniques. Despite the evident advantages, artificial intelligence applications hardly ever find their way to end-users due to the specialized knowledge necessary for designing and using them, as well as the users’ unfamiliarity with the required technology. The authors aimed to design an easy-to-use online platform (CytoNet) that gives access to a learning vector quantizer neural network (LVQ NN) that discriminates benign from malignant thyroid lesions to users (medical doctors) with no specialized technical background on artificial intelligence. CytoNet, a Versatile WebBased System for Accessing Advisory Cytology Services: Application of Artificial Intelligence

[1]  Gustavo K. Rohde,et al.  A Linear Optimal Transportation Framework for Quantifying and Visualizing Variations in Sets of Images , 2012, International Journal of Computer Vision.

[2]  B Cochand-Priollet,et al.  Learning vector quantizer in the investigation of thyroid lesions. , 1999, Analytical and quantitative cytology and histology.

[3]  Gustavo K. Rohde,et al.  Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning , 2014, Medical Image Anal..

[4]  Cenk Sahin,et al.  A Radial Basis Function Neural Network (RBFNN) Approach for Structural Classification of Thyroid Diseases , 2008, Journal of Medical Systems.

[5]  José M. Grañeda,et al.  An Artificial Intelligence Approach to Thrombophilia Risk , 2017 .

[6]  Petros Karakitsos,et al.  Cascaded learning vector quantizer neural networks for the discrimination of thyroid lesions. , 2011, Analytical and quantitative cytology and histology.

[7]  Panagiota Spyridonos,et al.  Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images , 2008, Comput. Biol. Medicine.

[8]  Roberto Tagliaferri,et al.  Neural network analysis for evaluating cancer risk in thyroid nodules with an indeterminate diagnosis at aspiration cytology: identification of a low-risk subgroup. , 2004, Thyroid : official journal of the American Thyroid Association.

[9]  B Cochand-Priollet,et al.  Potential of the back propagation neural network in the morphologic examination of thyroid lesions. , 1996, Analytical and quantitative cytology and histology.

[10]  Konstantinos Koutroumbas,et al.  Discriminating benign from malignant thyroid lesions using artificial intelligence and statistical selection of morphometric features. , 2006, Oncology reports.

[11]  Charalampos Siristatidis,et al.  Artificial Intelligence in IVF: A Need , 2011, Systems biology in reproductive medicine.

[12]  G. Jayaram,et al.  A logistic model for thyroid lesions , 1992, Diagnostic cytopathology.

[13]  N. F. Friend,et al.  A step-wise logistic regression analysis of papillary carcinoma of the thyroid. , 1986, Acta cytologica.

[14]  P. Rout,et al.  Diagnostic value of qualitative and quantitative variables in thyroid lesions , 1999, Cytopathology : official journal of the British Society for Clinical Cytology.

[15]  D. Koutsouris,et al.  Classification of fetal heart rate tracings based on wavelet-transform and self-organizing-map neural networks , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Dayou Liu,et al.  Design of an Enhanced Fuzzy k-nearest Neighbor Classifier Based Computer Aided Diagnostic System for Thyroid Disease , 2012, Journal of Medical Systems.

[17]  K. Blekas,et al.  Fuzzy neural network-based texture analysis of ultrasonic images , 2000, IEEE Engineering in Medicine and Biology Magazine.

[18]  D. Koutsouris,et al.  Computerised intrapartum diagnosis of fetal hypoxia based on fetal heart rate monitoring and fetal pulse oximetry recordings utilising wavelet analysis and neural networks , 2002, BJOG : an international journal of obstetrics and gynaecology.

[19]  H. Gharib,et al.  Fine-Needle Aspiration Biopsy of the Thyroid Gland , 2015 .

[20]  D. Cavouras,et al.  Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. , 2005, Ultrasound in medicine & biology.

[21]  Lu-Cheng Zhu,et al.  A Model to Discriminate Malignant from Benign Thyroid Nodules Using Artificial Neural Network , 2013, PloS one.

[22]  B. Gopinath,et al.  Support Vector Machine based diagnostic system for thyroid cancer using statistical texture features. , 2013, Asian Pacific journal of cancer prevention : APJCP.

[23]  Abraham Pouliakis,et al.  Artificial neural networks in gynaecological diseases: current and potential future applications. , 2010, Medical science monitor : international medical journal of experimental and clinical research.

[24]  H. Gharib,et al.  Epidemiology of thyroid nodules. , 2008, Best practice & research. Clinical endocrinology & metabolism.

[25]  Massimo Buscema,et al.  Artificial neural networks in the recognition of the presence of thyroid disease in patients with atrophic body gastritis. , 2008, World journal of gastroenterology.

[26]  Nikos Dimitropoulos,et al.  Thyroid Texture Representation via Noise Resistant Image Features , 2008, 2008 21st IEEE International Symposium on Computer-Based Medical Systems.

[27]  Wonho Lee,et al.  A proposal for a thyroid imaging reporting and data system for ultrasound features of thyroid carcinoma. , 2009, Thyroid : official journal of the American Thyroid Association.

[28]  Aboul Ella Hassanien,et al.  Fuzzy and hard clustering analysis for thyroid disease , 2013, Comput. Methods Programs Biomed..

[29]  Herbert Schildt,et al.  Struts : the complete reference , 2004 .

[30]  Gang Wang,et al.  A Three-Stage Expert System Based on Support Vector Machines for Thyroid Disease Diagnosis , 2012, Journal of Medical Systems.

[31]  M Yearworth,et al.  Artificial neural networks in diagnosis of thyroid function from in vitro laboratory tests. , 1993, Clinical chemistry.

[32]  N. A. Shapiro,et al.  Application of artificial neural network for classification of thyroid follicular tumors. , 2007, Analytical and quantitative cytology and histology.

[33]  Victor L. Berardi,et al.  An investigation of neural networks in thyroid function diagnosis , 1998, Health care management science.

[34]  Krzysztof Wołk,et al.  Translation of Medical Texts using Neural Networks , 2016, Deep Learning and Neural Networks.

[35]  Wei Wang,et al.  A flexible and robust approach for segmenting cell nuclei from 2D microscopy images using supervised learning and template matching , 2013, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[36]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[37]  A. Gawande,et al.  Long‐term assessment of a multidisciplinary approach to thyroid nodule diagnostic evaluation , 2007, Cancer.

[38]  Noel De Palma,et al.  J2EE server scalability through EJB replication , 2006, SAC '06.

[39]  Dimitrios Koutsouris,et al.  Artificial Neural Networks as Decision Support Tools in Cytopathology: Past, Present, and Future , 2016, Biomedical engineering and computational biology.

[40]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.