[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128514-en":3,"doc-seo-128514-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},128514,687207017582,"Himbo","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Classification of Histological Images of Thyroid Nodules - Using Deep Features and Machine Learning","Thyroid nodules are common and include benign and malignant pathological types, requiring reliable differentiation because cancer often needs surgery while benign lesions can be monitored. This study proposes an automatic classification tool focused on papillary carcinoma and follicular adenoma using histological image analysis. Two pre-trained CNN models (VGG16 and VGG19) extract deep features, followed by PCA dimensionality reduction and machine-learning classifiers (SVM, KNN, Random Forest).","Classification of histological images of thyroid nodules based on a combination of Deep Features and Machine Learning  \nType of article: Original  \nLinda BELLAL, Meriem SAIM, Amina BENAHMED, Kamila KHEMIS Biomedical Engineering dept. Faculty of Technology University of Tlemcen, Algeria  \nAbstract  \nBackground: Thyroid nodules are a prevalent worldwide disease with complex pathological types. They can be classified as either benign or malignant. This paper presents a tool for automatically classifying histological images of thyroid nodules, with a focus on papillary carcinoma and follicular adenoma.  \nMethods: In this work, two pre-trained Convolutional Neural Network (CNN) architectures, VGG16 and VGG19, are used to extract deep features. Then, a principal component analysis was used to reduce the dimensionality of the vectors. Then, three machine learning algorithms (Support Vector Machine, KNearest Neighbor, and Random Forest) were used for classification. These investigations were applied to our database collection,  \nResults: The proposed investigations have been applied to our private database collection with a total of 112 histological images. The highest results were obtained by the VGG16 transfer deep feature and the SVM classifier with an accuracy rate equal to 100% .  \nKeywords: Thyroid nodules, Papillary carcinoma, Follicular adenoma, Deep feature, Support Vector Machine learning, K Nearest Neighbor, Random Forest, supervised machine learning, transfer learning,  \nCorresponding author: Linda BELLAL, Biomedical Engineering dept. Faculty of Technology University of Tlemcen, Algeria, Email: [lindabellal1995@gmail.com](lindabellal1995@gmail.com).  \nReceived: December 25 2022. Reviewed: February 27 2023. Accepted: 03 May 2023. Published: 15 October 2023.  \nScreened by iThenticate. .©2017-2023 KNOWLEDGE KINGDOM PUBLISHING.  \n1. Introduction  \nThe thyroid gland can develop solid or fluid-filled nodules, which are common disorders with clinical symptoms of various pathological kinds. There are two types of thyroid nodules: benign thyroid nodules and malignant thyroid nodules. Thyroid adenoma and nodular goiter are benign thyroid nodules. The thyroid's papillary carcinomas, follicular, medullary, and anaplastic carcinomas are all examples of malignant nodules. The differential diagnosis of thyroid nodules is crucial because thyroid cancer requires surgery while benign nodules just require follow-up. The pathological evaluation of tissues from resected tumors is the gold standard for tumor diagnosis. Currently, pathologists obtain the vast majority of abnormal tissue cuts, and clinical diagnosis is based on long-term collections of samples. In spite of this, manual differential diagnosis of thyroid tumor histological images is still challenging for three main reasons: first, the ability to accurately diagnose samples depends greatly on the pathologist's professional training and experience, and such experience cannot be quickly acquired; second, the task is time-consuming, expensive, and boring; and third, it is challenging for the human eye to distinguish subtle changes in the tissues. As a result, pathologists may become exhausted, which might lead to an incorrect diagnosis.  \nThus, determining the correct histological diagnosis of thyroid nodules is difficult and requires an automatic system that aids in diagnosis [1] .  \nMachine learning algorithms (ML) are used to allocate test data to specified groups in classification tasks. Deep learning algorithms are being applied to the pathological diagnosis of various diseases and are being employed more and more in the field of medical imaging recently. But the DL algorithms require a large database to give us satisfactory and accurate results, especially in the field of medicine, and unfortunately, this is not the case in our work, because we do not have a large database.  \nTransfer learning is a popular and efficient method where the information gained by a DL model while addr","cbCail0b5f4c4mYk","https://ap.wps.com/l/cbCail0b5f4c4mYk","pdf",848644,1,11,"English","en",105,"# Introduction\n## Problem motivation and clinical relevance\n## Deep learning, transfer learning, and model strategy\n# Materials and Methods\n## Dataset and preprocessing\n## Feature extraction with VGG16/VGG19 and PCA\n## Classification models","[{\"question\":\"Why is automatic classification of thyroid nodule histology needed?\",\"answer\":\"Manual differential diagnosis is difficult due to subtle tissue differences, reliance on pathologist experience, and high time and cost burden. Exhaustion can also lead to incorrect diagnoses.\"},{\"question\":\"Which deep learning models and classifiers are used in the method?\",\"answer\":\"The study uses pre-trained CNN architectures VGG16 and VGG19 to extract deep features, then applies PCA and classifiers including SVM, KNN, and Random Forest for categorization.\"},{\"question\":\"What dataset size and result performance are reported?\",\"answer\":\"Experiments were conducted on a private dataset of 112 histological images. The best performance comes from VGG16 deep transfer features combined with an SVM classifier, achieving 100% accuracy.\"}]","Classification of Histological Images of Thyroid Nodules - Using Deep Features and Machine Learning | PDF",1786001477,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"classification-of-histological-images-of-thyroid-nodules-using-deep-features-and-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/classification-of-histological-images-of-thyroid-nodules-using-deep-features-and-machine-learning/128514/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-06",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automatic classification of thyroid nodule histology needed?","Question",{"text":75,"@type":76},"Manual differential diagnosis is difficult due to subtle tissue differences, reliance on pathologist experience, and high time and cost burden. Exhaustion can also lead to incorrect diagnoses.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which deep learning models and classifiers are used in the method?",{"text":80,"@type":76},"The study uses pre-trained CNN architectures VGG16 and VGG19 to extract deep features, then applies PCA and classifiers including SVM, KNN, and Random Forest for categorization.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset size and result performance are reported?",{"text":84,"@type":76},"Experiments were conducted on a private dataset of 112 histological images. The best performance comes from VGG16 deep transfer features combined with an SVM classifier, achieving 100% accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]