[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-368787-105":59,"doc-detail-368787-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","a-comparative-analysis-of-deep-learning-architectures-for-thyroid-tissue-classification-with-hyperspectral-imaging-scientific-paper","A comparative analysis of deep learning architectures for thyroid tissue classification with hyperspectral imaging - scientific paper","","Hyperspectral imaging offers medical value by encoding spectral information that can distinguish biomolecular characteristics in thyroid tissue, but its high dimensionality and data volume make analysis challenging. Deep learning, including convolutional and recurrent neural networks, enables detailed modeling of complex patterns beyond traditional approaches. This study compares three deep learning architectures—RNN, FCNN, and 1D-CNN—integrated with micro-FTIR spectroscopy for region-based classification of goiter, cancerous, and healthy tissues. Using a 60-patient dataset and grouped 10-fold cross-validation, 1D-CNN achieved 97.60% accuracy, outperforming RNN (96.88%) and FCNN (93.66%), improving precision in thyroid pathology analysis.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-comparative-analysis-of-deep-learning-architectures-for-thyroid-tissue-classification-with-hyperspectral-imaging-scientific-paper/368787/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-comparative-analysis-of-deep-learning-architectures-for-thyroid-tissue-classification-with-hyperspectral-imaging-scientific-paper/368787.png","ImageObject",300,407,{"name":92,"@type":93},"McGucket","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is hyperspectral imaging useful for thyroid tissue analysis?","Question",{"text":113,"@type":114},"It represents spectral information that can differentiate biomolecular characteristics within tissue samples, supporting more informative analysis for pathology.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What deep learning architectures are compared in this work?",{"text":118,"@type":114},"The study integrates micro-FTIR spectroscopy with three deep learning architectures: RNN, FCNN, and 1D-CNN, and compares their performance for region-based tissue classification.",{"name":120,"@type":111,"acceptedAnswer":121},"Which model performed best and what accuracy was achieved?",{"text":122,"@type":114},"The 1D-CNN model achieved the highest accuracy of 97.60% on region-based classification, outperforming RNN (96.88%) and FCNN (93.66%).","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},368787,1790673756,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},1236954412713,"https://us-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nA comparative analysis of deep learning architectures for thyroid tissue classification with hyperspectral imaging  \nMatheus de Freitas Oliveira Baffa1, Denise Maria Zezell2, Luciano Bachmann1, Thiago Martini Pereira3 & Joaquim Cezar Felipe1􀀍  \nHyperspectral imaging has shown significant applicability in the medical field, particularly for its ability to represent spectral information that can differentiate specific biomolecular characteristics in tissue samples. However, the complexity of analyzing HSI data, due to its high dimensionality and the large volume of information, presents significant challenges. At the same time, deep learning, particularly convolutional neural networks and recurrent neural networks, has become an essential tool in medical diagnostics, providing detailed analysis across various contexts. These techniques enable the analysis of complex information often unattainable through traditional methods. This paper introduces a novel approach that integrates micro-FTIR spectroscopy with three different deep learning architectures, namely RNN, FCNN, and 1D-CNN, to compare their performance in region-based classification of thyroid tissues, including goiter, cancerous, and healthy types. The proposed deep learning methods were developed on a dataset of 60 patients and evaluated using grouped 10-fold cross-validation. The 1D-CNN achieved the highest scores in classifying the spectral data provided by micro-FTIR, enabling more precise and accurate region-based tissue classification. The 1D-CNN achieved an accuracy of 97.60%, while RNN and FCNN achieved 96.88% and 93.66%, respectively. These results highlight the effectiveness of this approach in enhancing the precision of thyroid pathology analysis.  \nMachine learning, particularly deep learning techniques, has become an important tool in daily medical procedures. These advancements support a wide variety of applications, from large language models (LLMs) that guide personalized healthcare recommendations1, to medical imaging diagnostics, such as detecting brain cancer in MRI through image analysis2.  \nAmong the most widely used deep learning architectures, convolutional neural networks (CNNs) have gained significant attention due to their performance in tasks such as image classification, object detection, and segmentation. CNNs have been particularly valuable in medical imaging, where they have been applied to radiological scans3, pathology slides4, and other medical images to assist in accurate and efficient diagnosis.  \nCNNs are comprised of convolutional layers that perform convolutions across the input image, extracting filters that represent patterns such as edges and textures. These patterns capture different levels of complexity, highlighting important characteristics of the data. Such mechanisms have been adapted for other types of input data, including one-dimensional data, such as signals and vector data, as well as three-dimensional data, such as volumes and videos5.  \nOne-dimensional CNNs (1D-CNNs) operates similarly to its 2D version but is designed to process onedimensional data. In a 1D-CNN, convolutional layers slide filters along the input sequence to detect patterns across the data points. These filters capture essential features, such as peaks, trends, or repetitive patterns, which are then used to build a feature map5,6. This mechanism is particularly effective for spectral analysis, where the network can identify subtle variations and characteristics within the spectrum.  \nLong short-term memory recurrent neural networks (LSTM-RNNs) are another deep learning architecture widely used in medical applications, especially in the analysis of time-series data, such as ECG and EEG signal processing7. The LSTM-RNN works by incorporating memory cells that are capable of maintaining information in memory for long periods of time. This capability allows the network to cap","cbCaijfgqGibt7Ba","https://ap.wps.com/l/cbCaijfgqGibt7Ba","pdf",1677313,"English","# Introduction\n## Hyperspectral imaging and challenges\n## Deep learning for medical diagnostics\n# Related background\n## Convolutional neural networks (CNNs)\n## One-dimensional CNNs (1D-CNN)\n## LSTM recurrent neural networks (LSTM-RNN)\n## Fully-connected neural networks (FCNN)\n# Spectral analysis challenges","[{\"question\":\"Why is hyperspectral imaging useful for thyroid tissue analysis?\",\"answer\":\"It represents spectral information that can differentiate biomolecular characteristics within tissue samples, supporting more informative analysis for pathology.\"},{\"question\":\"What deep learning architectures are compared in this work?\",\"answer\":\"The study integrates micro-FTIR spectroscopy with three deep learning architectures: RNN, FCNN, and 1D-CNN, and compares their performance for region-based tissue classification.\"},{\"question\":\"Which model performed best and what accuracy was achieved?\",\"answer\":\"The 1D-CNN model achieved the highest accuracy of 97.60% on region-based classification, outperforming RNN (96.88%) and FCNN (93.66%).\"}]","A comparative analysis of deep learning architectures for thyroid tissue classification with hyperspectral imaging - scientific paper | PDF",1790178531,23,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dcbdc3243c670aaa02f0cf4d312f52b7.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6c7b34893ecfbd169e9982c07e0cdab8.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0dbe610bad883e0221cc1e7dbda6a304.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/04180e547202ef60594545b55b86eea1.webp",980,1287]