[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-365190-105":59,"doc-detail-365190-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","identification-of-cancerous-tissues-based-on-residual-neural-network","Identification of cancerous tissues based on residual neural network","","Residual neural network methods are proposed to rapidly identify cancerous tissues despite challenges from complex experimental procedures and low identification accuracy. A theoretical transmission framework models laser beam transport in cancerous and normal biological tissues to obtain tissue-carrying laser speckle patterns at the receiving plane. A three-task residual network, T-ResNet-18, is trained on simulated prostate tissues, rat tissues, and cell suspensions, achieving accuracy above 99%. Dataset size, training epochs, and tissue thickness effects are analyzed and compared with ResNet-18, VGG16, and AlexNet.",{"@graph":69,"@context":122},[70,84,105],{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/identification-of-cancerous-tissues-based-on-residual-neural-network/365190/",{"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/identification-of-cancerous-tissues-based-on-residual-neural-network/365190.png","ImageObject",300,407,{"name":92,"@type":93},"Margaret","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address?","Question",{"text":112,"@type":113},"The paper targets the difficulty of identifying cancerous tissues with complex experimental methods and low identification accuracy. It introduces a rapid identification approach to improve performance.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are laser speckle patterns related to tissue identification?",{"text":117,"@type":113},"A theoretical transmission model simulates laser beam transport through cancerous and normal tissues. Laser speckle patterns carrying tissue information are then captured at the receiving plane for further classification.",{"name":119,"@type":110,"acceptedAnswer":120},"What is T-ResNet-18 and how is it evaluated?",{"text":121,"@type":113},"T-ResNet-18 is a three-task residual neural network designed to identify speckle images. It is trained using simulated normal and cancerous tissue samples and evaluated by achieving accuracy exceeding 99%, with comparisons against ResNet-18, VGG16, and AlexNet.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},365190,1790318746,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"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":41},137451207643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nIdentification of cancerous tissues based on residual neural network  \nYing Liu1, Xiaoyun Liu1􀀍, Siyu Gao1, Tengfei Chai1, Zihao Zhao1, Hongwei Wang1, Yumeihui Jin1 & Yueqiu Jiang2􀀍  \nThe identification of cancerous tissues remains challenging due to the complexity of experimental methods and low identification accuracy rates. Therefore, this paper proposes a rapid identification method. We introduce a new theoretical transmission method for modeling laser beams transport in cancerous and normal biological tissues. Using this method, laser speckle patterns carrying tissue information are obtained at the light transmission receiving plane. Then, we propose a three-task residual neural network, T-ResNet-18, for identifying speckle images. We simulate the human normal and cancerous prostate tissues, rat normal and cancerous tissues, and normal and abnormal cell suspension as training samples. The results show the identification accuracy exceeding 99% . Additionally, we discuss the impact of varying dataset sizes, training epochs, and tissue thickness on identification accuracy and compare the performance ofT-ResNet-18 with ResNet-18, VGG16 and AlexNet, showing that T-ResNet-18 significantly outperforms classic neural networks.  \nKeywords Cancerous tissue identification, Biological tissue phase screen, Residual neural network, Power spectral density function  \nMany experimental studies are hampered by the lack of an accurate theory on the propagation of light in heterogeneous media. In this regard, numerical simulation of laser radiation transport plays an increasingly important role overcoming this limitation. In the field of biophotonics, various models have been developed to describe radiation transport in scattering tissues at macroscopic, mesoscopic, and microscopic scales. For example, Monte Carlo (MC) simulation1–3, finite-difference time domain4,5, and beam propagation method6,7, etc. MC simulations, introduced in the 1970s, rely on the probabilistic interpretation of photon trajectories and are considered the gold standard for studying the optical properties of scattering media. However, this approach is time-consuming in 3D simulations, has indeterminable statistical errors, and is difficult to accelerate while controlling the estimation error.  \nLater, the researchers have observed that the refractive index distribution of biological cells and tissues is similar to the fractal distribution and have used the fractal propagation method (FPM) to describe them. In 2005, Xu et al. demonstrated that the light scattering properties of biological tissues and cell suspensions can be effectively represented using a fractal continuous random medium model based on FPM8. In 2008, Xu et al. experimentally fitted the parameters of FPM and the angular dependence of light scattering spectra for human cervical squamous carcinoma epithelial (SiHa) cells. When the size distributions of cells and cell nuclei were fixed through independent microscopy measurements, the consistency between the model and experimental data demonstrated the effectiveness of the fractal model9. In 2015, Radosevich et al. proposed that the fundamental physical characteristic causing light scattering in biological tissues is the spatial refractive index fluctuations. They introduced the spatial refractive index autocorrelation function into the FPM and further derived the general refractive index power spectral density function for biological tissues10.  \nThe spatial refractive index fluctuation of biological media is the main cause of light scattering. This paper applies the refractive index power spectral density function of biological tissues to phase screen theory11, 12. The phase screen theory converts the disturbances of medium in space into phase modulation on the light beam. This phase modulation is fitted into a two-dimensional matrix screen, which is then placed in the path of ","cbCaip4RRSaMPQLc","https://ap.wps.com/l/cbCaip4RRSaMPQLc","pdf",3882781,12,"English","# Identification of cancerous tissues based on residual neural network\n## Problem background and motivation\n## Laser transmission modeling in biological tissues\n## Phase screen and refractive-index power spectral density\n## T-ResNet-18 training strategy and experimental results\n## Comparisons and parameter-sensitivity analysis\n## Clinical context and related deep-learning diagnostic work","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper targets the difficulty of identifying cancerous tissues with complex experimental methods and low identification accuracy. It introduces a rapid identification approach to improve performance.\"},{\"question\":\"How are laser speckle patterns related to tissue identification?\",\"answer\":\"A theoretical transmission model simulates laser beam transport through cancerous and normal tissues. Laser speckle patterns carrying tissue information are then captured at the receiving plane for further classification.\"},{\"question\":\"What is T-ResNet-18 and how is it evaluated?\",\"answer\":\"T-ResNet-18 is a three-task residual neural network designed to identify speckle images. It is trained using simulated normal and cancerous tissue samples and evaluated by achieving accuracy exceeding 99%, with comparisons against ResNet-18, VGG16, and AlexNet.\"}]","Identification of cancerous tissues based on residual neural network | PDF",1790160305]