[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86576-en":3,"doc-seo-86576-105":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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86576,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction","Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma, yet its preoperative prediction from MRI is difficult because important imaging cues are subtle and often extend beyond tumor boundaries into surrounding peritumoral regions. Convolutional models struggle with long-range spatial dependencies, while transformer and diffusion approaches can be robust but incur heavy computation from combining global attention with iterative denoising. The work formulates PNI prediction as diffusion-based classification and implements the denoising network with a transformer representation, adding adaptive routing across attention heads, spatial tokens, and MLP width, achieving AUC 0.731 at 257.57 GFLOPs.","Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction  \nYoungung Han 1 ,3 , Dohyun Kweon2 ,3 , Kyeonghun Kim3 , Hyunsu Go 1 , Jina Jeong 1 , Suah Park1 , Induk Um4 , Junga Kim 1 , Anna Jung 1 , Yului Jeong 1 , Sungha Park1 ,5 , Jinyong Jun 1  \nPa Hong6 , Woo Kyoung Jeong7 , Won Jae Lee6 , Ken Ying-Kai Liao8 , Hyuk-Jae Lee 1 , Nam-Joon Kim 1 ,†  \n1 Seoul National University, Seoul, Republic of Korea 2 Kyung Hee University, Seoul, Republic of Korea  \n3 OUTTA, Seoul, Republic of Korea 4 Chung-Ang University, Seoul, Republic of Korea  \n5 Seoul National University School of Medicine, Seoul, Republic of Korea  \n6 Samsung Changwon Hospital, Changwon, Republic of Korea 7 Samsung Medical Center, Seoul, Republic of Korea  \n8NVIDIA AI Technology Center, Taipei, Taiwan  \n†Corresponding author: [knj01@snu.ac.kr](knj01@snu.ac.kr)  \narXiv :2607 . 11533v1 [ cs .CV] 13 Jul 2026  \nAbstract—Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. However, its preoperative prediction from magnetic resonance imaging (MRI) remains challenging due to subtle imaging features that extend beyond tumor boundaries into surrounding regions. Conventional convolutional neural networks are limited in capturing long-range spatial dependencies. Transformer-based architectures improve global modeling of volumetric MRI by aggregating spatially distributed contextual cues, yet capturing subtle and noise-sensitive patterns in peritumoral regions remains challenging. Diffusion-based classifiers offer an alternative formulation by leveraging denoising-based class scoring to better capture such subtle patterns. However, these approaches introduce substantial computational overhead due to the combination of transformer-based modeling and iterative denoising processes. To address these challenges, we formulate PNI prediction as a diffusion-based classification problem and implement the denoising network using a transformer-based representation. To improve computational efficiency, we introduce adaptive routing across attention heads, spatial tokens, and MLP width. Experimental results demonstrate that the proposed approach achieves an AUC of 0.731 with 257.57 GFLOPs.  \nIndex Terms—diffusion transformer, adaptive routing, token selection, computational efficiency, 3D MRI analysis, perineural invasion  \nI. INTRODUCTION  \nPerineural invasion (PNI) is a critical prognostic factor closely associated with tumor aggressiveness and poor clinical outcomes [1] . Preoperative prediction of PNI from MRI may assist in surgical planning and inform neoadjuvant treatment strategies; however, it remains challenging due to subtle and spatially diffuse imaging features that often extend beyond tumor boundaries [2]–[4] . PNI involves tumor spread along and around nerve structures, resulting in weak and spatially distributed patterns that are difficult to detect [1], [5]–[8] . CNN-based models primarily rely on local receptive fields [9], which may limit their ability to capture long-range spatial dependencies across slices and surrounding peritumoral regions. Subtle peritumoral cues are often weak and spatially distributed beyond localized regions, making them difficult to capture with purely local representations.  \nTransformer-based architectures model global interactions via self-attention [10]–[12], aggregating dispersed contextual cues. However, subtle peritumoral cues remain sensitive to noise and ambiguity, especially in medical imaging with low signal-to-noise ratios and inter-patient variability [13] . Diffusion-based classifiers have therefore been explored to improve robustness to subtle and noisy patterns [14], [15] .  \nDiffusion models probabilistically model data distributions [16], [17] and can be adapted for classification by comparing class-conditional denoising or reconstruction errors [15]. To combine denoising-based classification with longrange volumetric MRI modeling, we adopt a transformer-based denoising backbone [18]–[20","cbCaibN4WHiT8pm2","https://ap.wps.com/l/cbCaibN4WHiT8pm2","pdf",6987872,2,1,5,"English","en",105,"# Introduction\n# Proposed Method\n## Diffusion Transformer for Classification","[{\"question\":\"Why is predicting perineural invasion (PNI) from MRI challenging preoperatively?\",\"answer\":\"PNI involves subtle, spatially diffuse imaging patterns that often extend beyond tumor boundaries into peritumoral regions, making the visual evidence weak and hard to detect.\"},{\"question\":\"How does the proposed method improve robustness compared with CNN-based approaches?\",\"answer\":\"It uses transformer-based long-range modeling to aggregate dispersed contextual cues, and it frames classification with diffusion-based denoising to better capture subtle and noise-sensitive patterns.\"},{\"question\":\"What mechanism reduces computation in the diffusion transformer classifier?\",\"answer\":\"Adaptive routing dynamically allocates computation across attention heads, spatial tokens, and MLP width, improving efficiency while targeting regions relevant to tumor boundary context.\"}]",1784212730,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"adaptive-routing-for-efficient-diffusion-transformer-based-pni-prediction","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/adaptive-routing-for-efficient-diffusion-transformer-based-pni-prediction/86576/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is predicting perineural invasion (PNI) from MRI challenging preoperatively?","Question",{"text":75,"@type":76},"PNI involves subtle, spatially diffuse imaging patterns that often extend beyond tumor boundaries into peritumoral regions, making the visual evidence weak and hard to detect.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve robustness compared with CNN-based approaches?",{"text":80,"@type":76},"It uses transformer-based long-range modeling to aggregate dispersed contextual cues, and it frames classification with diffusion-based denoising to better capture subtle and noise-sensitive patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"What mechanism reduces computation in the diffusion transformer classifier?",{"text":84,"@type":76},"Adaptive routing dynamically allocates computation across attention heads, spatial tokens, and MLP width, improving efficiency while targeting regions relevant to tumor boundary context.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":22,"slug":137},19,"General","general"]