[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85729-en":3,"doc-seo-85729-105":29,"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":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":13,"seo_description":14,"update_tm":27,"read_time":28},85729,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Performance Benchmarking and Optimisation of Clustering Algorithms for Local and Non-Local Similarity Measure in Medical Image Analysis","Medical imaging produces high-resolution data that creates major storage, transmission, and computation burdens. Low-rank matrix approximation (LoRMA) can compress images by leveraging redundancy, but global formulations may miss local structures crucial for diagnosis. The study benchmarks clustering methods that exploit non-local self-similarity to group structurally similar regions, supporting tasks such as adaptive image compression. Five clustering algorithms are optimized via random search and evaluated with Silhouette, Davies-Bouldin, and Calinski-Harabasz indices across MRI, ultrasound, and chest X-ray modalities.","arXiv :2607 .09821v1 [ ee ss .IV] 10 Jul 2026  \nPerformance Benchmarking and Optimisation of Clustering Algorithms for Local and Non-Local Similarity Measure in Medical Image Analysis  \nSisipho Hamlomo 1 ,2 and Marcellin Atemkeng 1 ,3  \n1 Department of Mathematics, Rhodes University, PO Box 94, Makhanda, 6140, South Africa  \n2 Department of Statistics, Rhodes University, PO Box 94, Makhanda, 6140, South Africa  \n3 National Institute for Theoretical and Computational Sciences (NITheCS),  \nStellenbosch 7600, South Africa  \n{s.hamlomo, [m.atemkeng](m.atemkeng}@ru.ac.za)[}](m.atemkeng}@ru.ac.za)[@ru.ac.za](m.atemkeng}@ru.ac.za)  \nAbstract. Medical imaging generates high-resolution images posing significant storage, transmission, and computational challenges. While lowrank matrix approximation (LoRMA) techniques offer efficient compression by exploiting structural redundancy, global approaches often fail topreserve local details critical for diagnosis. This paper focuses on clustering techniques that exploit non-local self-similarity to identify structurally similar regions in medical images. These clusters can be used for post-processing tasks such as adaptive image compression. We evaluate five clustering techniques: k-means, mini-batch k-means, agglomerative hierarchical clustering, balanced iterative reducing and clustering using hierarchies (BIRCH), and bisecting k-means across MRI, ultrasound, and chest X-ray modalities. All clustering techniques were optimised using random search, and cluster quality was assessed using the Silhouette score, the Davies-Bouldin (DB) index, and the Calinski-Harabasz (CH) index. Results demonstrate that standard k-means and bisecting k-means generally achieve strong cluster cohesion and separation across modalities. However, they tend to form a small number of clusters with high intra-cluster variability, limiting their effectiveness for post-processing tasks such as adaptive compression. Agglomerative clustering outperformed other techniques for MRI and ultrasound in terms of intra-cluster homogeneity, making it more suitable for preserving fine diagnostic details. For chest X-rays, mini-batch k-means achieved the best balance between clustering quality and intra-cluster compactness. BIRCH consistently underperformed across all modalities.  \nKeywords: Medical image compression, clustering, low-rank matrix approximation, hyperparameter tuning  \n1 Introduction  \nMedical imaging plays an important role in modern healthcare, enabling accurate diagnosis, treatment planning, and disease monitoring. Advances in imag-  \n2 Sisipho Hamlomo and Marcellin Atemkeng  \ning modalities such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound have significantly enhanced image resolution and diagnostic capability [1,2,3] . However, these high-resolution images produce vast amounts of high-dimensional data, posing data storage, transmission, and computational processing challenges during image analysis [4,5,6] . In addition, medical images often suffer from noise, artefacts, and variations due to different acquisition conditions, further complicating efficient image analysis [7] . Therefore, efficient image compression becomes essential to reduce the cost burden on healthcare data management systems. To address these challenges, various image compression techniques have been explored, broadly categorised into lossless and lossy methods. While lossless techniques preserve all original data, they often achieve low compression ratios, which limits their practicality in bandwidthconstrained and storage-limited environments [8,9] . Consequently, lossy compression methods, which aim to reduce data redundancy while preserving and extracting important features, have received increased attention. Standard image compression techniques such as discrete cosine transform (DCT)-based JPEG [10,11,12] and wavelet-based JPEG2000 [13,14,15] have been widely applied. These methods have the advantage of bein","cbCaivx3z8Qi503s","https://ap.wps.com/l/cbCaivx3z8Qi503s","pdf",768548,1,16,"English","en",105,"# Abstract\n# Introduction\n## Motivation: compression challenges in medical imaging\n## LoRMA and the need to preserve local details\n## Non-local patch grouping via clustering","[{\"question\":\"Why is adaptive image compression important in medical image analysis?\",\"answer\":\"High-resolution medical images create storage, transmission, and computational burdens. Compression is needed, but standard approaches may lose fine structural and diagnostic details, so adaptive strategies are required to preserve clinically significant information.\"},{\"question\":\"Which clustering techniques are evaluated in the study?\",\"answer\":\"The paper evaluates k-means, mini-batch k-means, agglomerative hierarchical clustering, BIRCH, and bisecting k-means. Each method is optimized using random search and assessed across MRI, ultrasound, and chest X-ray modalities.\"},{\"question\":\"How are clustering results measured and compared?\",\"answer\":\"Clustering quality is quantified using the Silhouette score, Davies-Bouldin (DB) index, and Calinski-Harabasz (CH) index. The study compares these metrics along with implications for intra-cluster homogeneity relevant to adaptive compression.\"}]",1784205862,40,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"performance-benchmarking-and-optimisation-of-clustering-algorithms-for-local-and-non-local-similarity-measure-in-medical-image-analysis","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/performance-benchmarking-and-optimisation-of-clustering-algorithms-for-local-and-non-local-similarity-measure-in-medical-image-analysis/85729/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 adaptive image compression important in medical image analysis?","Question",{"text":75,"@type":76},"High-resolution medical images create storage, transmission, and computational burdens. Compression is needed, but standard approaches may lose fine structural and diagnostic details, so adaptive strategies are required to preserve clinically significant information.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which clustering techniques are evaluated in the study?",{"text":80,"@type":76},"The paper evaluates k-means, mini-batch k-means, agglomerative hierarchical clustering, BIRCH, and bisecting k-means. Each method is optimized using random search and assessed across MRI, ultrasound, and chest X-ray modalities.",{"name":82,"@type":73,"acceptedAnswer":83},"How are clustering results measured and compared?",{"text":84,"@type":76},"Clustering quality is quantified using the Silhouette score, Davies-Bouldin (DB) index, and Calinski-Harabasz (CH) index. The study compares these metrics along with implications for intra-cluster homogeneity relevant to adaptive compression.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":28,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]