[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121840-en":3,"doc-seo-121840-105":29,"detail-sidebar-cat-0-en-105":89},{"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":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},121840,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Distinguishing Leukemic Cells Using Fractal Chromatin Patterns and Machine Learning","Clinical diagnosis relies on accurate differentiation of white blood cell types from a Complete Blood Count, yet leukemic blasts remain difficult to classify reliably. This study quantifies fractal patterns in leukemic and non-leukemic cell chromatin and trains a random forest model using features extracted from nucleus images. The approach aims to increase laboratory accuracy and efficiency by improving discrimination among multiple leukemic cell categories and separating leukemic from non-leukemic populations.","BRIGHAM YOUNG UNIVERSITY  \nDEPARTMENT OF MICROBIOLOGY AND MOLECULAR BIOLOGY  \nDistinguishing Leukemic Cells Using Fractal Chromatin Patterns and  \nMachine Learning  \n1Abigail Gordhamer, 1 Paul Young, 1 Ryan Cordner  \n1 Department of Microbiology and Molecular Biology, Brigham Young University.  \nPURPOSE  \nOne of the most important tests in the clinical laboratory is the Complete Blood Count, which involves identifying the white blood cells in a patient’s blood. The respective counts of the different white blood cell  \ntypes correlate with various states of health and disease and are critical to diagnosing diseases such as leukemia. Leukemic cells (blasts) are considered especially difficult to distinguish, and it is of the upmost importance  \nthat these cells are identified correctly. To aid in the process of leukemic cell identification, we quantified fractal patterns in the chromatin of white blood cells and used the data to identify cells with a random forest algorithm. By distinguishing between cells with the help of a machine learning algorithm, we hope to improve accuracy and efficiency in the clinical laboratory and more easily identify leukemic cells.  \nMETHODS  \nWe compiled image banks of 300-500 images for fifteen types of white blood cells by taking pictures of patient blood samples. We then isolated the nucleus in each image and used a program called TWOMBLI to generate amask image and high-definition matrix image for each nucleus. From these images, TWOMBLI calculated parameters that indicate fractal patterns in the nucleus such as lacunarity, curvature, branchpoints, endpoints, etc. Using these parameters, we calculated the average values for each cell type and compared those values to one another. Additionally, we ran our data through a random forest algorithm and calculated the accuracy, precision, specificity, and sensitivity from the confusion matrix.  \nRESULTS  \nThe random forest algorithm was able to identify five different types of leukemic cells with up to 92% accuracy and 90% precision. We also found that the algorithm could distinguish leukemic cells from non-leukemic cells with 97% accuracy and 95% precision. The most important parameters used in the algorithm were endpoints and branch points. A t-test revealed that certain parameters, such as lacunarity and percent high density matrix, have a p-value of 2.4e-25 or lower when compared amongst cell types.  \nL1  \nL2  \nL3  \nLymphocyte  \nMonoblast  \nMonocyte  \nMyeloblast  \nMyelocyte  \nReactive Lymphocyte  \nL1  \n85  \n13  \n8  \n0  \n0  \n3  \n21  \n0  \n4  \nL2  \n9  \n56  \n25  \n0  \n19  \n0  \n23  \n2  \n10  \nL3  \n1  \n3  \n3  \n0  \n2  \n0  \n4  \n0  \n3  \nLymphocyte  \n0  \n0  \n0  \n43  \n0  \n10  \n0  \n0  \n0  \nMonoblast  \n1  \n16  \n3  \n0  \n61  \n0  \n10  \n5  \n5  \nMonocyte  \n0  \n0  \n0  \n4  \n0  \n46  \n0  \n0  \n0  \nMyeloblast  \n16  \n58  \n11  \n1  \n27  \n0  \n100  \n9  \n12  \nMyelocyte  \n0  \n0  \n0  \n1  \n1  \n0  \n0  \n27  \n1  \nReactive Lymphocyte  \n2  \n2  \n3  \n1  \n1  \n0  \n12  \n5  \n18  \nTable 1. Confusion Matrix. Results from the random forest classifier algorithm’s performance on test data. Columns represent the actual cell identity while rows represent the random forest classification algorithm’s determination of the cell identity.  \n\n|  | L1 | L2 | L3 | Lymphocyte | Monoblast | Monocyte | Myeloblast | Myelocyte | Reactive Lymphocyte |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| Specificity | 0.93 | 0.87 | 0.98 | 0.98 | 0.94 | 0.99 | 0.79 | 0.996 | 0.97 |\n| Sensitivity | 0.75 | 0.38 | 0.06 | 0.86 | 0.55 | 0.78 | 0.59 | 0.56 | 0.34 |\n| Accuracy | 0.90 | 0.78 | 0.92 | 0.98 | 0.89 | 0.98 | 0.75 | 0.97 | 0.92 |\n| Precision | 0.63 | 0.39 | 0.19 | 0.81 | 0.60 | 0.92 | 0.43 | 0.90 | 0.41 |\n| Misidentification Rate | 0.25 | 0.62 | 0.94 | 0.14 | 0.45 | 0.22 | 0.41 | 0.43 | 0.66 |\n\nTable 2. Cell Prediction Metrics. The model’s performance for accuracy, precision, sensitivity, and specificity for each cell type from the test data are reported.  \n350 ~~ ~~  \nLacunarity Endpoints HGU (micro","cbCaim5s5yfMbIO7","https://ap.wps.com/l/cbCaim5s5yfMbIO7","pdf",535595,1,"English","en",105,"# Purpose\n# Methods\n# Results\n# Conclusions","[{\"question\":\"What problem does the study address in clinical blood testing?\",\"answer\":\"Differentiating white blood cell types in complete blood counts, especially distinguishing leukemic blasts accurately, remains challenging and affects diagnosis of leukemia and related conditions.\"},{\"question\":\"How are fractal chromatin features extracted from cell images?\",\"answer\":\"Patient blood sample images are used to isolate each nucleus, then TWOMBLI generates mask and matrix images and computes fractal-related parameters such as lacunarity, curvature, branch points, and endpoints.\"},{\"question\":\"What performance does the random forest model achieve?\",\"answer\":\"The model identifies five leukemic cell types with up to 92% accuracy and 90% precision, and it distinguishes leukemic from non-leukemic cells with 97% accuracy and 95% precision.\"}]","Distinguishing Leukemic Cells Using Fractal Chromatin Patterns and Machine Learning | PDF",1785807162,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"distinguishing-leukemic-cells-using-fractal-chromatin-patterns-and-machine-learning","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"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":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/distinguishing-leukemic-cells-using-fractal-chromatin-patterns-and-machine-learning/121840/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the study address in clinical blood testing?","Question",{"text":73,"@type":74},"Differentiating white blood cell types in complete blood counts, especially distinguishing leukemic blasts accurately, remains challenging and affects diagnosis of leukemia and related conditions.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How are fractal chromatin features extracted from cell images?",{"text":78,"@type":74},"Patient blood sample images are used to isolate each nucleus, then TWOMBLI generates mask and matrix images and computes fractal-related parameters such as lacunarity, curvature, branch points, and endpoints.",{"name":80,"@type":71,"acceptedAnswer":81},"What performance does the random forest model achieve?",{"text":82,"@type":74},"The model identifies five leukemic cell types with up to 92% accuracy and 90% precision, and it distinguishes leukemic from non-leukemic cells with 97% accuracy and 95% precision.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]