[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121825-en":3,"doc-seo-121825-105":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":4,"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":27,"seo_description":14,"update_tm":28,"read_time":29},121825,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Machine Learning Applied to Raman Spectroscopy to Classify Cancers","Cancer diagnosis remains difficult due to substantial inter-rater variability among histopathologists when classifying cancer sub-types. Earlier, more reliable diagnosis is essential to expand treatment potential, motivating tools that support pathology workflows. Raman spectroscopy offers promise for distinguishing cancer types, but Raman datasets are high-dimensional and often contain artefacts, complicating medical-data classification. This thesis investigates machine learning approaches for Raman oncology datasets (ovarian, colonic, oesophageal) and evaluates traditional and deep learning models, plus interpretability to link biochemical signals to disease classes.","Machine Learning Applied to Raman Spectroscopy to Classify Cancers  \nNathan Blake  \nAcademic Supervisors:  \nProf. Geraint Thomas  \nProf. Lewis Griffin  \nIndustrial Supervisor:  \nIan Bell  \nA dissertation submitted in partial fulfillment  \nof the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUniversity College London.  \nCell and Developmental Biology  \nUniversity College London  \nAugust 2, 2023  \n2  \nI, Nathan Blake, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been  \nindicated in the work.  \nAbstract  \nCancer diagnosis is notoriously difficult, evident in the inter-rater variability between histopathologists classifying cancerous sub-types. Although there are many cancer pathologies, they have in common that earlier diagnosis would maximise treatment potential. To reduce this variability and expedite diagnosis, there has been a drive to arm histopathologists with additional tools. One such tool is Raman spectroscopy, which has demonstrated potential in distinguishing between various cancer types. However, Raman data has high dimensionality and often contains artefacts and together with challenges inherent to medical data, classification attempts can be frustrated. Deep learning has recently emerged with the promise of unlocking many complex datasets, but it is not clear how this modelling paradigm can best exploit Raman data for cancer diagnosis.  \nThree Raman oncology datasets (from ovarian, colonic and oesophageal tissue) were used to examine various methodological challenges to machine learning applied to Raman data, in conjunction with a thorough review of the recent literature. The performance of each dataset is assessed with two traditional and one deep learning models. A technique is then applied to the deep learning model to aid interpretability and relate biochemical antecedents to disease classes. In addition, a clinical problem for each dataset was addressed, including the transferability of models developed using multi-centre Raman data taken different on spectrometers of the same make.  \nMany subtleties of data processing were found to be important to the realistic assessment of a machine learning models. In particular, appropriate cross-validation during hyperparameter selection, splitting data into training and test sets according to the inherent structure of biomedical data and addressing the number of samples  \nAbstract 4  \nper disease class are all found to be important factors. Additionally, it was found that instrument correction was not needed to ensure system transferability if Raman data is collected with a common protocol on spectrometers of the same make.  \nImpact Statement  \nThe findings in this thesis can be split into two categories: those related to the methodological rigour of conducting machine learning for cancer diagnosis using Raman spectroscopy, and clinical findings regarding the application of the technique to specific oncology tasks identified by collaborating histopathologists.  \nRegarding methodological rigour, this thesis has confirmed findings in the literature that without nested cross-validation the accuracy of models can be inflated by 5-10%, by over-fitting model hyperparameters. Similarly, the method of splitting data during model training was found to significantly impact the estimated accuracy of models, with inappropriate methods inflating accuracy by as much as 10-20% . It also finds that baseline correction during pre-processing does not necessarily increase the performance of models, and may even obscure clinically relevant information and complicate cross-validation by introducing more hyperparameters. Together with a systematic review of the related recent literature this thesis contributes to a growing movement within the medical Raman community to improve methodological rigour.  \nThere are three main clinical findings.The first is that the technique can be used to distinguish between ova","cbCaikcswc2U0DNa","https://ap.wps.com/l/cbCaikcswc2U0DNa","pdf",35401917,1,254,"English","en",105,"# Abstract\n## Datasets and evaluation approach\n## Model interpretability and clinical tasks\n# Impact Statement\n## Methodological rigour and cross-validation\n## Clinical findings across oncology problems\n## Model transferability across spectrometers\n# Author Contribution Statement","[{\"question\":\"What problem does this thesis address in cancer diagnosis?\",\"answer\":\"It targets the inter-rater variability in histopathological classification and aims to expedite earlier diagnosis using additional tools.\"},{\"question\":\"Why is Raman spectroscopy challenging for machine learning in medical classification?\",\"answer\":\"Raman data is high-dimensional and can include artefacts, and medical-data characteristics further complicate reliable modelling and evaluation.\"},{\"question\":\"How did the thesis assess methodological rigour when training and evaluating models?\",\"answer\":\"It emphasizes appropriate nested cross-validation during hyperparameter selection, structure-aware train/test splits for biomedical data, and careful consideration of sample counts per disease class.\"}]","Machine Learning Applied to Raman Spectroscopy to Classify Cancers | PDF",1785807058,640,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-applied-to-raman-spectroscopy-to-classify-cancers","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-applied-to-raman-spectroscopy-to-classify-cancers/121825/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this thesis address in cancer diagnosis?","Question",{"text":75,"@type":76},"It targets the inter-rater variability in histopathological classification and aims to expedite earlier diagnosis using additional tools.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is Raman spectroscopy challenging for machine learning in medical classification?",{"text":80,"@type":76},"Raman data is high-dimensional and can include artefacts, and medical-data characteristics further complicate reliable modelling and evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the thesis assess methodological rigour when training and evaluating models?",{"text":84,"@type":76},"It emphasizes appropriate nested cross-validation during hyperparameter selection, structure-aware train/test splits for biomedical data, and careful consideration of sample counts per disease class.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]