FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387191004> ?p ?o ?g. }

• W4387191004 endingPage "121800" @default.
• W4387191004 startingPage "121800" @default.
• W4387191004 abstract "The histopathological analysis of a suspected region is critical for cancer diagnosis, treatment, and management. Histopathological diagnosis consists in analyzing the characteristics of the lesions using tissue sections stained with hematoxylin and eosin. Classification of digital tumor pathology images, called whole slide images (WSIs), is a great challenge since WSIs usually have huge resolutions while lacking localized annotations. Multiple instance learning (MIL) is a commonly used method applied to pathological image analysis. However, most MIL methods often focus only on the global representation of WSIs, ignoring whether the category labels play other roles in the model training besides being a supervision signal. In addition, feature confusion is also a problem that should be avoided for the analysis of WSIs with weakly supervised methods. To address these problems, we propose a novel algorithm of classifying WSI for cancer diagnosis. The proposed model, ProMIL, uses only slide-level labels rather than localized annotations for analysis. There are three innovations in this work. Firstly, we present the concept of class proxy which is the representation of the intrinsic feature of each category, and plays a key role in guiding the training of the model. Secondly, we design a novel WSI representation learning module that utilizes a multi-scale feature extraction strategy to represent each patch in a WSI and then aggregates these representations using an attention mechanism to encode the WSI. Thirdly, we design a metric-learning-based weakly supervised multiclass-classifier by measuring the similarity between each WSI embedding and class proxies. The proposed ProMIL can effectively alleviate the side effect of feature confusion, and carry intuitive interpretability and scalability. To evaluate the performance of ProMIL, we conduct a series of experiments on several datasets of WSIs with different types of cancer from open data sources. It can be observed from the experimental results that ProMIL outperforms most of the compared methods and achieves better performance on a various type of cancer image data for classification, thus suggesting the proposed method is suitable for classifying different categories of cancer rather than a specific kind of cancer. Therefore, it is expected to act as a general framework to be extended to more cancer diagnoses." @default.
• W4387191004 created "2023-09-30" @default.
• W4387191004 creator A5018308240 @default.
• W4387191004 creator A5030402313 @default.
• W4387191004 creator A5034261700 @default.
• W4387191004 creator A5049978856 @default.
• W4387191004 creator A5088929013 @default.
• W4387191004 date "2024-03-01" @default.
• W4387191004 modified "2023-10-16" @default.
• W4387191004 title "ProMIL: A weakly supervised multiple instance learning for whole slide image classification based on class proxy" @default.
• W4387191004 cites W1994488211 @default.
• W4387191004 cites W2044523229 @default.
• W4387191004 cites W2110119381 @default.
• W4387191004 cites W2117539524 @default.
• W4387191004 cites W2133059825 @default.
• W4387191004 cites W2468387181 @default.
• W4387191004 cites W2531897166 @default.
• W4387191004 cites W2716665989 @default.
• W4387191004 cites W2798991696 @default.
• W4387191004 cites W2894084084 @default.
• W4387191004 cites W2900257566 @default.
• W4387191004 cites W2914836117 @default.
• W4387191004 cites W2956228567 @default.
• W4387191004 cites W2962898354 @default.
• W4387191004 cites W2963466847 @default.
• W4387191004 cites W2963952323 @default.
• W4387191004 cites W2964271799 @default.
• W4387191004 cites W2969985801 @default.
• W4387191004 cites W2986297814 @default.
• W4387191004 cites W2991603289 @default.
• W4387191004 cites W2997424368 @default.
• W4387191004 cites W3035524453 @default.
• W4387191004 cites W3089090082 @default.
• W4387191004 cites W3102988878 @default.
• W4387191004 cites W3103152812 @default.
• W4387191004 cites W3105220622 @default.
• W4387191004 cites W3126296879 @default.
• W4387191004 cites W3132799678 @default.
• W4387191004 cites W3135547872 @default.
• W4387191004 cites W3176719058 @default.
• W4387191004 cites W3197713479 @default.
• W4387191004 cites W3202280620 @default.
• W4387191004 cites W4290052641 @default.
• W4387191004 cites W4312765357 @default.
• W4387191004 cites W4313065529 @default.
• W4387191004 doi "https://doi.org/10.1016/j.eswa.2023.121800" @default.
• W4387191004 hasPublicationYear "2024" @default.
• W4387191004 type Work @default.
• W4387191004 citedByCount "0" @default.
• W4387191004 crossrefType "journal-article" @default.
• W4387191004 hasAuthorship W4387191004A5018308240 @default.
• W4387191004 hasAuthorship W4387191004A5030402313 @default.
• W4387191004 hasAuthorship W4387191004A5034261700 @default.
• W4387191004 hasAuthorship W4387191004A5049978856 @default.
• W4387191004 hasAuthorship W4387191004A5088929013 @default.
• W4387191004 hasConcept C119857082 @default.
• W4387191004 hasConcept C12267149 @default.
• W4387191004 hasConcept C123860398 @default.
• W4387191004 hasConcept C138885662 @default.
• W4387191004 hasConcept C153180895 @default.
• W4387191004 hasConcept C154945302 @default.
• W4387191004 hasConcept C2776401178 @default.
• W4387191004 hasConcept C2777212361 @default.
• W4387191004 hasConcept C2777522853 @default.
• W4387191004 hasConcept C41008148 @default.
• W4387191004 hasConcept C41608201 @default.
• W4387191004 hasConcept C41895202 @default.
• W4387191004 hasConcept C95623464 @default.
• W4387191004 hasConceptScore W4387191004C119857082 @default.
• W4387191004 hasConceptScore W4387191004C12267149 @default.
• W4387191004 hasConceptScore W4387191004C123860398 @default.
• W4387191004 hasConceptScore W4387191004C138885662 @default.
• W4387191004 hasConceptScore W4387191004C153180895 @default.
• W4387191004 hasConceptScore W4387191004C154945302 @default.
• W4387191004 hasConceptScore W4387191004C2776401178 @default.
• W4387191004 hasConceptScore W4387191004C2777212361 @default.
• W4387191004 hasConceptScore W4387191004C2777522853 @default.
• W4387191004 hasConceptScore W4387191004C41008148 @default.
• W4387191004 hasConceptScore W4387191004C41608201 @default.
• W4387191004 hasConceptScore W4387191004C41895202 @default.
• W4387191004 hasConceptScore W4387191004C95623464 @default.
• W4387191004 hasLocation W43871910041 @default.
• W4387191004 hasOpenAccess W4387191004 @default.
• W4387191004 hasPrimaryLocation W43871910041 @default.
• W4387191004 hasRelatedWork W1975767702 @default.
• W4387191004 hasRelatedWork W2136729892 @default.
• W4387191004 hasRelatedWork W2345479200 @default.
• W4387191004 hasRelatedWork W2549990292 @default.
• W4387191004 hasRelatedWork W2849310602 @default.
• W4387191004 hasRelatedWork W2951819827 @default.
• W4387191004 hasRelatedWork W3128797991 @default.
• W4387191004 hasRelatedWork W4212803330 @default.
• W4387191004 hasRelatedWork W2183306018 @default.
• W4387191004 hasRelatedWork W3111219495 @default.
• W4387191004 hasVolume "238" @default.
• W4387191004 isParatext "false" @default.
• W4387191004 isRetracted "false" @default.
• W4387191004 workType "article" @default.