FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308714061> ?p ?o ?g. }

• W4308714061 abstract "Abstract Background Multiplex immunofluorescence (mIF) can provide invaluable insights into spatial biology and the complexities of the immune tumor microenvironment (iTME). However, existing analysis approaches are both laborious and highly user-dependent. In order to overcome these limitations we developed a novel, end-to-end deep learning (DL) pipeline for rapid and accurate analysis of both tumor-microarray (TMA) and whole slide mIF images. Methods Our pipeline consists of two DL models: a multi-classifier for classifying multi-channel cell images into 12 different cell types, and a binary classifier for determining the positivity of a given marker in single-channel images. The DL multi-classifier was trained on 7,000 tiles labeled with cell annotations from a publicly available CODEX dataset, consisting of 140 tissue cores from 35 colorectal cancer (CRC) patients. For the binary classifier training, the multi-channel tiles were further split into ∼100,000 single-channel tiles, for which the ground truth was inferred from the known expression of these markers in each cell-type. This DL binary classifier was then utilized to quantify the positivity of various cell state (phenotypic) markers. In addition, the binary classifier was exploited as a cell-typing tool, by predicting the positivity of individual lineage cell markers. The performance of our DL models was evaluated on 1,800 annotations from 14 test tissue cores. The models were further evaluated on a new 6-plex melanoma cohort, stained with PhenoImager®, and were compared to the performance of clustering, manual thresholding or machine learning-based cell-typing methods applied on the same test sets. Results Our DL multi-classifier achieved highly accurate results, outperforming all of the tested cell-typing methods, including clustering, manual-thresholding and ML-based approaches, in both CODEX CRC and PhenoImager melanoma cohorts (accuracy of 91% and 87%, respectively), with F1-scores above 80% in the vast majority of cell types. Our DL binary classifier, which was trained solely on the lineage markers of the CRC dataset, also outperformed existing methods, demonstrating excellent F1-scores (>80%) for determining the positivity of unseen phenotypic and lineage markers across the two tumor types and imaging modalities. Notably, as little as 20 annotations were required in order to boost the performance on an unseen dataset to above 85% accuracy and 80% F1-scores. As a result, the DL binary classifier could successfully be used as a cell-typing model, in a manner that is transferable between experimental approaches. Conclusions We present a novel state-of-the-art DL-based framework for multiplex imaging analysis, that enables accurate cell typing and phenotypic marker quantification, which is robust across markers, tumor indications, and imaging modalities." @default.
• W4308714061 created "2022-11-14" @default.
• W4308714061 creator A5002092709 @default.
• W4308714061 creator A5002526652 @default.
• W4308714061 creator A5017559288 @default.
• W4308714061 creator A5023153328 @default.
• W4308714061 creator A5025628455 @default.
• W4308714061 creator A5026965924 @default.
• W4308714061 creator A5042976072 @default.
• W4308714061 creator A5045568372 @default.
• W4308714061 creator A5054364242 @default.
• W4308714061 creator A5055153211 @default.
• W4308714061 creator A5058238015 @default.
• W4308714061 creator A5064253891 @default.
• W4308714061 creator A5072041544 @default.
• W4308714061 creator A5073537601 @default.
• W4308714061 creator A5078199228 @default.
• W4308714061 creator A5078781359 @default.
• W4308714061 creator A5091889780 @default.
• W4308714061 date "2022-11-10" @default.
• W4308714061 modified "2023-09-26" @default.
• W4308714061 title "A novel deep learning pipeline for cell typing and phenotypic marker quantification in multiplex imaging" @default.
• W4308714061 cites W2344591493 @default.
• W4308714061 cites W2609921003 @default.
• W4308714061 cites W2801309958 @default.
• W4308714061 cites W2890156321 @default.
• W4308714061 cites W2899783716 @default.
• W4308714061 cites W2922475342 @default.
• W4308714061 cites W3047081808 @default.
• W4308714061 cites W3182552500 @default.
• W4308714061 cites W3191029526 @default.
• W4308714061 cites W3194189918 @default.
• W4308714061 cites W4281733104 @default.
• W4308714061 doi "https://doi.org/10.1101/2022.11.09.515776" @default.
• W4308714061 hasPublicationYear "2022" @default.
• W4308714061 type Work @default.
• W4308714061 citedByCount "0" @default.
• W4308714061 crossrefType "posted-content" @default.
• W4308714061 hasAuthorship W4308714061A5002092709 @default.
• W4308714061 hasAuthorship W4308714061A5002526652 @default.
• W4308714061 hasAuthorship W4308714061A5017559288 @default.
• W4308714061 hasAuthorship W4308714061A5023153328 @default.
• W4308714061 hasAuthorship W4308714061A5025628455 @default.
• W4308714061 hasAuthorship W4308714061A5026965924 @default.
• W4308714061 hasAuthorship W4308714061A5042976072 @default.
• W4308714061 hasAuthorship W4308714061A5045568372 @default.
• W4308714061 hasAuthorship W4308714061A5054364242 @default.
• W4308714061 hasAuthorship W4308714061A5055153211 @default.
• W4308714061 hasAuthorship W4308714061A5058238015 @default.
• W4308714061 hasAuthorship W4308714061A5064253891 @default.
• W4308714061 hasAuthorship W4308714061A5072041544 @default.
• W4308714061 hasAuthorship W4308714061A5073537601 @default.
• W4308714061 hasAuthorship W4308714061A5078199228 @default.
• W4308714061 hasAuthorship W4308714061A5078781359 @default.
• W4308714061 hasAuthorship W4308714061A5091889780 @default.
• W4308714061 hasBestOaLocation W43087140611 @default.
• W4308714061 hasConcept C119857082 @default.
• W4308714061 hasConcept C121608353 @default.
• W4308714061 hasConcept C12267149 @default.
• W4308714061 hasConcept C153180895 @default.
• W4308714061 hasConcept C154945302 @default.
• W4308714061 hasConcept C193270364 @default.
• W4308714061 hasConcept C2781188995 @default.
• W4308714061 hasConcept C2781209916 @default.
• W4308714061 hasConcept C28490314 @default.
• W4308714061 hasConcept C41008148 @default.
• W4308714061 hasConcept C54355233 @default.
• W4308714061 hasConcept C60644358 @default.
• W4308714061 hasConcept C70721500 @default.
• W4308714061 hasConcept C73555534 @default.
• W4308714061 hasConcept C86803240 @default.
• W4308714061 hasConcept C95623464 @default.
• W4308714061 hasConceptScore W4308714061C119857082 @default.
• W4308714061 hasConceptScore W4308714061C121608353 @default.
• W4308714061 hasConceptScore W4308714061C12267149 @default.
• W4308714061 hasConceptScore W4308714061C153180895 @default.
• W4308714061 hasConceptScore W4308714061C154945302 @default.
• W4308714061 hasConceptScore W4308714061C193270364 @default.
• W4308714061 hasConceptScore W4308714061C2781188995 @default.
• W4308714061 hasConceptScore W4308714061C2781209916 @default.
• W4308714061 hasConceptScore W4308714061C28490314 @default.
• W4308714061 hasConceptScore W4308714061C41008148 @default.
• W4308714061 hasConceptScore W4308714061C54355233 @default.
• W4308714061 hasConceptScore W4308714061C60644358 @default.
• W4308714061 hasConceptScore W4308714061C70721500 @default.
• W4308714061 hasConceptScore W4308714061C73555534 @default.
• W4308714061 hasConceptScore W4308714061C86803240 @default.
• W4308714061 hasConceptScore W4308714061C95623464 @default.
• W4308714061 hasLocation W43087140611 @default.
• W4308714061 hasOpenAccess W4308714061 @default.
• W4308714061 hasPrimaryLocation W43087140611 @default.
• W4308714061 hasRelatedWork W2041399278 @default.
• W4308714061 hasRelatedWork W2041636156 @default.
• W4308714061 hasRelatedWork W2099369243 @default.
• W4308714061 hasRelatedWork W2136184105 @default.
• W4308714061 hasRelatedWork W2160451891 @default.
• W4308714061 hasRelatedWork W3194539120 @default.
• W4308714061 hasRelatedWork W4223656335 @default.
• W4308714061 hasRelatedWork W4242764575 @default.
• W4308714061 hasRelatedWork W2187500075 @default.

• next