Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920983249> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2920983249 abstract "Histologic grading from images has become widely accepted as a powerful indicator of prognosis in breast cancer. Automated grading can assist the doctor diagnosing the medical condition. But algorithms still lag behind human experts in this task, as human experts excel in identifying parts, detecting characteristics and relating concepts and semantics. This can be improved by making algorithms distinguish and characterize the most relevant types of objects in the image and characterizing images from that. We propose a three-stage automated approach named OBI (Object-based Identification) with steps: 1. Object-based identification, which identifies the “type of object” of each region and characterizes it; 2. Learn about image, which characterizes distribution of characteristics of those types of objects in image; 3. Determination of degree of malignancy, which assigns a degree of malignancy based on a classifier over object type characteristics (the statistical distribution of characteristics of structures) in the image. Our proof-of-concept prototype uses publicly-available Mytos-Atypia dataset [19] to compare accuracy with alternatives. Results summary: human expert (medical doctor) 84%, classic machine learning 74%, convolution neural networks (CNN), 78%, our approach (OBI) 86%. As future work, we expect to generalize our results to other datasets and problems, explore mimicking knowledge of human concepts further, merge the object-based approach with CNN techniques and adapt it to other medical imaging contexts." @default.
- W2920983249 created "2019-03-22" @default.
- W2920983249 creator A5049382757 @default.
- W2920983249 date "2019-03-15" @default.
- W2920983249 modified "2023-09-26" @default.
- W2920983249 title "Objects characterization-based approach to enhance detection of degree of malignancy in breast cancer histopathology" @default.
- W2920983249 cites W1932198206 @default.
- W2920983249 cites W1970120446 @default.
- W2920983249 cites W1977442670 @default.
- W2920983249 cites W2105421062 @default.
- W2920983249 cites W2107901014 @default.
- W2920983249 cites W2127831489 @default.
- W2920983249 cites W2151608510 @default.
- W2920983249 cites W2344480160 @default.
- W2920983249 cites W2549267210 @default.
- W2920983249 cites W2559256154 @default.
- W2920983249 cites W4238254613 @default.
- W2920983249 doi "https://doi.org/10.1117/12.2511986" @default.
- W2920983249 hasPublicationYear "2019" @default.
- W2920983249 type Work @default.
- W2920983249 sameAs 2920983249 @default.
- W2920983249 citedByCount "2" @default.
- W2920983249 countsByYear W29209832492019 @default.
- W2920983249 countsByYear W29209832492020 @default.
- W2920983249 crossrefType "proceedings-article" @default.
- W2920983249 hasAuthorship W2920983249A5049382757 @default.
- W2920983249 hasConcept C121332964 @default.
- W2920983249 hasConcept C121608353 @default.
- W2920983249 hasConcept C126322002 @default.
- W2920983249 hasConcept C142724271 @default.
- W2920983249 hasConcept C24890656 @default.
- W2920983249 hasConcept C2775997480 @default.
- W2920983249 hasConcept C2779399171 @default.
- W2920983249 hasConcept C2985322473 @default.
- W2920983249 hasConcept C41008148 @default.
- W2920983249 hasConcept C530470458 @default.
- W2920983249 hasConcept C544855455 @default.
- W2920983249 hasConcept C71924100 @default.
- W2920983249 hasConceptScore W2920983249C121332964 @default.
- W2920983249 hasConceptScore W2920983249C121608353 @default.
- W2920983249 hasConceptScore W2920983249C126322002 @default.
- W2920983249 hasConceptScore W2920983249C142724271 @default.
- W2920983249 hasConceptScore W2920983249C24890656 @default.
- W2920983249 hasConceptScore W2920983249C2775997480 @default.
- W2920983249 hasConceptScore W2920983249C2779399171 @default.
- W2920983249 hasConceptScore W2920983249C2985322473 @default.
- W2920983249 hasConceptScore W2920983249C41008148 @default.
- W2920983249 hasConceptScore W2920983249C530470458 @default.
- W2920983249 hasConceptScore W2920983249C544855455 @default.
- W2920983249 hasConceptScore W2920983249C71924100 @default.
- W2920983249 hasLocation W29209832491 @default.
- W2920983249 hasOpenAccess W2920983249 @default.
- W2920983249 hasPrimaryLocation W29209832491 @default.
- W2920983249 hasRelatedWork W1974013817 @default.
- W2920983249 hasRelatedWork W2014447844 @default.
- W2920983249 hasRelatedWork W2419874298 @default.
- W2920983249 hasRelatedWork W3032710552 @default.
- W2920983249 hasRelatedWork W3122712013 @default.
- W2920983249 hasRelatedWork W3210389428 @default.
- W2920983249 hasRelatedWork W4307984913 @default.
- W2920983249 hasRelatedWork W4308010588 @default.
- W2920983249 hasRelatedWork W2182713959 @default.
- W2920983249 hasRelatedWork W2184883450 @default.
- W2920983249 isParatext "false" @default.
- W2920983249 isRetracted "false" @default.
- W2920983249 magId "2920983249" @default.
- W2920983249 workType "article" @default.