Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202645152> ?p ?o ?g. }
- W3202645152 abstract "Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advances and increased data availability. However, the high costs of annotations hinder the collection of large and completely labeled datasets, motivating semi-supervised detection approaches. In this paper, we introduce mean teacher hetero-modal detection (MTHD), which addresses two important gaps in current semi-supervised detection. First, it is not obvious how to enforce unlabeled consistency constraints across the very different outputs of various detectors, which has resulted in various compromises being used in the state of the art. Using an anchor-free framework, MTHD formulates a mean teacher approach without such compromises, enforcing consistency on the soft-output of object centers and size. Second, multi-sequence data is often critical, e.g., for abdominal lesion detection, but unlabeled data is often missing sequences. To deal with this, MTHD incorporates hetero-modal learning in its framework. Unlike prior art, MTHD is able to incorporate an expansive set of consistency constraints that include geometric transforms and random sequence combinations. We train and evaluate MTHD on liver lesion detection using the largest MR lesion dataset to date (1099 patients with (>5000) volumes). MTHD surpasses the best fully-supervised and semi-supervised competitors by (10.1%) and (3.5%), respectively, in average sensitivity." @default.
- W3202645152 created "2021-10-11" @default.
- W3202645152 creator A5015929533 @default.
- W3202645152 creator A5016038454 @default.
- W3202645152 creator A5030025128 @default.
- W3202645152 creator A5037220775 @default.
- W3202645152 creator A5045227579 @default.
- W3202645152 creator A5049078993 @default.
- W3202645152 creator A5058215578 @default.
- W3202645152 creator A5069536954 @default.
- W3202645152 creator A5085898704 @default.
- W3202645152 creator A5086574909 @default.
- W3202645152 date "2021-01-01" @default.
- W3202645152 modified "2023-10-16" @default.
- W3202645152 title "Hetero-Modal Learning and Expansive Consistency Constraints for Semi-supervised Detection from Multi-sequence Data" @default.
- W3202645152 cites W1861492603 @default.
- W3202645152 cites W2024569129 @default.
- W3202645152 cites W2048679005 @default.
- W3202645152 cites W2502805798 @default.
- W3202645152 cites W2603225292 @default.
- W3202645152 cites W2754374720 @default.
- W3202645152 cites W2883683269 @default.
- W3202645152 cites W2884584803 @default.
- W3202645152 cites W2978017498 @default.
- W3202645152 cites W2979564444 @default.
- W3202645152 cites W2980091915 @default.
- W3202645152 cites W2997936889 @default.
- W3202645152 cites W3014795415 @default.
- W3202645152 cites W3035396860 @default.
- W3202645152 cites W3035406940 @default.
- W3202645152 cites W3084433012 @default.
- W3202645152 cites W3108112547 @default.
- W3202645152 cites W3117686595 @default.
- W3202645152 cites W3176293577 @default.
- W3202645152 doi "https://doi.org/10.1007/978-3-030-87589-3_31" @default.
- W3202645152 hasPublicationYear "2021" @default.
- W3202645152 type Work @default.
- W3202645152 sameAs 3202645152 @default.
- W3202645152 citedByCount "0" @default.
- W3202645152 crossrefType "book-chapter" @default.
- W3202645152 hasAuthorship W3202645152A5015929533 @default.
- W3202645152 hasAuthorship W3202645152A5016038454 @default.
- W3202645152 hasAuthorship W3202645152A5030025128 @default.
- W3202645152 hasAuthorship W3202645152A5037220775 @default.
- W3202645152 hasAuthorship W3202645152A5045227579 @default.
- W3202645152 hasAuthorship W3202645152A5049078993 @default.
- W3202645152 hasAuthorship W3202645152A5058215578 @default.
- W3202645152 hasAuthorship W3202645152A5069536954 @default.
- W3202645152 hasAuthorship W3202645152A5085898704 @default.
- W3202645152 hasAuthorship W3202645152A5086574909 @default.
- W3202645152 hasBestOaLocation W32026451522 @default.
- W3202645152 hasConcept C119857082 @default.
- W3202645152 hasConcept C124101348 @default.
- W3202645152 hasConcept C153180895 @default.
- W3202645152 hasConcept C154945302 @default.
- W3202645152 hasConcept C159985019 @default.
- W3202645152 hasConcept C185592680 @default.
- W3202645152 hasConcept C188027245 @default.
- W3202645152 hasConcept C192562407 @default.
- W3202645152 hasConcept C2776145971 @default.
- W3202645152 hasConcept C2776436953 @default.
- W3202645152 hasConcept C2778112365 @default.
- W3202645152 hasConcept C2780502288 @default.
- W3202645152 hasConcept C30407753 @default.
- W3202645152 hasConcept C41008148 @default.
- W3202645152 hasConcept C54355233 @default.
- W3202645152 hasConcept C58973888 @default.
- W3202645152 hasConcept C71139939 @default.
- W3202645152 hasConcept C86803240 @default.
- W3202645152 hasConceptScore W3202645152C119857082 @default.
- W3202645152 hasConceptScore W3202645152C124101348 @default.
- W3202645152 hasConceptScore W3202645152C153180895 @default.
- W3202645152 hasConceptScore W3202645152C154945302 @default.
- W3202645152 hasConceptScore W3202645152C159985019 @default.
- W3202645152 hasConceptScore W3202645152C185592680 @default.
- W3202645152 hasConceptScore W3202645152C188027245 @default.
- W3202645152 hasConceptScore W3202645152C192562407 @default.
- W3202645152 hasConceptScore W3202645152C2776145971 @default.
- W3202645152 hasConceptScore W3202645152C2776436953 @default.
- W3202645152 hasConceptScore W3202645152C2778112365 @default.
- W3202645152 hasConceptScore W3202645152C2780502288 @default.
- W3202645152 hasConceptScore W3202645152C30407753 @default.
- W3202645152 hasConceptScore W3202645152C41008148 @default.
- W3202645152 hasConceptScore W3202645152C54355233 @default.
- W3202645152 hasConceptScore W3202645152C58973888 @default.
- W3202645152 hasConceptScore W3202645152C71139939 @default.
- W3202645152 hasConceptScore W3202645152C86803240 @default.
- W3202645152 hasLocation W32026451521 @default.
- W3202645152 hasLocation W32026451522 @default.
- W3202645152 hasOpenAccess W3202645152 @default.
- W3202645152 hasPrimaryLocation W32026451521 @default.
- W3202645152 hasRelatedWork W10719664 @default.
- W3202645152 hasRelatedWork W10944326 @default.
- W3202645152 hasRelatedWork W12820539 @default.
- W3202645152 hasRelatedWork W3979659 @default.
- W3202645152 hasRelatedWork W4771408 @default.
- W3202645152 hasRelatedWork W6266756 @default.
- W3202645152 hasRelatedWork W6581905 @default.
- W3202645152 hasRelatedWork W6869908 @default.
- W3202645152 hasRelatedWork W7046360 @default.