Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382600492> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4382600492 endingPage "e0287301" @default.
- W4382600492 startingPage "e0287301" @default.
- W4382600492 abstract "Recent advancements in computer vision and neural networks have facilitated the medical imaging survival analysis for various medical applications. However, challenges arise when patients have multiple images from multiple lesions, as current deep learning methods provide multiple survival predictions for each patient, complicating result interpretation. To address this issue, we developed a deep learning survival model that can provide accurate predictions at the patient level. We propose a deep attention long short-term memory embedded aggregation network (DALAN) for histopathology images, designed to simultaneously perform feature extraction and aggregation of lesion images. This design enables the model to efficiently learn imaging features from lesions and aggregate lesion-level information to the patient level. DALAN comprises a weight-shared CNN, attention layers, and LSTM layers. The attention layer calculates the significance of each lesion image, while the LSTM layer combines the weighted information to produce an all-encompassing representation of the patient’s lesion data. Our proposed method performed better on both simulated and real data than other competing methods in terms of prediction accuracy. We evaluated DALAN against several naive aggregation methods on simulated and real datasets. Our results showed that DALAN outperformed the competing methods in terms of c-index on the MNIST and Cancer dataset simulations. On the real TCGA dataset, DALAN also achieved a higher c-index of 0.803±0.006 compared to the naive methods and the competing models. Our DALAN effectively aggregates multiple histopathology images, demonstrating a comprehensive survival model using attention and LSTM mechanisms." @default.
- W4382600492 created "2023-06-30" @default.
- W4382600492 creator A5039234270 @default.
- W4382600492 creator A5046802258 @default.
- W4382600492 date "2023-06-29" @default.
- W4382600492 modified "2023-10-15" @default.
- W4382600492 title "A deep attention LSTM embedded aggregation network for multiple histopathological images" @default.
- W4382600492 cites W1812256879 @default.
- W4382600492 cites W1836650925 @default.
- W4382600492 cites W1977756844 @default.
- W4382600492 cites W2007900522 @default.
- W4382600492 cites W2033442541 @default.
- W4382600492 cites W2064675550 @default.
- W4382600492 cites W2112796928 @default.
- W4382600492 cites W2194775991 @default.
- W4382600492 cites W228600387 @default.
- W4382600492 cites W2343160907 @default.
- W4382600492 cites W2571620227 @default.
- W4382600492 cites W2753919178 @default.
- W4382600492 cites W2761668583 @default.
- W4382600492 cites W2765366332 @default.
- W4382600492 cites W2799291955 @default.
- W4382600492 cites W2891590469 @default.
- W4382600492 cites W2956228567 @default.
- W4382600492 cites W2971045153 @default.
- W4382600492 cites W3004016611 @default.
- W4382600492 cites W3043535018 @default.
- W4382600492 cites W3100084586 @default.
- W4382600492 cites W3135547872 @default.
- W4382600492 cites W3172710683 @default.
- W4382600492 cites W3176016422 @default.
- W4382600492 cites W4200609800 @default.
- W4382600492 cites W4285385978 @default.
- W4382600492 cites W4290975899 @default.
- W4382600492 doi "https://doi.org/10.1371/journal.pone.0287301" @default.
- W4382600492 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37384648" @default.
- W4382600492 hasPublicationYear "2023" @default.
- W4382600492 type Work @default.
- W4382600492 citedByCount "1" @default.
- W4382600492 countsByYear W43826004922023 @default.
- W4382600492 crossrefType "journal-article" @default.
- W4382600492 hasAuthorship W4382600492A5039234270 @default.
- W4382600492 hasAuthorship W4382600492A5046802258 @default.
- W4382600492 hasBestOaLocation W43826004921 @default.
- W4382600492 hasConcept C108583219 @default.
- W4382600492 hasConcept C119857082 @default.
- W4382600492 hasConcept C138885662 @default.
- W4382600492 hasConcept C142724271 @default.
- W4382600492 hasConcept C153180895 @default.
- W4382600492 hasConcept C154945302 @default.
- W4382600492 hasConcept C190502265 @default.
- W4382600492 hasConcept C2776401178 @default.
- W4382600492 hasConcept C2781156865 @default.
- W4382600492 hasConcept C41008148 @default.
- W4382600492 hasConcept C41895202 @default.
- W4382600492 hasConcept C52622490 @default.
- W4382600492 hasConcept C71924100 @default.
- W4382600492 hasConceptScore W4382600492C108583219 @default.
- W4382600492 hasConceptScore W4382600492C119857082 @default.
- W4382600492 hasConceptScore W4382600492C138885662 @default.
- W4382600492 hasConceptScore W4382600492C142724271 @default.
- W4382600492 hasConceptScore W4382600492C153180895 @default.
- W4382600492 hasConceptScore W4382600492C154945302 @default.
- W4382600492 hasConceptScore W4382600492C190502265 @default.
- W4382600492 hasConceptScore W4382600492C2776401178 @default.
- W4382600492 hasConceptScore W4382600492C2781156865 @default.
- W4382600492 hasConceptScore W4382600492C41008148 @default.
- W4382600492 hasConceptScore W4382600492C41895202 @default.
- W4382600492 hasConceptScore W4382600492C52622490 @default.
- W4382600492 hasConceptScore W4382600492C71924100 @default.
- W4382600492 hasFunder F4320320671 @default.
- W4382600492 hasIssue "6" @default.
- W4382600492 hasLocation W43826004921 @default.
- W4382600492 hasLocation W43826004922 @default.
- W4382600492 hasLocation W43826004923 @default.
- W4382600492 hasOpenAccess W4382600492 @default.
- W4382600492 hasPrimaryLocation W43826004921 @default.
- W4382600492 hasRelatedWork W2590796488 @default.
- W4382600492 hasRelatedWork W2734358244 @default.
- W4382600492 hasRelatedWork W2750384547 @default.
- W4382600492 hasRelatedWork W2809732489 @default.
- W4382600492 hasRelatedWork W2886711096 @default.
- W4382600492 hasRelatedWork W2950475743 @default.
- W4382600492 hasRelatedWork W3046591097 @default.
- W4382600492 hasRelatedWork W3088091256 @default.
- W4382600492 hasRelatedWork W4380078352 @default.
- W4382600492 hasRelatedWork W4386603768 @default.
- W4382600492 hasVolume "18" @default.
- W4382600492 isParatext "false" @default.
- W4382600492 isRetracted "false" @default.
- W4382600492 workType "article" @default.