Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211646> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387211646 endingPage "744" @default.
- W4387211646 startingPage "735" @default.
- W4387211646 abstract "As the primary treatment option for cataracts, it is estimated that millions of cataract surgeries are performed each year globally. Predicting the Best Corrected Visual Acuity (BCVA) in cataract patients is crucial before surgeries to avoid medical disputes. However, accurate prediction remains a challenge in clinical practice. Traditional methods based on patient characteristics and surgical parameters have limited accuracy and often underestimate postoperative visual acuity. In this paper, we propose a novel framework for predicting visual acuity after cataract surgery using masked self-attention. Especially different from existing methods, which are based on monomodal data, our proposed method takes preoperative images and patient demographic data as input to leverage multimodal information. Furthermore, we expand our method to a more complex and challenging clinical scenario, i.e., the incomplete multimodal data. Firstly, we apply efficient Transformers to extract modality-specific features. Then, an attentional fusion network is utilized to fuse the multimodal information. To address the modality-missing problem, an attention mask mechanism is proposed to improve the robustness. We evaluate our method on a collected dataset of 1960 patients who underwent cataract surgery and compare its performance with other state-of-the-art approaches. The results show that our proposed method outperforms other methods and achieves a mean absolute error of 0.122 logMAR. The percentages of the prediction errors within ± 0.10 logMAR are 94.3%. Besides, extensive experiments are conducted to investigate the effectiveness of each component in predicting visual acuity. Codes will be available at https://github.com/liyiersan/MSA ." @default.
- W4387211646 created "2023-10-01" @default.
- W4387211646 creator A5002711718 @default.
- W4387211646 creator A5015897349 @default.
- W4387211646 creator A5043300518 @default.
- W4387211646 creator A5043706626 @default.
- W4387211646 date "2023-01-01" @default.
- W4387211646 modified "2023-10-01" @default.
- W4387211646 title "Incomplete Multimodal Learning for Visual Acuity Prediction After Cataract Surgery Using Masked Self-Attention" @default.
- W4387211646 cites W105145916 @default.
- W4387211646 cites W2181051149 @default.
- W4387211646 cites W2617842795 @default.
- W4387211646 cites W3015571459 @default.
- W4387211646 cites W3096609285 @default.
- W4387211646 cites W3115898000 @default.
- W4387211646 cites W3139816046 @default.
- W4387211646 cites W3165634772 @default.
- W4387211646 cites W3170841864 @default.
- W4387211646 cites W3175825020 @default.
- W4387211646 cites W4214724890 @default.
- W4387211646 cites W4295938041 @default.
- W4387211646 cites W4312980231 @default.
- W4387211646 cites W4313164293 @default.
- W4387211646 cites W4313452854 @default.
- W4387211646 doi "https://doi.org/10.1007/978-3-031-43990-2_69" @default.
- W4387211646 hasPublicationYear "2023" @default.
- W4387211646 type Work @default.
- W4387211646 citedByCount "0" @default.
- W4387211646 crossrefType "book-chapter" @default.
- W4387211646 hasAuthorship W4387211646A5002711718 @default.
- W4387211646 hasAuthorship W4387211646A5015897349 @default.
- W4387211646 hasAuthorship W4387211646A5043300518 @default.
- W4387211646 hasAuthorship W4387211646A5043706626 @default.
- W4387211646 hasConcept C104317684 @default.
- W4387211646 hasConcept C118487528 @default.
- W4387211646 hasConcept C119857082 @default.
- W4387211646 hasConcept C153083717 @default.
- W4387211646 hasConcept C154945302 @default.
- W4387211646 hasConcept C185592680 @default.
- W4387211646 hasConcept C2775888743 @default.
- W4387211646 hasConcept C2778257484 @default.
- W4387211646 hasConcept C2780225610 @default.
- W4387211646 hasConcept C41008148 @default.
- W4387211646 hasConcept C55493867 @default.
- W4387211646 hasConcept C63479239 @default.
- W4387211646 hasConcept C71924100 @default.
- W4387211646 hasConcept C9357733 @default.
- W4387211646 hasConceptScore W4387211646C104317684 @default.
- W4387211646 hasConceptScore W4387211646C118487528 @default.
- W4387211646 hasConceptScore W4387211646C119857082 @default.
- W4387211646 hasConceptScore W4387211646C153083717 @default.
- W4387211646 hasConceptScore W4387211646C154945302 @default.
- W4387211646 hasConceptScore W4387211646C185592680 @default.
- W4387211646 hasConceptScore W4387211646C2775888743 @default.
- W4387211646 hasConceptScore W4387211646C2778257484 @default.
- W4387211646 hasConceptScore W4387211646C2780225610 @default.
- W4387211646 hasConceptScore W4387211646C41008148 @default.
- W4387211646 hasConceptScore W4387211646C55493867 @default.
- W4387211646 hasConceptScore W4387211646C63479239 @default.
- W4387211646 hasConceptScore W4387211646C71924100 @default.
- W4387211646 hasConceptScore W4387211646C9357733 @default.
- W4387211646 hasLocation W43872116461 @default.
- W4387211646 hasOpenAccess W4387211646 @default.
- W4387211646 hasPrimaryLocation W43872116461 @default.
- W4387211646 hasRelatedWork W2004912592 @default.
- W4387211646 hasRelatedWork W2053196557 @default.
- W4387211646 hasRelatedWork W2075843574 @default.
- W4387211646 hasRelatedWork W2461336085 @default.
- W4387211646 hasRelatedWork W3119736004 @default.
- W4387211646 hasRelatedWork W3173595162 @default.
- W4387211646 hasRelatedWork W4205247288 @default.
- W4387211646 hasRelatedWork W4232707728 @default.
- W4387211646 hasRelatedWork W4307839771 @default.
- W4387211646 hasRelatedWork W4307843927 @default.
- W4387211646 isParatext "false" @default.
- W4387211646 isRetracted "false" @default.
- W4387211646 workType "book-chapter" @default.