Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183499274> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3183499274 endingPage "012030" @default.
- W3183499274 startingPage "012030" @default.
- W3183499274 abstract "Abstract Pneumothorax is a lung emergency. Automated computer-aid pneumothorax diagnosis based on chest X-ray can help reduce the diagnostic time and save valuable time for the treatment. A total of 21,759 patient’s frontal-view chest X-ray images from one medical center are used in this study. The dataset is divided into two categories: pneumothorax and non-pneumothorax, which are evaluated by two radiologists with over ten years of practical experience. A two-stage training for pneumothorax classification based on multi-instance learning (MIL) are proposed, first training a patch-level classifier, followed by an image-level classifier training, which is initialized with the patch pre-trained weights. The image-level classifier initialized with patch pre-trained weights achieves good classification performance with the F1-score, accuracy and recall of 0.869, 0.915 and 0.843 respectively, which are larger compared to that of the model initialized without patch pre-trained weights (0.785, 0.878 and 0.783). The two-stage training strategy can improve the performance of pneumothorax classification and does not require too high GPU memory and long training time." @default.
- W3183499274 created "2021-08-02" @default.
- W3183499274 creator A5002734812 @default.
- W3183499274 creator A5071725756 @default.
- W3183499274 creator A5076516617 @default.
- W3183499274 date "2021-07-01" @default.
- W3183499274 modified "2023-09-28" @default.
- W3183499274 title "A patch-based and multi-instance learning strategy for pneumothorax classification on chest X-rays" @default.
- W3183499274 cites W1966716734 @default.
- W3183499274 cites W2099820832 @default.
- W3183499274 cites W2113609977 @default.
- W3183499274 cites W2117539524 @default.
- W3183499274 cites W2296073425 @default.
- W3183499274 cites W2525205678 @default.
- W3183499274 cites W2538673204 @default.
- W3183499274 cites W2559794190 @default.
- W3183499274 cites W2581082771 @default.
- W3183499274 cites W2964350391 @default.
- W3183499274 cites W4210816537 @default.
- W3183499274 cites W4243726317 @default.
- W3183499274 doi "https://doi.org/10.1088/1742-6596/1976/1/012030" @default.
- W3183499274 hasPublicationYear "2021" @default.
- W3183499274 type Work @default.
- W3183499274 sameAs 3183499274 @default.
- W3183499274 citedByCount "0" @default.
- W3183499274 crossrefType "journal-article" @default.
- W3183499274 hasAuthorship W3183499274A5002734812 @default.
- W3183499274 hasAuthorship W3183499274A5071725756 @default.
- W3183499274 hasAuthorship W3183499274A5076516617 @default.
- W3183499274 hasBestOaLocation W31834992741 @default.
- W3183499274 hasConcept C118552586 @default.
- W3183499274 hasConcept C119857082 @default.
- W3183499274 hasConcept C126838900 @default.
- W3183499274 hasConcept C153180895 @default.
- W3183499274 hasConcept C154945302 @default.
- W3183499274 hasConcept C2778329176 @default.
- W3183499274 hasConcept C2780724011 @default.
- W3183499274 hasConcept C41008148 @default.
- W3183499274 hasConcept C71924100 @default.
- W3183499274 hasConcept C95623464 @default.
- W3183499274 hasConceptScore W3183499274C118552586 @default.
- W3183499274 hasConceptScore W3183499274C119857082 @default.
- W3183499274 hasConceptScore W3183499274C126838900 @default.
- W3183499274 hasConceptScore W3183499274C153180895 @default.
- W3183499274 hasConceptScore W3183499274C154945302 @default.
- W3183499274 hasConceptScore W3183499274C2778329176 @default.
- W3183499274 hasConceptScore W3183499274C2780724011 @default.
- W3183499274 hasConceptScore W3183499274C41008148 @default.
- W3183499274 hasConceptScore W3183499274C71924100 @default.
- W3183499274 hasConceptScore W3183499274C95623464 @default.
- W3183499274 hasIssue "1" @default.
- W3183499274 hasLocation W31834992741 @default.
- W3183499274 hasOpenAccess W3183499274 @default.
- W3183499274 hasPrimaryLocation W31834992741 @default.
- W3183499274 hasRelatedWork W2001652754 @default.
- W3183499274 hasRelatedWork W2549006548 @default.
- W3183499274 hasRelatedWork W2623427976 @default.
- W3183499274 hasRelatedWork W2807311372 @default.
- W3183499274 hasRelatedWork W2921036759 @default.
- W3183499274 hasRelatedWork W2961085424 @default.
- W3183499274 hasRelatedWork W2972035100 @default.
- W3183499274 hasRelatedWork W3043252291 @default.
- W3183499274 hasRelatedWork W4214932115 @default.
- W3183499274 hasRelatedWork W3158004940 @default.
- W3183499274 hasVolume "1976" @default.
- W3183499274 isParatext "false" @default.
- W3183499274 isRetracted "false" @default.
- W3183499274 magId "3183499274" @default.
- W3183499274 workType "article" @default.