Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377018979> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4377018979 abstract "The purpose of this study is to examine the utilization of unlabeled data for abdominal organ classification in multi-label (non-mutually exclusive classes) ultrasound images, as an alternative to the conventional transfer learning approach.We present a new method for classifying abdominal organs in ultrasound images. Unlike previous approaches that only relied on labeled data, we consider the use of both labeled and unlabeled data. To explore this approach, we first examine the application of deep clustering for pretraining a classification model. We then compare two training methods, fine-tuning with labeled data through supervised learning and fine-tuning with both labeled and unlabeled data using semisupervised learning. All experiments were conducted on a large dataset of unlabeled images (nu=84967) and a small set of labeled images (ns=2742) comprising progressively 10%, 20%, 50%, and 100% of the images.We show that for supervised fine-tuning, deep clustering is an effective pre-training method, with performance matching that of ImageNet pre-training using five times less labeled data. For semi-supervised learning, deep clustering pre-training also yields higher performance when the amount of labeled data is limited. Best performance is obtained with deep clustering pre-training combined with semi-supervised learning and 2742 labeled example images with an F1-score weighted average of 84.1%.This method can be used as a tool to preprocess large unprocessed databases, thus reducing the need for prior annotations of abdominal ultrasound studies for the training of image classification algorithms, which in turn could improve the clinical use of ultrasound images." @default.
- W4377018979 created "2023-05-19" @default.
- W4377018979 creator A5003634141 @default.
- W4377018979 creator A5046898859 @default.
- W4377018979 creator A5072025901 @default.
- W4377018979 creator A5084597676 @default.
- W4377018979 creator A5085598075 @default.
- W4377018979 date "2023-05-18" @default.
- W4377018979 modified "2023-09-30" @default.
- W4377018979 title "Deep clustering for abdominal organ classification in ultrasound imaging" @default.
- W4377018979 cites W2170638036 @default.
- W4377018979 cites W2559435482 @default.
- W4377018979 cites W3023371261 @default.
- W4377018979 cites W3094123278 @default.
- W4377018979 cites W3206611485 @default.
- W4377018979 cites W4214831717 @default.
- W4377018979 doi "https://doi.org/10.1117/1.jmi.10.3.034502" @default.
- W4377018979 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37216152" @default.
- W4377018979 hasPublicationYear "2023" @default.
- W4377018979 type Work @default.
- W4377018979 citedByCount "0" @default.
- W4377018979 crossrefType "journal-article" @default.
- W4377018979 hasAuthorship W4377018979A5003634141 @default.
- W4377018979 hasAuthorship W4377018979A5046898859 @default.
- W4377018979 hasAuthorship W4377018979A5072025901 @default.
- W4377018979 hasAuthorship W4377018979A5084597676 @default.
- W4377018979 hasAuthorship W4377018979A5085598075 @default.
- W4377018979 hasConcept C108583219 @default.
- W4377018979 hasConcept C115961682 @default.
- W4377018979 hasConcept C150899416 @default.
- W4377018979 hasConcept C153180895 @default.
- W4377018979 hasConcept C154945302 @default.
- W4377018979 hasConcept C2776145971 @default.
- W4377018979 hasConcept C41008148 @default.
- W4377018979 hasConcept C58489278 @default.
- W4377018979 hasConcept C71924100 @default.
- W4377018979 hasConcept C73555534 @default.
- W4377018979 hasConceptScore W4377018979C108583219 @default.
- W4377018979 hasConceptScore W4377018979C115961682 @default.
- W4377018979 hasConceptScore W4377018979C150899416 @default.
- W4377018979 hasConceptScore W4377018979C153180895 @default.
- W4377018979 hasConceptScore W4377018979C154945302 @default.
- W4377018979 hasConceptScore W4377018979C2776145971 @default.
- W4377018979 hasConceptScore W4377018979C41008148 @default.
- W4377018979 hasConceptScore W4377018979C58489278 @default.
- W4377018979 hasConceptScore W4377018979C71924100 @default.
- W4377018979 hasConceptScore W4377018979C73555534 @default.
- W4377018979 hasIssue "03" @default.
- W4377018979 hasLocation W43770189791 @default.
- W4377018979 hasLocation W43770189792 @default.
- W4377018979 hasOpenAccess W4377018979 @default.
- W4377018979 hasPrimaryLocation W43770189791 @default.
- W4377018979 hasRelatedWork W1590407081 @default.
- W4377018979 hasRelatedWork W2738221750 @default.
- W4377018979 hasRelatedWork W2889705046 @default.
- W4377018979 hasRelatedWork W2949280030 @default.
- W4377018979 hasRelatedWork W2953350812 @default.
- W4377018979 hasRelatedWork W2997709384 @default.
- W4377018979 hasRelatedWork W3192840557 @default.
- W4377018979 hasRelatedWork W4213299466 @default.
- W4377018979 hasRelatedWork W4245792239 @default.
- W4377018979 hasRelatedWork W4281637929 @default.
- W4377018979 hasVolume "10" @default.
- W4377018979 isParatext "false" @default.
- W4377018979 isRetracted "false" @default.
- W4377018979 workType "article" @default.