Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313546672> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4313546672 abstract "Medical image analysis has experienced different stages of development, especially with the emergence of deep learning. However, it is difficult to acquire large-scale, highquality labeled data to train the model when using deep learning. This paper proposes a semi-supervised learning method to achieve medical image segmentation using limited labeled data and large-scale unlabeled data. Inspired by the classic Generative Adversarial Network (GAN), we proposed semi-supervised learning based on GAN (semi-GAN) to implement medical image segmentation. In the proposed semiGAN, adversarial training between the generator and discriminator has achieved higher segmentation accuracy. The dataset used was hippocampus data in Medical Segmentation Decathlon (MSD), and there are four training data settings: 25 labeled slices/3,374 unlabeled slices; 50 labeled slices/3,349 unlabeled slices; 100 labeled slices/3,299 unlabeled slices; 200 labeled slices/3,199 unlabeled slices. For each data setting, there are two experiments conducted: fully-supervised learning based on a generator network using only labeled data (F-Generator), and semi-GAN. The experiments showed that semi-GAN can improve segmentation accuracy by an average of 0.4% using unlabeled data compared to F-Generator using labeled data. Further study will be conducted to improve the semi-GAN architecture." @default.
- W4313546672 created "2023-01-06" @default.
- W4313546672 creator A5009701985 @default.
- W4313546672 creator A5012711018 @default.
- W4313546672 creator A5029909446 @default.
- W4313546672 date "2022-11-28" @default.
- W4313546672 modified "2023-10-07" @default.
- W4313546672 title "Leveraging Unlabeled Data Using Semi-Supervised Generative Adversarial Network for Medical Image Segmentation" @default.
- W4313546672 cites W1875387157 @default.
- W4313546672 cites W1884191083 @default.
- W4313546672 cites W2592929672 @default.
- W4313546672 cites W2736462652 @default.
- W4313546672 cites W2750925197 @default.
- W4313546672 cites W2751665805 @default.
- W4313546672 cites W2805702212 @default.
- W4313546672 cites W2891451067 @default.
- W4313546672 cites W2978017498 @default.
- W4313546672 cites W3005303098 @default.
- W4313546672 cites W3009175488 @default.
- W4313546672 cites W3013884416 @default.
- W4313546672 cites W3042127584 @default.
- W4313546672 cites W3123982987 @default.
- W4313546672 cites W3133070173 @default.
- W4313546672 cites W3164045928 @default.
- W4313546672 doi "https://doi.org/10.1109/iconda56696.2022.10000292" @default.
- W4313546672 hasPublicationYear "2022" @default.
- W4313546672 type Work @default.
- W4313546672 citedByCount "0" @default.
- W4313546672 crossrefType "proceedings-article" @default.
- W4313546672 hasAuthorship W4313546672A5009701985 @default.
- W4313546672 hasAuthorship W4313546672A5012711018 @default.
- W4313546672 hasAuthorship W4313546672A5029909446 @default.
- W4313546672 hasConcept C108583219 @default.
- W4313546672 hasConcept C115961682 @default.
- W4313546672 hasConcept C119857082 @default.
- W4313546672 hasConcept C121332964 @default.
- W4313546672 hasConcept C124504099 @default.
- W4313546672 hasConcept C136389625 @default.
- W4313546672 hasConcept C153180895 @default.
- W4313546672 hasConcept C154945302 @default.
- W4313546672 hasConcept C163258240 @default.
- W4313546672 hasConcept C2776145971 @default.
- W4313546672 hasConcept C2779803651 @default.
- W4313546672 hasConcept C2780992000 @default.
- W4313546672 hasConcept C2988773926 @default.
- W4313546672 hasConcept C41008148 @default.
- W4313546672 hasConcept C50644808 @default.
- W4313546672 hasConcept C58973888 @default.
- W4313546672 hasConcept C62520636 @default.
- W4313546672 hasConcept C76155785 @default.
- W4313546672 hasConcept C89600930 @default.
- W4313546672 hasConcept C94915269 @default.
- W4313546672 hasConceptScore W4313546672C108583219 @default.
- W4313546672 hasConceptScore W4313546672C115961682 @default.
- W4313546672 hasConceptScore W4313546672C119857082 @default.
- W4313546672 hasConceptScore W4313546672C121332964 @default.
- W4313546672 hasConceptScore W4313546672C124504099 @default.
- W4313546672 hasConceptScore W4313546672C136389625 @default.
- W4313546672 hasConceptScore W4313546672C153180895 @default.
- W4313546672 hasConceptScore W4313546672C154945302 @default.
- W4313546672 hasConceptScore W4313546672C163258240 @default.
- W4313546672 hasConceptScore W4313546672C2776145971 @default.
- W4313546672 hasConceptScore W4313546672C2779803651 @default.
- W4313546672 hasConceptScore W4313546672C2780992000 @default.
- W4313546672 hasConceptScore W4313546672C2988773926 @default.
- W4313546672 hasConceptScore W4313546672C41008148 @default.
- W4313546672 hasConceptScore W4313546672C50644808 @default.
- W4313546672 hasConceptScore W4313546672C58973888 @default.
- W4313546672 hasConceptScore W4313546672C62520636 @default.
- W4313546672 hasConceptScore W4313546672C76155785 @default.
- W4313546672 hasConceptScore W4313546672C89600930 @default.
- W4313546672 hasConceptScore W4313546672C94915269 @default.
- W4313546672 hasLocation W43135466721 @default.
- W4313546672 hasOpenAccess W4313546672 @default.
- W4313546672 hasPrimaryLocation W43135466721 @default.
- W4313546672 hasRelatedWork W1542934499 @default.
- W4313546672 hasRelatedWork W2752124967 @default.
- W4313546672 hasRelatedWork W2801525523 @default.
- W4313546672 hasRelatedWork W2908875379 @default.
- W4313546672 hasRelatedWork W3099805903 @default.
- W4313546672 hasRelatedWork W3120994036 @default.
- W4313546672 hasRelatedWork W3204638265 @default.
- W4313546672 hasRelatedWork W3212586182 @default.
- W4313546672 hasRelatedWork W4210379404 @default.
- W4313546672 hasRelatedWork W4308970678 @default.
- W4313546672 isParatext "false" @default.
- W4313546672 isRetracted "false" @default.
- W4313546672 workType "article" @default.