Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387207007> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4387207007 endingPage "e497" @default.
- W4387207007 startingPage "e497" @default.
- W4387207007 abstract "Deep learning has achieved great success in medical image segmentation. Most existing deep learning (DL) approaches make no adjustments to the model prior to inference. These models can perform well on the data of the same distribution, but their performance usually degrades when applied to the images from different source, i.e., different scanners. To tackle the problem caused by domain shift, we proposed an unsupervised domain adaptation (UDA) method based on entropy minimization and physical consistency constraints.The proposed method combines feature-level and instance-level domain adaptation techniques to transfer knowledge from the source to the target domain. Specifically, the feature-level adaptation technique uses a graph-based entropy minimization to reduce the discrepancy between the source and target domains. The instance-level adaptation technique employs a novel consistency loss to regularize the physical consistency of the same object, such as volume, length, and centroid, thus improving the segmentation accuracy of the target domain. A collection of 93 abdominal MR images, comprising 45 cases from a 0.35T MRI scanner (TRUFI) and 48 cases from a 1.5T MRI scanner (T2), was utilized to evaluate the effectiveness of the proposed method. The contours of 6 organs-at-risk were delineated by a senior radiation oncologist, serving as the ground truth. Three models, the source model (SRC) trained on the source domain, the target model (TGT) trained on the target domain, and the UDA model adapted from the source domain to the target domain, were compared on the target domain using the Dice Similarity Coefficient (DSC).In the experiment of 0.35T-to-1.5T, the proposed UDA method outperformed the source model, achieving an average DSC score of 0.82 ± 0.11, compared to 0.58 ± 0.23 (SRC) and 0.85 ± 0.09 (TGT), respectively. In the inverse experiment 1.5T-to-0.35T, the UDA model achieved an average DSC score of 0.79±0.13, compared to DSCs of 0.52 ± 0.25 and 0.81 ± 0.11 for the SRC and TGT respectively. The UDA method yielded a significant improvement of 46%, compared to the SRC. Particularly, OARs (organ at risk) with higher deformability such as the stomach and duodenum achieved a 58% and 63% improvement in performance, respectively.This work presents a compelling approach of UDA for auto-segmentation on multi-source MRIs. Experimental results demonstrate that the UDA effectively improve the segmentation performance of the source model in the target domain, resulting in a more robust segmentation model." @default.
- W4387207007 created "2023-09-30" @default.
- W4387207007 creator A5060178337 @default.
- W4387207007 creator A5070632299 @default.
- W4387207007 creator A5083732285 @default.
- W4387207007 creator A5087193137 @default.
- W4387207007 creator A5088359251 @default.
- W4387207007 date "2023-10-01" @default.
- W4387207007 modified "2023-10-17" @default.
- W4387207007 title "Unsupervised Domain Adaptation of Auto-Segmentation on Multi-Source MRIs" @default.
- W4387207007 doi "https://doi.org/10.1016/j.ijrobp.2023.06.1736" @default.
- W4387207007 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37785564" @default.
- W4387207007 hasPublicationYear "2023" @default.
- W4387207007 type Work @default.
- W4387207007 citedByCount "0" @default.
- W4387207007 crossrefType "journal-article" @default.
- W4387207007 hasAuthorship W4387207007A5060178337 @default.
- W4387207007 hasAuthorship W4387207007A5070632299 @default.
- W4387207007 hasAuthorship W4387207007A5083732285 @default.
- W4387207007 hasAuthorship W4387207007A5087193137 @default.
- W4387207007 hasAuthorship W4387207007A5088359251 @default.
- W4387207007 hasConcept C106301342 @default.
- W4387207007 hasConcept C121332964 @default.
- W4387207007 hasConcept C138885662 @default.
- W4387207007 hasConcept C146599234 @default.
- W4387207007 hasConcept C146849305 @default.
- W4387207007 hasConcept C153180895 @default.
- W4387207007 hasConcept C154945302 @default.
- W4387207007 hasConcept C2776401178 @default.
- W4387207007 hasConcept C31972630 @default.
- W4387207007 hasConcept C41008148 @default.
- W4387207007 hasConcept C41895202 @default.
- W4387207007 hasConcept C62520636 @default.
- W4387207007 hasConcept C89600930 @default.
- W4387207007 hasConceptScore W4387207007C106301342 @default.
- W4387207007 hasConceptScore W4387207007C121332964 @default.
- W4387207007 hasConceptScore W4387207007C138885662 @default.
- W4387207007 hasConceptScore W4387207007C146599234 @default.
- W4387207007 hasConceptScore W4387207007C146849305 @default.
- W4387207007 hasConceptScore W4387207007C153180895 @default.
- W4387207007 hasConceptScore W4387207007C154945302 @default.
- W4387207007 hasConceptScore W4387207007C2776401178 @default.
- W4387207007 hasConceptScore W4387207007C31972630 @default.
- W4387207007 hasConceptScore W4387207007C41008148 @default.
- W4387207007 hasConceptScore W4387207007C41895202 @default.
- W4387207007 hasConceptScore W4387207007C62520636 @default.
- W4387207007 hasConceptScore W4387207007C89600930 @default.
- W4387207007 hasIssue "2" @default.
- W4387207007 hasLocation W43872070071 @default.
- W4387207007 hasLocation W43872070072 @default.
- W4387207007 hasOpenAccess W4387207007 @default.
- W4387207007 hasPrimaryLocation W43872070071 @default.
- W4387207007 hasRelatedWork W1669643531 @default.
- W4387207007 hasRelatedWork W1976416492 @default.
- W4387207007 hasRelatedWork W1982826852 @default.
- W4387207007 hasRelatedWork W2005437358 @default.
- W4387207007 hasRelatedWork W2008656436 @default.
- W4387207007 hasRelatedWork W2023558673 @default.
- W4387207007 hasRelatedWork W2110230079 @default.
- W4387207007 hasRelatedWork W2134924024 @default.
- W4387207007 hasRelatedWork W2370723160 @default.
- W4387207007 hasRelatedWork W2517104666 @default.
- W4387207007 hasVolume "117" @default.
- W4387207007 isParatext "false" @default.
- W4387207007 isRetracted "false" @default.
- W4387207007 workType "article" @default.