AI Article Synopsis
- - The study aimed to create and assess an automated workflow called LATTE for evaluating atherosclerotic disease in 3D carotid MR images, specifically focusing on lesion assessment.
- - LATTE uses a convolutional neural network approach to accurately classify arteries as normal or with lesions, employing unsupervised domain adaptation to enhance performance across varying imaging conditions without needing extra annotations.
- - The results showed that LATTE significantly improved lesion classification accuracy (AUC >0.88 for advanced lesions) when using domain adaptation, indicating its potential effectiveness for consistent carotid atherosclerosis assessment across different clinical setups.
Article Abstract
Purpose: To develop and evaluate a domain adaptive and fully automated review workflow (lesion assessment through tracklet evaluation, LATTE) for assessment of atherosclerotic disease in 3D carotid MR vessel wall imaging (MR VWI).
Methods: VWI of 279 subjects with carotid atherosclerosis were used to develop LATTE, mainly convolutional neural network (CNN)-based domain adaptive lesion classification after image quality assessment and artery of interest localization. Heterogeneity in test sets from various sites usually causes inferior CNN performance. With our novel unsupervised domain adaptation (DA), LATTE was designed to accurately classify arteries into normal arteries and early and advanced lesions without additional annotations on new datasets. VWI of 271 subjects from four datasets (eight sites) with slightly different imaging parameters/signal patterns were collected to assess the effectiveness of DA of LATTE using the area under the receiver operating characteristic curve (AUC) on all lesions and advanced lesions before and after DA.
Results: LATTE had good performance with advanced/all lesion classification, with the AUC of >0.88/0.83, significant improvements from >0.82/0.80 if without DA.
Conclusions: LATTE can locate target arteries and distinguish carotid atherosclerotic lesions with consistently improved performance with DA on new datasets. It may be useful for carotid atherosclerosis detection and assessment on various clinical sites.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/mrm.28794 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Semantic prioritization in visual counterfactual explanations with weighted segmentation and auto-adaptive region selection.
Neural Netw
December 2024
Department of Artificial Intelligence, Korea University, 02841, Seoul, Republic of Korea. Electronic address:
In the domain of non-generative visual counterfactual explanations (CE), traditional techniques frequently involve the substitution of sections within a query image with corresponding sections from distractor images. Such methods have historically overlooked the semantic relevance of the replacement regions to the target object, thereby impairing the model's interpretability and hindering the editing workflow. Addressing these challenges, the present study introduces an innovative methodology named as Weighted Semantic Map with Auto-adaptive Candidate Editing Network (WSAE-Net).
View Article and Find Full Text PDFStyle mixup enhanced disentanglement learning for unsupervised domain adaptation in medical image segmentation.
Med Image Anal
December 2024
Department of Electrical Engineering, Yale University, New Haven, CT, USA; Department of Biomedical Engineering, Yale University, New Haven, CT, USA. Electronic address:
Unsupervised domain adaptation (UDA) has shown impressive performance by improving the generalizability of the model to tackle the domain shift problem for cross-modality medical segmentation. However, most of the existing UDA approaches depend on high-quality image translation with diversity constraints to explicitly augment the potential data diversity, which is hard to ensure semantic consistency and capture domain-invariant representation. In this paper, free of image translation and diversity constraints, we propose a novel Style Mixup Enhanced Disentanglement Learning (SMEDL) for UDA medical image segmentation to further improve domain generalization and enhance domain-invariant learning ability.
View Article and Find Full Text PDFExposure to saturated fatty acids (SFAs), such as palmitic acid, can lead to cellular metabolic dysfunction known as lipotoxicity. Although canonical adaptive metabolic processes like lipid storage or desaturation are known cellular responses to saturated fat exposure, the link between SFA metabolism and organellar biology remains an area of active inquiry. We performed a genome-wide CRISPR knockout screen in human epithelial cells to identify modulators of SFA toxicity.
View Article and Find Full Text PDFThe novel CD16A/anti-CD3 bifunctional protein, eCD16A/anti-CD3-BFP, redirects T cell cytotoxicity toward antibody-bound target cells.
Hum Vaccin Immunother
December 2025
Department of Research and Development, ManySmart Therapeutics, Taipei, Taiwan.
Monoclonal antibodies enhance innate immunity, while bispecific T cell engager antibodies redirect adaptive T cell immunity. To stimulate both innate and adaptive mechanisms, we created a bifunctional eCD16A/anti-CD3-BFP adapter protein for combined use with clinically approved monoclonal IgG1 antibodies. The adaptor protein contains the extracellular domain of the human CD16A high-affinity variant, which binds the Fc domain of IgG1 antibodies, and an anti-human CD3 single-chain variable fragment that redirects T cell cytotoxicity.
View Article and Find Full Text PDFA MACPF Protein OsCAD1 Balances Plant Growth and Immunity Through Regulating Salicylic Acid Homeostasis in Rice.
Plant Cell Environ
January 2025
State Key Laboratory of Rice Biology and Breeding, Key Laboratory for Zhejiang Super Rice Research, China National Center for Rice Improvement, China National Rice Research Institute, Hangzhou, Zhejiang, China.
Unraveling the mechanisms behind plant growth and immunity contributes to effective crop improvement. Membrane attack complex/perforin (MACPF) domain proteins play vital roles in innate and adaptive immunity in vertebrates; however, their molecular functions in plants remain largely unexplored. Here, we isolated and characterized a rice mutant, Oryza sativa constitutively activated cell death 1 (oscad1), which exhibited a lesion mimic phenotype and growth inhibition with increased cell death, elevated ROS accumulation, and enhanced resistance to bacterial blight Xanthomonas oryzae pv.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!