Background: A globally harmonized protocol (HarP) for manual hippocampal segmentation based on magnetic resonance has been recently developed by a task force from European Alzheimer's Disease Consortium (EADC) and Alzheimer's Disease Neuroimaging Initiative (ADNI). Our aim was to produce benchmark labels based on the HarP for manual segmentation.
Methods: Five experts of manual hippocampal segmentation underwent specific training on the HarP and segmented 40 right and left hippocampi from 10 ADNI subjects on both 1.5 T and 3 T scans. An independent expert visually checked segmentations for compliance with the HarP. Descriptive measures of agreement between tracers were intraclass correlation coefficients (ICCs) of crude volumes and similarity coefficients of three-dimensional volumes.
Results: Two hundred labels have been provided for the 20 magnetic resonance images. Intra- and interrater ICCs were >0.94, and mean similarity coefficients were 1.5 T, 0.73 (95% confidence interval [CI], 0.71-0.75); 3 T, 0.75 (95% CI, 0.74-0.76).
Conclusion: Certified benchmark labels have been produced based on the HarP to be used for tracers' training and qualification.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jalz.2013.12.019 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Scale-Consistent and Temporally Ensembled Unsupervised Domain Adaptation for Object Detection.
Sensors (Basel)
January 2025
School of Mechanical and Electrical Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China.
Unsupervised Domain Adaptation for Object Detection (UDA-OD) aims to adapt a model trained on a labeled source domain to an unlabeled target domain, addressing challenges posed by domain shifts. However, existing methods often face significant challenges, particularly in detecting small objects and over-relying on classification confidence for pseudo-label selection, which often leads to inaccurate bounding box localization. To address these issues, we propose a novel UDA-OD framework that leverages scale consistency (SC) and Temporal Ensemble Pseudo-Label Selection (TEPLS) to enhance cross-domain robustness and detection performance.
View Article and Find Full Text PDFCINet: A Constraint- and Interaction-Based Network for Remote Sensing Change Detection.
Sensors (Basel)
December 2024
School of Physics and Electronics, Nanning Normal University, Nanning 530100, China.
Remote sensing change detection (RSCD), which utilizes dual-temporal images to predict change locations, plays an essential role in long-term Earth observation missions. Although many deep learning based RSCD models perform well, challenges remain in effectively extracting change information between dual-temporal images and fully leveraging interactions between their feature maps. To address these challenges, a constraint- and interaction-based network (CINet) for RSCD is proposed.
View Article and Find Full Text PDFDeep learning generalization for diabetic retinopathy staging from fundus images.
Physiol Meas
January 2025
Biomedical Engineering Faculty, Technion Israel Institute of Technology, Technion city, Haifa, Haifa, 32000, ISRAEL.
Diabetic retinopathy (DR) is a serious diabetes complication that can lead to vision loss, making timely identification crucial. Existing data-driven algorithms for DR staging from digital fundus images (DFIs) often struggle with generalization due to distribution shifts between training and target domains. To address this, DRStageNet, a deep learning model, was developed using six public and independent datasets with 91,984 DFIs from diverse demographics.
View Article and Find Full Text PDFLearning with noisy labels via clean aware sharpness aware minimization.
Sci Rep
January 2025
School of Mechanical, Electrical, and Information Engineering, Putian University, Putian, 351100, China.
Noise label learning has attracted considerable attention owing to its ability to leverage large amounts of inexpensive and imprecise data. Sharpness aware minimization (SAM) has shown effective improvements in the generalization performance in the presence of noisy labels by introducing adversarial weight perturbations in the model parameter space. However, our experimental observations have shown that the SAM generalization bottleneck primarily stems from the difficulty of finding the correct adversarial perturbation amidst the noisy data.
View Article and Find Full Text PDFMIFS: An adaptive multipath information fused self-supervised framework for drug discovery.
Neural Netw
January 2025
Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China; College of Computer and Information Science, Chongqing Normal University, Chongqing, 401331, China. Electronic address:
The production of expressive molecular representations with scarce labeled data is challenging for AI-driven drug discovery. Mainstream studies often follow a pipeline that pre-trains a specific molecular encoder and then fine-tunes it. However, the significant challenges of these methods are (1) neglecting the propagation of diverse information within molecules and (2) the absence of knowledge and chemical constraints in the pre-training strategy.
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!