AI Article Synopsis
Article Abstract
We describe CounterSynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks where fidelity is limited by data imbalance, distributional instability, confounding, or underspecification, and exhibits inequitable performance across distinct subpopulations. Focusing on demographic attributes, we evaluate the quality of synthesised counterfactuals with voxel-based morphometry, classification and regression of the conditioning attributes, and the Fréchet inception distance. Examining downstream discriminative performance in the context of engineered demographic imbalance and confounding, we use UK Biobank and OASIS magnetic resonance imaging data to benchmark CounterSynth augmentation against current solutions to these problems. We achieve state-of-the-art improvements, both in overall fidelity and equity. The source code for CounterSynth is available at https://github.com/guilherme-pombo/CounterSynth.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10591114 | PMC |
| http://dx.doi.org/10.1016/j.media.2022.102723 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision.
Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit
June 2024
Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical imaging. To overcome this limitation, we introduce Adam-v2, a new self-supervised learning framework extending Adam [79] by explicitly incorporating part-whole hierarchies into its learning objectives through three key branches: (1) Localizability, acquiring discriminative representations to distinguish different anatomical patterns; (2) Composability, learning each anatomical structure in a parts-to-whole manner; and (3) Decomposability, comprehending each anatomical structure in a whole-to-parts manner. Experimental results across 10 tasks, compared to 11 baselines in zero-shot, few-shot transfer, and full fine-tuning settings, showcase Adam-v2's superior performance over large-scale medical models and existing SSL methods across diverse downstream tasks.
View Article and Find Full Text PDFSemantic Mask Reconstruction and Category Semantic Learning for few-shot image generation.
Neural Netw
December 2024
Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, 200237, China; Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China. Electronic address:
Few-shot image generation aims at generating novel images for the unseen category when given K images from the same category. Despite significant advancements in existing few-shot image generation methods, great challenges remain regarding the quality and diversity of the generated images. This issue stems from the model's struggle to fully comprehend the semantic content of images and extract sufficiently semantic representations.
View Article and Find Full Text PDFMetabolomic profiles differentiate between porto-sinusoidal vascular disorder, cirrhosis, and healthy individuals.
JHEP Rep
December 2024
Division of Gastroenterology and Hepatology, Department of Medicine III, Medical University of Vienna, Vienna, Austria.
Article Synopsis
- The study focused on identifying unique metabolomic signatures in patients with porto-sinusoidal vascular disorder (PSVD) and cirrhosis to improve diagnosis.
- Serum samples from healthy volunteers and patients with PSVD or cirrhosis were analyzed using advanced techniques like liquid chromatography-mass spectrometry, identifying significant metabolic changes linked to PSVD.
- Machine learning models were developed to distinguish PSVD from cirrhosis and healthy controls; key metabolites like taurocholic acid showed strong potential for non-invasive diagnostic use.
Comparison of stable carotid plaques in patients with mild-to-moderate carotid stenosis with vulnerable plaques in patients with significant carotid stenosis.
Medicine (Baltimore)
November 2024
Department of Radiology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen, China.
Article Synopsis
- The study compared stable and vulnerable carotid plaques to assess differences in their characteristics and the effectiveness of wall shear stress (WSS) as a diagnostic tool using magnetic resonance imaging.
- A total of 64 atherosclerotic plaques were analyzed, where WSS parameters were evaluated using computational simulations based on 3D imaging and Doppler ultrasound data.
- Results showed that vulnerable plaques had significantly lower WSSdown values compared to stable plaques, indicating that WSSdown is a crucial indicator for diagnosing plaque vulnerability, achieving high sensitivity and specificity rates.
SingletSeeker: an unsupervised clustering approach for automated singlet discrimination in cytometry.
Cytometry B Clin Cytom
November 2024
BD Biosciences, Becton, Dickinson and Company, Ashland, OR, WA, USA.
Flow cytometry is a high-throughput, high-dimensional technique that generates large sets of single-cell data. Prior to analyzing this data, it is common to exclude any events that contain two or more cells, multiplets, to ensure downstream analysis and quantification is of single-cell events, singlets, only. The process of singlet discrimination is critical yet fundamentally subjective and time-consuming; it is performed manually by the user, where the proper exclusion of multiplets depends on the user's expertise and often varies from experiment to experiment.
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!