Recent advancements in generative artificial intelligence have shown promise in producing realistic images from complex data distributions. We developed a denoising diffusion probabilistic model trained on the CheXchoNet dataset, encoding the joint distribution of demographic data and echocardiogram measurements. We generated a synthetic dataset skewed towards younger patients with a higher prevalence of structural left ventricle disease. A diagnostic deep learning model trained on the synthetic dataset performed comparably to one trained on real data producing an AUROC=0.75(95%CI 0.72-0.77), with similar performance on an internal dataset. Combining real data with positive samples from the synthetic data improved diagnostic accuracy producing an AUROC=0.80(95%CI 0.78-0.82). Subgroup analysis showed the largest performance improvement across younger patients. These results suggest diffusion models can increase diagnostic accuracy and fine-tune models for specific populations.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11601717 | PMC |
| http://dx.doi.org/10.1101/2024.11.21.24317662 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
YOLOSeg with applications to wafer die particle defect segmentation.
Sci Rep
January 2025
Department of Industrial Engineering and Management, Ming Chi University of Technology, New Taipei City, 243, Taiwan.
This study develops the you only look once segmentation (YOLOSeg), an end-to-end instance segmentation model, with applications to segment small particle defects embedded on a wafer die. YOLOSeg uses YOLOv5s as the basis and extends a UNet-like structure to form the segmentation head. YOLOSeg can predict not only bounding boxes of particle defects but also the corresponding bounding polygons.
View Article and Find Full Text PDFMotion-Compensated Multishot Pancreatic Diffusion-Weighted Imaging With Deep Learning-Based Denoising.
Invest Radiol
January 2025
From the Department of Radiology, Stanford University, Stanford, CA (K.W., M.J.M., A.M.L., A.B.S., A.J.H., D.B.E., R.L.B.); Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA (K.W.); GE HealthCare, Houston, TX (X.W.); GE HealthCare, Boston, MA (A.G.); and GE HealthCare, Menlo Park, CA (P.L.).
Objectives: Pancreatic diffusion-weighted imaging (DWI) has numerous clinical applications, but conventional single-shot methods suffer from off resonance-induced artifacts like distortion and blurring while cardiovascular motion-induced phase inconsistency leads to quantitative errors and signal loss, limiting its utility. Multishot DWI (msDWI) offers reduced image distortion and blurring relative to single-shot methods but increases sensitivity to motion artifacts. Motion-compensated diffusion-encoding gradients (MCGs) reduce motion artifacts and could improve motion robustness of msDWI but come with the cost of extended echo time, further reducing signal.
View Article and Find Full Text PDFNeurophysiological data augmentation for EEG-fNIRS multimodal features based on a denoising diffusion probabilistic model.
Comput Methods Programs Biomed
January 2025
College of Medical Instruments, Shanghai University of Medicine and Health Sciences, Shanghai, 201318, PR China; Shanghai Yangpu Mental Health Center, Shanghai, 200093, PR China. Electronic address:
Background And Objective: The hybrid brain computer interfaces (BCI) combining electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) have attracted extensive attention for overcoming the decoding limitations of the single-modality BCI. With the deepening application of deep learning approaches in BCI systems, its significant performance improvement has become apparent. However, the scarcity of brain signal data limits the performance of deep learning models.
View Article and Find Full Text PDFEvaluating the effect of noise reduction strategies in CT perfusion imaging for predicting infarct core with deep learning.
Neuroradiol J
January 2025
Canon Stroke and Vascular Research Center, University at Buffalo, Buffalo, NY, USA.
This study evaluates the efficacy of deep learning models in identifying infarct tissue on computed tomography perfusion (CTP) scans from patients with acute ischemic stroke due to large vessel occlusion, specifically addressing the potential influence of varying noise reduction techniques implemented by different vendors. We analyzed CTP scans from 60 patients who underwent mechanical thrombectomy achieving a modified thrombolysis in cerebral infarction (mTICI) score of 2c or 3, ensuring minimal changes in the infarct core between the initial CTP and follow-up MR imaging. Noise reduction techniques, including principal component analysis (PCA), wavelet, non-local means (NLM), and a no denoising approach, were employed to create hemodynamic parameter maps.
View Article and Find Full Text PDFJoint k-b space diffusion-weighted image reconstruction and apparent diffusion coefficient fitting for diffusion-weighted turbo-spin-echo imaging.
Med Phys
January 2025
Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
Background: Diffusion-weighted (DW) turbo-spin-echo (TSE) imaging offers improved geometric fidelity compared to single-shot echo-planar-imaging (EPI). However, it suffers from low signal-to-noise ratio (SNR) and prolonged acquisition times, thereby restricting its applications in diagnosis and MRI-guided radiotherapy (MRgRT).
Purpose: To develop a joint k-b space reconstruction algorithm for concurrent reconstruction of DW-TSE images and the apparent diffusion coefficient (ADC) map with enhanced image quality and more accurate quantitative measurements.
Want 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!