Publications by authors named "Athira Jacob"

: To validate the automated quantification of cardiac chamber volumes and myocardial mass on non-contrast chest CT using cardiac MR (CMR) as a reference. : We retrospectively included 53 consecutive patients who received non-contrast chest CT and CMR within three weeks. A deep learning model created cardiac segmentations on axial soft-tissue reconstructions from CT, covering all four cardiac chambers and the left ventricular myocardium.

View Article and Find Full Text PDF
Article Synopsis
  • Coronary CT angiography (CCTA) is crucial before transcatheter aortic valve replacement (TAVR), and this study aimed to assess how well AI software can predict major adverse cardiovascular events (MACE) in TAVR patients by analyzing cardiac parameters.
  • The study included 648 patients, revealing that 17.9% experienced MACE within an average follow-up of 24 months, with left ventricle long axis shortening (LV-LAS) identified as a key predictor of MACE after considering other clinical factors.
  • The results showed that the AI-derived LV-LAS significantly improved prediction models for MACE, demonstrating that automated cardiac assessments can effectively aid in risk stratification prior to TAVR procedures
View Article and Find Full Text PDF
Article Synopsis
  • The study aims to create a deep learning algorithm using MRI to quickly and accurately classify individuals into groups: normal subjects, and patients with dilated cardiomyopathy, hypertrophic cardiomyopathy, and ischemic heart disease.
  • A total of 1,337 subjects were analyzed, employing advanced imaging techniques and extracting key cardiac features to train the algorithm, testing its effectiveness through various statistical methods and comparisons against expert evaluations.
  • The model achieved high accuracy rates, particularly distinguishing normal subjects with an area under the curve (AUC) of 0.952, while improving classification metrics slightly with the addition of unlabeled normal data.
View Article and Find Full Text PDF
Article Synopsis
  • This study examined whether an AI-based method for measuring left ventricular ejection fraction (LVEF) during stress tests could better predict death in patients compared to traditional methods.
  • Researchers analyzed data from over 9,700 patients, finding a strong correlation between AI-measured stress LVEF and expert-measured LVEF, as well as a significant association with all-cause mortality.
  • The study concluded that the AI method provides valuable prognostic information that improves risk assessment beyond conventional factors and traditional stress CMR findings.
View Article and Find Full Text PDF

Background: Accurate chamber volumetry from gated, non-contrast cardiac CT (NCCT) scans can be useful for potential screening of heart failure.

Objectives: To validate a new, fully automated, AI-based method for cardiac volume and myocardial mass quantification from NCCT scans compared to contrasted CT Angiography (CCTA).

Methods: Of a retrospectively collected cohort of 1051 consecutive patients, 420 patients had both NCCT and CCTA scans at mid-diastolic phase, excluding patients with cardiac devices.

View Article and Find Full Text PDF
Article Synopsis
  • Deep learning (DL) segmentation is emerging as a popular method for analyzing cardiac MRI images, specifically for accurately determining left ventricular (LV) volume and borders.
  • The study compares two whole-heart MRI reconstruction techniques—respiratory motion-corrected (Mcorr) and multi-volume respiratory motion-resolved (Mres)—to assess which produces more accurate LV volume measurements using DL-based segmentation.
  • Results indicate that LV volumes derived from Mres images are likely to be more precise when compared to manual expert tracing than those from Mcorr images, with a focus on evaluating the absolute volume difference and similarity coefficients between manual and automated segmentations.
View Article and Find Full Text PDF
Article Synopsis
  • The study aimed to evaluate if fully automated AI-based global circumferential strain (GCS) measured during stress cardiovascular MRI can provide additional predictive value for major adverse cardiovascular events (MACE).
  • The research involved over 2,100 patients and found that while stress-GCS correlated with MACE in patients with normal stress CMR, it did not predict such events in those with abnormal CMR.
  • The findings suggest that stress-GCS offers better prognostic assessment in individuals with normal CMR compared to traditional methods, despite a low overall event rate among these patients.
View Article and Find Full Text PDF

Background: The left atrioventricular coupling index (LACI) is a strong and independent predictor of heart failure (HF) in individuals without clinical cardiovascular disease. Its prognostic value is not established in patients with cardiovascular disease.

Objectives: This study sought to determine in patients undergoing stress cardiac magnetic resonance (CMR) whether fully automated artificial intelligence-based LACI can provide incremental prognostic value to predict HF.

View Article and Find Full Text PDF

Objectives: To evaluate the effectiveness of a novel artificial intelligence (AI) algorithm for fully automated measurement of left atrial (LA) volumes and function using cardiac CT in patients with atrial fibrillation.

Methods: We included 79 patients (mean age 63 ± 12 years; 35 with atrial fibrillation (AF) and 44 controls) between 2017 and 2020 in this retrospective study. Images were analyzed by a trained AI algorithm and an expert radiologist.

View Article and Find Full Text PDF

Background: Low-dose computed tomography (LDCT) are performed routinely for lung cancer screening. However, a large amount of nonpulmonary data from these scans remains unassessed. We aimed to validate a deep learning model to automatically segment and measure left atrial (LA) volumes from routine NCCT and evaluate prediction of cardiovascular outcomes.

View Article and Find Full Text PDF

While it is well known that the vestibular system is responsible for maintaining balance, posture and coordination, there is increasing evidence that it also plays an important role in cognition. Moreover, a growing number of epidemiological studies are demonstrating a link between vestibular dysfunction and cognitive deficits in older adults; however, the exact pathways through which vestibular loss may affect cognition are unknown. In this cross-sectional study, we sought to identify relationships between vestibular function and variation in morphometry in brain structures from structural neuroimaging.

View Article and Find Full Text PDF

Most long-term memories are forgotten, becoming progressively less likely to be recalled. Still, some memory fragments may persist, as savings memory (easier relearning) can be detected long after recall has become impossible. What happens to a memory trace during forgetting that makes it inaccessible for recall and yet still effective to spark easier re-learning? We are addressing this question by tracking the transcriptional changes that accompany learning and then forgetting of a long-term sensitization memory in the tail-elicited siphon withdrawal reflex of Aplysia californica.

View Article and Find Full Text PDF

Objective: This study evaluated whether reduced vestibular function in aging adults is associated with lower hippocampal volume.

Study Design: Cross-sectional study.

Setting: Baltimore Longitudinal Study of Aging, a long-running longitudinal cohort study of healthy aging.

View Article and Find Full Text PDF

Background: Tagged Magnetic Resonance (tMR) imaging is a powerful technique for determining cardiovascular abnormalities. One of the reasons for tMR not being used in routine clinical practice is the lack of easy-to-use tools for image analysis and strain mapping. In this paper, we introduce a novel interdisciplinary method based on correlation image velocimetry (CIV) to estimate cardiac deformation and strain maps from tMR images.

View Article and Find Full Text PDF

A method for electroencephalography (EEG) - near-infrared spectroscopy (NIRS) based assessment of neurovascular coupling (NVC) during anodal transcranial direct current stimulation (tDCS). Anodal tDCS modulates cortical neural activity leading to a hemodynamic response, which was used to identify impaired NVC functionality. In this study, the hemodynamic response was estimated with NIRS.

View Article and Find Full Text PDF