Information Extraction from Multimodal ECG Documents

Wang, Fei; Syeda-Mahmood, Tanveer; Beymer, David

doi:10.1109/icdar.2009.189

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ECG signals can be auto-processed by detecting periodicity from ECG traces as images. The thick waveform peaks are considered the key features of this technique (Wang et al, 2009). Analysis of sub-cancer pixels from MRI and mammography images using a machine learning approach is quite popular.…”

Section: Multimodal Medical Data Extractionmentioning

confidence: 99%

Comprehensive Review of Multimodal Medical Data Analysis: Open Issues and Future Research Directions

Shetty¹,

Ananthanarayana²,

Mahale³

2022

AIP

View full text Add to dashboard Cite

Over the past few decades, the enormous expansion of medical data has led to searching for ways of data analysis in smart healthcare systems. Acquisition of data from pictures, archives, communication systems, electronic health records, online documents, radiology reports and clinical records of different styles with specific numerical information has given rise to the concept of multimodality and the need for machine learning and deep learning techniques in the analysis of the healthcare system. Medical data play a vital role in medical education and diagnosis; determining dependency between distinct modalities is essential. This paper gives a gist of current radiology medical data analysis techniques and their various approaches and frameworks for representation and classification. A brief outline of the existing medical multimodal data processing work is presented. The main objective of this study is to spot gaps in the surveyed area and list future tasks and challenges in radiology. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (or PRISMA) guidelines were incorporated in this study for effective article search and to investigate several relevant scientific publications. The systematic review was carried out on multimodal medical data analysis and highlighted advantages, limitations and strategies. The inherent benefit of multimodality in the medical domain powered with artificial intelligence has a significant impact on the performance of the disease diagnosis frameworks.

show abstract

Section: Multimodal Medical Data Extractionmentioning

confidence: 99%

Comprehensive Review of Multimodal Medical Data Analysis: Open Issues and Future Research Directions

Shetty¹,

Ananthanarayana²,

Mahale³

2022

AIP

View full text Add to dashboard Cite

show abstract

“…The heart cycle itself is estimated from two sources, (a) using optical character recognition of the numbers next to the symbol 'HR' in the image (lower right corner in Figure 1a), and (b) from the synchronizing EKG trace that is present in the echocardiogram image using an image-based ECG periodicity estimation algorithm described in [16]. Thus the LV detection is initiated in each consecutive frame in the heart cycle as shown in Figure 4 and the smallest LV region which is detected at the closure of the mitral valve is retained as the best estimate of the LV region.…”

Section: Integrating Sequence Informationmentioning

confidence: 99%

Automatic detection of left ventricular aneurysms in echocardiograms

Mahmood¹,

Syeda-Mahmood

2015

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Left ventricular cardiac aneurysms are bulgings in the myocardium muscle of the left ventricle. These irregular distortions of the left ventricular shape from its normal bullet-like appearance, are often due to result of myocardial infarction and can be fatal. In this paper we address, for the first time, the automatic detection of left ventricular (LV) cardiac aneurysms from 4-chamber views in echocardiograms. For this, we first detect the left ventricle in the echocardiogram image as the lumen region closest to the apex of the heart. The apex itself is estimated from the bounding lines of the viewing sector in an echocardiogram. The boundary of the LV is then analyzed to extract key curvature-based features for discrimination using a support vector machine with radial basis function kernels. Results of testing on a large echocardiogram video collection indicate that robust detection of left ventricle coupled with curvature features is sufficient to reliably separate LV aneurysms from normal left ventricular shapes.

show abstract

“…There has been a number of recent investigations regarding the prediction of physiological age using medical records, vital signs and laboratory data, or epigenetic changes [5][6][7]. The likelihood of having a "normal" ECG decreases with age.…”

Section: Introductionmentioning

confidence: 99%