Deep Learning Method to Estimate Glucose Level from Heart Rate Variability

Shaqiri, Ervin; Gušev, Marjan

doi:10.1109/telfor51502.2020.9306609

Cited by 7 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each training set, the outliers for each class, defined by scores that are either greater than upper quartile (UQ) + 1.5*interquartile range (IQR) or less than lower quartile (LQ )-1.5*IQR, (12) were removed (13)(14)(15). The cutoffs for separating "none" and "mild to moderate" and for separating "mild to moderate" and "severe" were determined by "none"-versus-rest and "severe"-versus-rest binary classifications respectively.…”

Section: Calibration With Cutoff Determinationmentioning

confidence: 99%

Emphysema Quantification and Severity Classification with 3-Dimensional Averaging Kernel and Airways Removal

Zhang

Chaudhari

Bondarenko

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Emphysema is a common pulmonary pathology known to be associated with increased risk of lung cancer and lung biopsy complications. The prevailing quantitation method of calculating the voxel-wise percentage of low attenuation area (LAA) of lung tissue from CT scans is prone to noise and error due to overcounting of single voxel LAA and incomplete segmentation of airways. Purpose: We aim to develop an accurate algorithm to quantitatively measure emphysema and classify its severity. Methods and Materials: Two chest CT datasets were obtained from two tertiary hospitals as training and external validation datasets. Exclusion criteria included any patients whose emphysema extent was not specified by the accompanying report. The training dataset included 722 patients, and the validation dataset included 1006 patients. Following lung segmentation and airway removal, we applied convolution of the segmented lung by averaging kernels of different sizes in 2D and 3D. Cutoffs between "none," "mild to moderate," and "severe" emphysema were determined via weighted logistic regression on the training dataset, and the categorical emphysema extent was obtained for each patient. The main measure for evaluating model performance was the area under the curve (AUC) of the receiver operating characteristic (ROC) on the training dataset and the accuracy of classification on both the training and the validation dataset. The 1x1x1 kernel, which is equivalent to the traditional LAA score, was used for comparison to other kernels for performance evaluation. Results: The best model used a 3D 3x3x3 kernel for average filtering with airways post-processing and achieved a mean AUC of 0.782 and 0.985 for "none"-versus-rest and "severe"-versus-rest classifications respectively. It achieved a 0.676 and 0.757 multiclass classification accuracy on the training and validation dataset respectively. Conclusions and Relevance: We present an automated pipeline that can achieve accurate emphysema quantification and severity classification. We showed that convolving the segmented lung with a 3D 3x3x3 kernel and post-processing to remove airways can reliably quantify emphysema.

show abstract