Bedside Ultrasound to Identify and Predict Severity of Dysphagia Following Ischemic Stroke: Human Versus Artificial Intelligence

OBJECTIVE

Dysphagia is a significant ischemic stroke complication that can lead to aspiration. Identification of at-risk patients can be logistically difficult and costly. Researchers investigated whether quantitative ultrasound assessment of hyoid bone movement during induced swallowing would predict failure of videofluoroscopy (VFS) or fiberoptic endoscopic evaluation of swallowing (FEES), as determined by a penetration-aspiration scale (PAS) score. Additionally, ability of a machine learning (ML) algorithm to predict PAS success or failure from real-time ultrasound video recordings was assessed.

METHODS

A prospective, single-blinded, observational pilot study was conducted from June 2019 through March 2020 at a comprehensive stroke center on a convenience sample of patients admitted with diagnosis of acute ischemic stroke undergoing VFS or FEES as part of dysphagia assessment. Researchers performed a midsagittal airway ultrasound during swallowing in patients receiving an objective swallowing assessment by speech language pathologists who were blinded to ultrasound results. Sonologists measured hyoid bone movement, and researchers then constructed an ML algorithm designed for real-time video analysis using a long short-term memory network with an embedded VGG16 convolutional neural network.

RESULTS

Videos from 69 patients were obtained with their respective PAS results. In total, 90% of available videos were used for algorithm training. After training, the ML algorithm was challenged with the 10% previously unseen videos and then compared with PAS outcomes. Statistical analysis included logistic regression and correlation matrix testing on human ultrasound measurements. Cohen's κ was calculated to compare deep learning algorithm prediction with PAS results. Measurement of hyoid bone elevation, forward displacement, total displacement and mandible length was unable to predict PAS assessment outcome (p values = 0.36, 0.13, 0.11 and 0.32, respectively). The ML algorithm showed substantial agreement with PAS testing results for predicting test outcome (κ = 0.79; 95% confidence interval: 0.52-1.0) CONCLUSION: Manual ultrasound measurement of hyoid movement during swallowing in stroke patients failed to predict PAS swallowing results. However, an ML algorithm showed substantial agreement with PAS results despite a small data set, which could greatly improve access to dysphagia assessment in the future.

Machine learning algorithm using publicly available echo database for simplified “visual estimation” of left ventricular ejection fraction

BACKGROUND

Left ventricular ejection fraction calculation automation typically requires complex algorithms and is dependent of optimal visualization and tracing of endocardial borders. This significantly limits usability in bedside clinical applications, where ultrasound automation is needed most.

AIM

To create a simple deep learning (DL) regression-type algorithm to visually estimate left ventricular (LV) ejection fraction (EF) from a public database of actual patient echo examinations and compare results to echocardiography laboratory EF calculations.

METHODS

A simple DL architecture previously proven to perform well on ultrasound image analysis, VGG16, was utilized as a base architecture running within a long short term memory algorithm for sequential image (video) analysis. After obtaining permission to use the Stanford EchoNet-Dynamic database, researchers randomly removed approximately 15% of the approximately 10036 echo apical 4-chamber videos for later performance testing. All database echo examinations were read as part of comprehensive echocardiography study performance and were coupled with EF, end systolic and diastolic volumes, key frames and coordinates for LV endocardial tracing in csv file. To better reflect point-of-care ultrasound (POCUS) clinical settings and time pressure, the algorithm was trained on echo video correlated with calculated ejection fraction without incorporating additional volume, measurement and coordinate data. Seventy percent of the original data was used for algorithm training and 15% for validation during training. The previously randomly separated 15% (1263 echo videos) was used for algorithm performance testing after training completion. Given the inherent variability of echo EF measurement and field standards for evaluating algorithm accuracy, mean absolute error (MAE) and root mean square error (RMSE) calculations were made on algorithm EF results compared to Echo Lab calculated EF. Bland-Atlman calculation was also performed. MAE for skilled echocardiographers has been established to range from 4% to 5%.

RESULTS

The DL algorithm visually estimated EF had a MAE of 8.08% (95%CI 7.60 to 8.55) suggesting good performance compared to highly skill humans. The RMSE was 11.98 and correlation of 0.348.

CONCLUSION

This experimental simplified DL algorithm showed promise and proved reasonably accurate at visually estimating LV EF from short real time echo video clips. Less burdensome than complex DL approaches used for EF calculation, such an approach may be more optimal for POCUS settings once improved upon by future research and development.

Development of a Deep Learning Network to Classify Inferior Vena Cava Collapse to Predict Fluid Responsiveness

OBJECTIVES

To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically ill patients.

METHODS

We used a data set of IVC ultrasound (US) videos to train the LSTM network. The data set was created from IVC US videos of spontaneously breathing critically ill patients undergoing intravenous fluid resuscitation as part of 2 prior prospective studies. We randomly selected 90% of the IVC videos to train the LSTM network and 10% of the videos to test the LSTM network's ability to predict fluid responsiveness. Fluid responsiveness was defined as a greater than 10% increase in the cardiac index after a 500-mL fluid bolus, as measured by bioreactance.

RESULTS

We analyzed 211 videos from 175 critically ill patients: 191 to train the LSTM network and 20 to test it. Using standard data augmentation techniques, we increased our sample size from 191 to 3820 videos. Of the 175 patients, 91 (52%) were fluid responders. The LSTM network was able to predict fluid responsiveness moderately well, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval [CI], 0.43-1.00), a positive likelihood ratio of infinity, and a negative likelihood ratio of 0.3 (95% CI, 0.12-0.77). In comparison, point-of-care US experts using video review offline and manual diameter measurement via software caliper tools achieved an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.83-0.99).

CONCLUSIONS

We demonstrated that an LSTM network can be trained by using videos of IVC US to classify IVC collapse to predict fluid responsiveness. Our LSTM network performed moderately well given the small training cohort but worse than point-of-care US experts. Further training and testing of the LSTM network with a larger data sets is warranted.

Are Convolutional Neural Networks Trained on ImageNet Images Wearing Rose-Colored Glasses?: A Quantitative Comparison of ImageNet, Computed Tomographic, Magnetic Resonance, Chest X-Ray, and Point-of-Care Ultrasound Images for Quality

OBJECTIVES

Deep learning for medical imaging analysis uses convolutional neural networks pretrained on ImageNet (Stanford Vision Lab, Stanford, CA). Little is known about how such color- and scene-rich standard training images compare quantitatively to medical images. We sought to quantitatively compare ImageNet images to point-of-care ultrasound (POCUS), computed tomographic (CT), magnetic resonance (MR), and chest x-ray (CXR) images.

METHODS

Using a quantitative image quality assessment technique (Blind/Referenceless Image Spatial Quality Evaluator), we compared images based on pixel complexity, relationships, variation, and distinguishing features. We compared 5500 ImageNet images to 2700 CXR, 2300 CT, 1800 MR, and 18,000 POCUS images. Image quality results ranged from 0 to 100 (worst). A 1-way analysis of variance was performed, and the standardized mean-difference effect size value (d) was calculated.

RESULTS

ImageNet images showed the best image quality rating of 21.7 (95% confidence interval [CI], 0.41) except for CXR at 13.2 (95% CI, 0.28), followed by CT at 35.1 (95% CI, 0.79), MR at 31.6 (95% CI, 0.75), and POCUS at 56.6 (95% CI, 0.21). The differences between ImageNet and all of the medical images were statistically significant (P ≤ .000001). The greatest difference in image quality was between ImageNet and POCUS (d = 2.38).

CONCLUSIONS

Point-of-care ultrasound (US) quality is significantly different from that of ImageNet and other medical images. This brings considerable implications for convolutional neural network training with medical images for various applications, which may be even more significant in the case of US images. Ultrasound deep learning developers should consider pretraining networks from scratch on US images, as training techniques used for CT, CXR, and MR images may not apply to US.

Are All Deep Learning Architectures Alike for Point-of-Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

OBJECTIVES

Little is known about optimal deep learning (DL) approaches for point-of-care ultrasound (POCUS) applications. We compared 6 popular DL architectures for POCUS cardiac image classification to determine whether an optimal DL architecture exists for future DL algorithm development in POCUS.

METHODS

We trained 6 convolutional neural networks (CNNs) with a range of complexities and ages (AlexNet, VGG-16, VGG-19, ResNet50, DenseNet201, and Inception-v4). Each CNN was trained by using images of 5 typical POCUS cardiac views. Images were extracted from 225 publicly available deidentified POCUS cardiac videos. A total of 750,018 individual images were extracted, with 90% used for model training and 10% for cross-validation. The training time and accuracy achieved were tracked. A real-world test of the algorithms was performed on a set of 125 completely new cardiac images. Descriptive statistics, Pearson R values, and κ values were calculated for each CNN.

RESULTS

Accuracy ranged from 96% to 85.6% correct for the 6 CNNs. VGG-16, one of the oldest and simplest CNNs, performed best at 96% correct with 232 minutes to train (R = 0.97; κ = 0.95; P < .00001). The worst-performing CNN was the newer DenseNet201, with 85.6% accuracy and 429 minutes to train (R = 0.92; κ = 0.82; P < .00001).

CONCLUSIONS

Six common image classification DL algorithms showed considerable variability in their accuracy and training time when trained and tested on identical data, suggesting that not all will perform optimally for POCUS DL applications. Contrary to well-established accuracies for CNNs, more modern and deeper algorithms yielded poorer results.

A rapid immunostaining method utilizing preformed antibody-avidin-biotin-peroxidase complexes

A rapid immunostaining method utilizing a preformed antibody-avidin-biotin-peroxidase complex that produces staining in paraffin sections and in frozen sections of tissues in 15 minutes is described. Although the complex did not produce staining with the common leukocyte monoclonal antibody, consistent staining was seen with most antibodies used. The complex gave consistent and reproducible staining for at least three months when maintained in storage at 4 degrees C. The results show that many available antibodies can be adapted to a rapid one-step staining procedure employing the avidin-biotin-peroxidase complex system.