Diagnostic accuracy of a novel software technology for detecting pneumothorax in a porcine model

Summers, Shane M.; Chin, Eric J.; April, Michael D.; Grisell, Ronald D.; Lospinoso, Joshua; Kheirabadi, Bijan S.; Salinas, José; Blackbourne, Lorne H.

doi:10.1016/j.ajem.2017.03.073

Cited by 6 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Summers et al [10] presented a dataset of porcine LUSs with 343 M-mode videos and 364 B-mode images. The dataset contains control samples and samples with varying volumes of air injected into pleural space, causing pneumothorax.…”

Section: Pneumothorax and Detection Of Lung Sliding Motionmentioning

confidence: 99%

Detecting the Absence of Lung Sliding in Lung Ultrasounds Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Certain post-thoracic surgery complications are monitored in a standard manner using methods that employ ionising radiation. A need to automatise the diagnostic procedure has now arisen following the clinical trial of a novel lung ultrasound examination procedure that can replace X-rays. Deep learning was used as a powerful tool for lung ultrasound analysis. We present a novel deep-learning method, automated M-mode classification, to detect the absence of lung sliding motion in lung ultrasound. Automated M-mode classification leverages semantic segmentation to select 2D slices across the temporal dimension of the video recording. These 2D slices are the input for a convolutional neural network, and the output of the neural network indicates the presence or absence of lung sliding in the given time slot. We aggregate the partial predictions over the entire video recording to determine whether the subject has developed post-surgery complications. With a 64-frame version of this architecture, we detected lung sliding on average with a balanced accuracy of 89%, sensitivity of 82%, and specificity of 92%. Automated M-mode classification is suitable for lung sliding detection from clinical lung ultrasound videos. Furthermore, in lung ultrasound videos, we recommend using time windows between 0.53 and 2.13 s for the classification of lung sliding motion followed by aggregation.

show abstract

Section: Pneumothorax and Detection Of Lung Sliding Motionmentioning

confidence: 99%

Detecting the Absence of Lung Sliding in Lung Ultrasounds Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Ground truth categorical binary labels for PTX pathology associated with 404 M-mode (209 bmp, 195 jpg) images and 420 B-mode mp4 video clips were provided to build automated medical diagnosis models. Baseline classification accuracy statistics as computed by the iFAST computerized assistant were 97.5% for M-mode images and 84.7% for B-mode video [8]. A Sonosite M-Turbo ultrasound machine captured all images and video loops.…”

Section: Datasetmentioning

confidence: 99%

“…A total of 420 B-mode videos and 404 M-mode still images from eight female Yorkshire porcine models (Sus scrofa) with and without PTX, used in a previous study [8], were acquired for our experiments. The images were then split into 80% train and 20% test sets.…”

Section: Data Retrievalmentioning

confidence: 99%

Automated Pneumothorax Diagnosis Using Deep Neural Networks

Lindsey

Lee

Grisell

et al. 2019

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Thoracic ultrasound can provide information leading to rapid diagnosis of pneumothorax with improved accuracy over the standard physical examination and with higher sensitivity than anteroposterior chest radiography. However, the clinical interpretation of a patient medical image is highly operator dependent. Furthermore, remote environments, such as the battlefield or deep-space exploration, may lack expertise for diagnosing certain pathologies. We have developed an automated image interpretation pipeline for the analysis of thoracic ultrasound data and the classification of pneumothorax events to provide decision support in such situations. Our pipeline consists of image preprocessing, data augmentation, and deep learning architectures for medical diagnosis. In this work, we demonstrate that robust, accurate interpretation of chest images and video can be achieved using deep neural networks. A number of novel image processing techniques were employed to achieve this result. Affine transformations were applied for data augmentation. Hyperparameters were optimized for learning rate, dropout regularization, batch size, and epoch iteration by a sequential model-based Bayesian approach. In addition, we utilized pretrained architectures, applying transfer learning and fine-tuning techniques to fully connected layers. Our pipeline yielded binary classification validation accuracies of 98.3% for M-mode images and 99.8% with B-mode video frames.

show abstract

“…An emerging body of literature has shown that software analysis on ultrasound images for trauma can be useful 4,5 . In studies on pneumothorax, it has been shown that with a high quality ultrasound and expert-acquired images a high sensitivity and specificity can be achieved by software in animal studies 6 …”

mentioning

confidence: 99%

“…4,5 In studies on pneumothorax, it has been shown that with a high quality ultrasound and expert-acquired images a high sensitivity and specificity can be achieved by software in animal studies. 6 Technological advances in probe design have resulted in the availability of low cost probes that can run off the limited voltage of a USB port. Images acquired using these smartphonebased probes generally have decreased resolution [7][8][9] and may benefit more computer assisted or AI methodologies.…”

mentioning

confidence: 99%