Dense Pixel-Labeling For Reverse-Transfer And Diagnostic Learning On Lung Ultrasound For Covid-19 And Pneumonia Detection

Gare, Gautam Rajendrakumar; Schoenling, Andrew; Philip, V. R.; Hung, Tran Van; deBoisblanc, Bennett P.; Rodriguez, Ricardo Luis; Galeotti, John

doi:10.1109/isbi48211.2021.9433826

Cited by 15 publications

(24 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we compared our method with two main detection methods using the same LUS testing set, including the equidistance method proposed by Anantrasirichai et al 21 . and the U‐Net detection method proposed by Gare et al 30 . Their detection accuracies all were evaluated using the “depth” index introduced in Section 2.3.3, whose experimental results were shown in Figure 11.…”

Section: Resultsmentioning

confidence: 99%

“…In other words, the final accumulated accuracy of the whole system was 93.39% and 91.90% for convex and linear probes, respectively. In addition, we compared our method with two main detection methods using the same LUS testing set, including the equidistance method proposed by Anantrasirichai et al 21 and the U-Net detection method proposed by Gare et al 30 Their detection accuracies all were evaluated using the "depth" index introduced in Section 2.3.3, whose experimental results were shown in Figure 11. The comparison results showed that our method was better than the previous classical methods on both linear array and convex array probes.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…As a result, these methods were easily influenced by other similar structures and may produce some errors. What is more, Gare et al 30 . used the pretrained U‐Net deep learning model for A‐line detection, this method needed lots of labels for training, whereas the manual marking of A‐lines was difficult and inefficient, which was also vulnerable to some similar structures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic detection of A‐line in lung ultrasound images using deep learning and image processing

Xing

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Background Auxiliary diagnosis and monitoring of lung diseases based on lung ultrasound (LUS) images is important clinical research. A‐line is one of the most common indicators of LUS that can offer support for the assessment of lung diseases. A traditional A‐line detection method mainly relies on experienced clinicians, which is inefficient and cannot meet the needs of these areas with backward medical level. Therefore, how to realize the automatic detection of A‐line in LUS image is important. Purpose In order to solve the disadvantages of traditional A‐line detection methods, realize automatic and accurate detection, and provide theoretical support for clinical application, we proposed a novel A‐line detection method for LUS images with different probe types in this paper. Methods First, the improved Faster R‐CNN model with a selection strategy of localization box was designed to accurately locate the pleural line. Then, the LUS image below the pleural line was segmented for independent analysis excluding the influence of other similar structures. Next, image‐processing methods based on total variation, matched filter, and gray difference were applied to achieve the automatic A‐line detection. Finally, the “depth” index was designed to verify the accuracy by judging whether the automatic measurement results belong to corresponding manual results (±5%). In experiments, 3000 convex array LUS images were used for training and validating the improved pleural line localization model by five‐fold cross validation. 850 convex array LUS images and 1080 linear array LUS images were used for testing the trained pleural line localization model and the proposed image‐processing‐based A‐line detection method. The accuracy analysis, error statistics, and Harsdorff distance were employed to evaluate the experimental results. Results After 100 epochs, the mean loss value of training and validation set of improved Faster R‐CNN model reached 0.6540 and 0.7882, with the validation accuracy of 98.70%. The trained pleural line localization model was applied in the testing set of convex and linear probes and reached the accuracy of 97.88% and 97.11%, respectively, which were 3.83% and 8.70% higher than the original Faster R‐CNN model. The accuracy, sensitivity, and specificity of A‐line detection reached 95.41%, 0.9244%, 0.9875%, and 94.63%, 0.9230%, and 0.9766% for convex and linear probes, respectively. Compared to the experienced clinicians’ results, the mean value and p value of depth error were 1.5342 ± 1.2097 and 0.9021, respectively, and the Harsdorff distance was 5.7305 ± 1.8311. In addition, the accumulated accuracy of the two‐stage experiment (pleural line localization and A‐line detection) was calculated as the final accuracy of the whole A‐line detection system. They were 93.39% and 91.90% for convex and linear probes, respectively, which were higher than these previous methods. Conclusions The proposed method combining image processing and deep learning can automatically and accurately detect A‐line in LUS ima...

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic detection of A‐line in lung ultrasound images using deep learning and image processing

Xing

et al. 2022

Medical Physics

View full text Add to dashboard Cite

show abstract

“…They further introduced a third sampled quaternary method to annotate all frames based on only 10% positively labeled samples from the whole dataset, which outperformed the previous two labeling strategies. Gare et al tried to convert a pre-trained segmentation model into a diagnostic classifier and compared the results from dense vs. sparse segmentation labeling [ 84 ]. Tested on a restricted dataset of 152 images from four patients (three COVID-19 positives and one control), they found that with pretrained segmentation weights and dense labeling pretrained U-net, the classifier performs best with an overall accuracy of 0.84.…”

Section: Machine Learning In Covid-19 Lusmentioning

confidence: 99%

Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic

et al. 2022

View full text Add to dashboard Cite

Ultrasound imaging of the lung has played an important role in managing patients with COVID-19–associated pneumonia and acute respiratory distress syndrome (ARDS). During the COVID-19 pandemic, lung ultrasound (LUS) or point-of-care ultrasound (POCUS) has been a popular diagnostic tool due to its unique imaging capability and logistical advantages over chest X-ray and CT. Pneumonia/ARDS is associated with the sonographic appearances of pleural line irregularities and B-line artefacts, which are caused by interstitial thickening and inflammation, and increase in number with severity. Artificial intelligence (AI), particularly machine learning, is increasingly used as a critical tool that assists clinicians in LUS image reading and COVID-19 decision making. We conducted a systematic review from academic databases (PubMed and Google Scholar) and preprints on arXiv or TechRxiv of the state-of-the-art machine learning technologies for LUS images in COVID-19 diagnosis. Openly accessible LUS datasets are listed. Various machine learning architectures have been employed to evaluate LUS and showed high performance. This paper will summarize the current development of AI for COVID-19 management and the outlook for emerging trends of combining AI-based LUS with robotics, telehealth, and other techniques.

show abstract

“…Related Work Current LUS AI approaches [22,3,10] train models directly for the diagnostic end task, sometimes using segmentation labels for pretraining [24,11] to help improve performance. Although segmentation labels may be thought of as a type of biomarker, segmentations do not succinctly describe the key properties of the videos and segmentation labels are costly to obtain.…”

Section: Introductionmentioning

confidence: 99%

Learning Generic Lung Ultrasound Biomarkers for Decoupling Feature Extraction from Downstream Tasks

Gare¹,

Fox²,

Lowery³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Contemporary artificial neural networks (ANN) are trained end-to-end, jointly learning both features and classifiers for the task of interest. Though enormously effective, this paradigm imposes significant costs in assembling annotated task-specific datasets and training large-scale networks. We propose to decouple feature learning from downstream lung ultrasound tasks by introducing an auxiliary pre-task of visual biomarker classification. We demonstrate that one can learn an informative, concise, and interpretable feature space from ultrasound videos by training models for predicting biomarker labels. Notably, biomarker feature extractors can be trained from data annotated with weak videoscale supervision. These features can be used by a variety of downstream Expert models targeted for diverse clinical tasks (Diagnosis, lung severity, S/F ratio). Crucially, task-specific expert models are comparable in accuracy to end-to-end models directly trained for such target tasks, while being significantly lower cost to train.

show abstract

Dense Pixel-Labeling For Reverse-Transfer And Diagnostic Learning On Lung Ultrasound For Covid-19 And Pneumonia Detection

Cited by 15 publications

References 13 publications

Automatic detection of A‐line in lung ultrasound images using deep learning and image processing

Automatic detection of A‐line in lung ultrasound images using deep learning and image processing

Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic

Learning Generic Lung Ultrasound Biomarkers for Decoupling Feature Extraction from Downstream Tasks

Contact Info

Product

Resources

About