scholarly journals Prenatal prediction of neonatal respiratory morbidity: a radiomics method based on imbalanced few-shot fetal lung ultrasound images

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Jing Jiao ◽  
Yanran Du ◽  
Xiaokang Li ◽  
Yi Guo ◽  
Yunyun Ren ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Data Augmentation ◽  
Lung Ultrasound ◽  
Fetal Lung ◽  
Performance Outcomes ◽  
Respiratory Morbidity ◽  
Ultrasound Images ◽  
Evaluation Tool ◽  
Non Invasive ◽  
Fetal Lungs

Abstract Background To develop a non-invasive method for the prenatal prediction of neonatal respiratory morbidity (NRM) by a novel radiomics method based on imbalanced few-shot fetal lung ultrasound images. Methods A total of 210 fetal lung ultrasound images were enrolled in this study, including 159 normal newborns and 51 NRM newborns. Fetal lungs were delineated as the region of interest (ROI), where radiomics features were designed and extracted. Integrating radiomics features selected and two clinical features, including gestational age and gestational diabetes mellitus, the prediction model was developed and evaluated. The modelling methods used were data augmentation, cost-sensitive learning, and ensemble learning. Furthermore, two methods, which embed data balancing into ensemble learning, were employed to address the problems of imbalance and few-shot simultaneously. Results Our model achieved sensitivity values of 0.82, specificity values of 0.84, balanced accuracy values of 0.83 and area under the curve values of 0.87 in the test set. The radiomics features extracted from the ROIs at different locations within the lung region achieved similar classification performance outcomes. Conclusion The feature set we designed can efficiently and robustly describe fetal lungs for NRM prediction. RUSBoost shows excellent performance compared to state-of-the-art classifiers on the imbalanced few-shot dataset. The diagnostic efficacy of the model we developed is similar to that of several previous reports of amniocentesis and can serve as a non-invasive, precise evaluation tool for NRM prediction.

Prenatal Prediction of Neonatal Respiratory Morbidity: A Radiomics Method Based on Imbalanced Few-Shot Fetal Lung Ultrasound Images

2021 ◽  
Author(s):  
Jing Jiao ◽  
Yanran Du ◽  
Xiaokang Li ◽  
Yi Guo ◽  
Yunyun Ren ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Data Augmentation ◽  
Lung Ultrasound ◽  
Fetal Lung ◽  
Performance Outcomes ◽  
Respiratory Morbidity ◽  
Ultrasound Images ◽  
Evaluation Tool ◽  
Non Invasive ◽  
Fetal Lungs

Abstract Background: To develop a non-invasive method for the prenatal prediction of neonatal respiratory morbidity (NRM) by a novel radiomics method based on imbalanced few-shot fetal lung ultrasound images.Methods: A total of 210 fetal lung ultrasound images were enrolled in this study, including 159 normal newborns and 51 NRM newborns. Fetal lungs were delineated as the region of interest (ROI), where radiomics features were designed and extracted. Integrating radiomics features selected and two clinical features, including gestational age (GA) and gestational diabetes mellitus (GDM), the prediction model was developed and evaluated. The modelling methods used were data augmentation, cost-sensitive learning, and ensemble learning. Furthermore, two methods, which embed data balancing into ensemble learning, were employed to address the problems of imbalance and few-shot simultaneously.Results: Our model achieved sensitivity values of 0.82, specificity values of 0.84, accuracy values of 0.84 and area under the curve values of 0.87 in the test set. The radiomics features extracted from the ROIs at different locations within the lung region achieved similar classification performance outcomes.Conclusion: The feature set we designed can efficiently and robustly describe fetal lungs for NRM prediction. RUSBoost shows excellent performance compared to state-of-the-art classifiers on the imbalanced few-shot dataset. The diagnostic efficacy of the model we developed is similar to that of several previous reports of amniocentesis and can serve as a non-invasive, precise evaluation tool for NRM prediction.

scholarly journals Evaluation of an improved tool for non-invasive prediction of neonatal respiratory morbidity based on fully automated fetal lung ultrasound analysis

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Xavier P. Burgos-Artizzu ◽  
Álvaro Perez-Moreno ◽  
David Coronado-Gutierrez ◽  
Eduard Gratacos ◽  
Montse Palacio
Keyword(s):  
Lung Ultrasound ◽  
Fetal Lung ◽  
Respiratory Morbidity ◽  
Non Invasive

scholarly journals The Rise of Lung Ultrasound in the Era of COVID-19

2021 ◽  
Vol 33 (4) ◽  
pp. 5-8
Author(s):  
Shailendra Kumar Motwani ◽  
Helen Saunders
Keyword(s):  
Lung Ultrasound ◽  
Image Interpretation ◽  
Ultrasound Images ◽  
The Novel ◽  
Non Invasive ◽  
Global Pandemic ◽  
Pleural Surface ◽  
Chest X Ray ◽  
Novel Coronavirus ◽  
Huge Challenge

The current global pandemic caused by the novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) presents a huge challenge for physicians. Rapid diagnosis, triage and clinical management of these patients is a challenge for physicians but may be aided using lung ultrasound. Lung ultrasound has been in use for over 10 years mainly by critical care practitioners and emergency physicians with variable uptake, but it has gained popularity during the Coronavirus disease-2019 (COVID-19) pandemic as a diagnostic tool and can be easily learned compared to the other ultrasound techniques. Image interpretation is based on identifying artefacts generated by the pleural surface. This technique is non-invasive and can be performed rapidly at the patient’s bedside. It has higher accuracy in diagnosis than auscultation and Chest X-ray (CXR) combined. In this article the authors describe the interpretation of lung ultrasound images, particularly in patients with COVID-19 and discuss indications for this technique. Physicians are recommended to gain familiarity with this technique and use of online resources for guidance.

scholarly journals Clinical Feasibility of Quantitative Ultrasound Texture Analysis: A Robustness Study Using Fetal Lung Ultrasound Images

2018 ◽  
Vol 38 (6) ◽  
pp. 1459-1476
Author(s):  
Alvaro Perez‐Moreno ◽  
Mara Dominguez ◽  
Federico Migliorelli ◽  
Eduard Gratacos ◽  
Montse Palacio ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Quantitative Ultrasound ◽  
Lung Ultrasound ◽  
Fetal Lung ◽  
Ultrasound Images

scholarly journals Classification of Lung Disease in Children by Using Lung Ultrasound Images and Deep Convolutional Neural Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Silvia Magrelli ◽  
Piero Valentini ◽  
Cristina De Rose ◽  
Rosa Morello ◽  
Danilo Buonsenso
Keyword(s):  
Deep Learning ◽  
Bacterial Pneumonia ◽  
Data Augmentation ◽  
Lung Ultrasound ◽  
Pulmonary Diseases ◽  
Batch Size ◽  
Ultrasound Images ◽  
Data Set ◽  
Relative Safety ◽  
Computer Aided

Bronchiolitis is the most common cause of hospitalization of children in the first year of life and pneumonia is the leading cause of infant mortality worldwide. Lung ultrasound technology (LUS) is a novel imaging diagnostic tool for the early detection of respiratory distress and offers several advantages due to its low-cost, relative safety, portability, and easy repeatability. More precise and efficient diagnostic and therapeutic strategies are needed. Deep-learning-based computer-aided diagnosis (CADx) systems, using chest X-ray images, have recently demonstrated their potential as a screening tool for pulmonary disease (such as COVID-19 pneumonia). We present the first computer-aided diagnostic scheme for LUS images of pulmonary diseases in children. In this study, we trained from scratch four state-of-the-art deep-learning models (VGG19, Xception, Inception-v3 and Inception-ResNet-v2) for detecting children with bronchiolitis and pneumonia. In our experiments we used a data set consisting of 5,907 images from 33 healthy infants, 3,286 images from 22 infants with bronchiolitis, and 4,769 images from 7 children suffering from bacterial pneumonia. Using four-fold cross-validation, we implemented one binary classification (healthy vs. bronchiolitis) and one three-class classification (healthy vs. bronchiolitis vs. bacterial pneumonia) out of three classes. Affine transformations were applied for data augmentation. Hyperparameters were optimized for the learning rate, dropout regularization, batch size, and epoch iteration. The Inception-ResNet-v2 model provides the highest classification performance, when compared with the other models used on test sets: for healthy vs. bronchiolitis, it provides 97.75% accuracy, 97.75% sensitivity, and 97% specificity whereas for healthy vs. bronchiolitis vs. bacterial pneumonia, the Inception-v3 model provides the best results with 91.5% accuracy, 91.5% sensitivity, and 95.86% specificity. We performed a gradient-weighted class activation mapping (Grad-CAM) visualization and the results were qualitatively evaluated by a pediatrician expert in LUS imaging: heatmaps highlight areas containing diagnostic-relevant LUS imaging-artifacts, e.g., A-, B-, pleural-lines, and consolidations. These complex patterns are automatically learnt from the data, thus avoiding hand-crafted features usage. By using LUS imaging, the proposed framework might aid in the development of an accessible and rapid decision support-method for diagnosing pulmonary diseases in children using LUS imaging.

Experimental Validation of Minimax Entropy Principle in Ultrasound Images

2019 ◽  
Vol 12 (6) ◽  
pp. 487-493
Author(s):  
Neha Mehta ◽  
Svav Prasad ◽  
Leena Arya
Keyword(s):  
Region Of Interest ◽  
Ultrasound Images ◽  
Human Gallbladder ◽  
New Approach ◽  
Non Invasive ◽  
Entropy Principle ◽  
Significant Performance ◽  
Considerable Impact ◽  
Ultrasonic Devices ◽  
Measure Of Uncertainty

Ultrasound imaging is one of the non-invasive imaging, that diagnoses the disease inside a human body and there are numerous ultrasonic devices being used frequently. Entropy as a well known statistical measure of uncertainty has a considerable impact on the medical images. A procedure for minimizing the entropy with respect to the region of interest is demonstrated. This new approach has shown the experiments using Extracted Region Of Interest Based Sharpened image, called as (EROIS) image based on Minimax entropy principle and various filters. In this turn, the approach also validates the versatility of the entropy concept. Experiments have been performed practically on the real-time ultrasound images collected from ultrasound centers and have shown a significant performance. The present approach has been validated with showing results over ultrasound images of the Human Gallbladder.

Isolation and characterization of a cytostatic histone H2B-like protein from fetal lungs of non-diabetic and diabetic rats

1993 ◽  
Vol 139 (1) ◽  
pp. 97-105
Author(s):  
P. R. Conliffe ◽  
H. P. J. Bennett ◽  
S. Mulay
Keyword(s):  
Amino Acid ◽  
Gel Filtration ◽  
Fetal Lung ◽  
Reversed Phase ◽  
Diabetic Rats ◽  
Histone H2b ◽  
Amino Terminal ◽  
Isolation And Characterization ◽  
Fetal Lungs ◽  
Cytostatic Factor

ABSTRACT It was observed in the course of other studies that rat fetal lung extracts inhibited proliferation of fetal lung cells in culture. The purpose of the present study was to isolate and characterize this cytostatic factor. It was found that fetal lungs contained a 16 kDa cytostatic factor and its concentration was twofold greater in fetal lungs of diabetic rats compared with control rats. This fetal lung cytostatic protein (FLCP) was purified by reversed-phase, heparin-affinity and gel filtration high-performance liquid chromatography and SDS-PAGE. The purified protein was electroblotted onto polyvinylidene difluoride membrane and subjected to sequence analysis. The amino-terminal sequence of this fetal lung cytostatic protein was PEPAKSAPAPXKGIGKQXXKAX XKA... and showed significant homology with histone H2B; however, the amino acid composition of FLCP suggested that it may be structurally distinct from histone H2B. Ion-spray mass spectrometry suggested that FLCP was made up of at least two species of the protein with molecular weights of 13 776·1 and 14 007·3 and was different from the molecular weight of rat histone H2B predicted by its cDNA sequence. The concentration of FLCP, based on amino acid compositions, was 0·32 nmol/g and 0·83 nmol/g wet fetal lung from non-diabetic and diabetic rats respectively. These findings suggest that the fetal rat lung produces a regulatory factor bearing considerable homology with but possibly different from histone H2B and that fetal lung immaturity during diabetic pregnancy might be contributed to by an increase in this factor. Journal of Endocrinology (1993) 139, 97–105

Sign in / Sign up

Export Citation Format

Share Document