Robust segmentation of lung in chest x-ray: applications in analysis of acute respiratory distress syndrome

Advanced Diagnostics of Respiratory Distress Syndrome in Premature Infants Treated with Surfactant and Budesonide through Computer-Assisted Chest X-ray Analysis

This research addresses the respiratory distress syndrome (RDS) in preterm newborns caused by insufficient surfactant synthesis, which can lead to serious complications, including pneumothorax, pulmonary hypertension, and pulmonary hemorrhage, increasing the risk of a fatal outcome. By analyzing chest radiographs and blood gases, we specifically focus on the significant contributions of these parameters to the diagnosis and analysis of the recovery of patients with RDS. The study involved 32 preterm newborns, and the analysis of gas parameters before and after the administration of surfactants and inhalation corticosteroid therapy revealed statistically significant changes in values of parameters such as FiO2, pH, pCO2, HCO3, and BE (Sig. < 0.05), while the pO2 parameter showed a potential change (Sig. = 0.061). Parallel to this, the research emphasizes the development of a lung segmentation algorithm implemented in the MATLAB programming environment. The key steps of the algorithm include preprocessing, segmentation, and visualization for a more detailed understanding of the recovery dynamics after RDS. These algorithms have achieved promising results, with a global accuracy of 0.93 ± 0.06, precision of 0.81 ± 0.16, and an F-score of 0.82 ± 0.14. These results highlight the potential application of algorithms in the analysis and monitoring of recovery in newborns with RDS, also underscoring the need for further development of software solutions in medicine, particularly in neonatology, to enhance the diagnosis and treatment of preterm newborns with respiratory distress syndrome.

Identifying the optimal deep learning architecture and parameters for automatic beam aperture definition in 3D radiotherapy

PURPOSE

Two-dimensional radiotherapy is often used to treat cervical cancer in low- and middle-income countries, but treatment planning can be challenging and time-consuming. Neural networks offer the potential to greatly decrease planning time through automation, but the impact of the wide range of hyperparameters to be set during training on model accuracy has not been exhaustively investigated. In the current study, we evaluated the effect of several convolutional neural network architectures and hyperparameters on 2D radiotherapy treatment field delineation.

METHODS

Six commonly used deep learning architectures were trained to delineate four-field box apertures on digitally reconstructed radiographs for cervical cancer radiotherapy. A comprehensive search of optimal hyperparameters for all models was conducted by varying the initial learning rate, image normalization methods, and (when appropriate) convolutional kernel size, the number of learnable parameters via network depth and the number of feature maps per convolution, and nonlinear activation functions. This yielded over 1700 unique models, which were all trained until performance converged and then tested on a separate dataset.

RESULTS

Of all hyperparameters, the choice of initial learning rate was most consistently significant for improved performance on the test set, with all top-performing models using learning rates of 0.0001. The optimal image normalization was not consistent across architectures. High overlap (mean Dice similarity coefficient = 0.98) and surface distance agreement (mean surface distance < 2 mm) were achieved between the treatment field apertures for all architectures using the identified best hyperparameters. Overlap Dice similarity coefficient (DSC) and distance metrics (mean surface distance and Hausdorff distance) indicated that DeepLabv3+ and D-LinkNet architectures were least sensitive to initial hyperparameter selection.

CONCLUSION

DeepLabv3+ and D-LinkNet are most robust to initial hyperparameter selection. Learning rate, nonlinear activation function, and kernel size are also important hyperparameters for improving performance.

Tumor segmentation via enhanced area growth algorithm for lung CT images

BACKGROUND

Since lung tumors are in dynamic conditions, the study of tumor growth and its changes is of great importance in primary diagnosis.

METHODS

Enhanced area growth (EAG) algorithm is introduced to segment the lung tumor in 2D and 3D modes on 60 patients CT images from four different databases by MATLAB software. The contrast augmentation, color intensity and maximum primary tumor radius determination, thresholding, start and neighbor points' designation in an array, and then modifying the points in the braid on average are the early steps of the proposed algorithm. To determine the new tumor boundaries, the maximum distance from the color-intensity center point of the primary tumor to the modified points is appointed via considering a larger target region and new threshold. The tumor center is divided into different subsections and then all previous stages are repeated from new designated points to define diverse boundaries for the tumor. An interpolation between these boundaries creates a new tumor boundary. The intersections with the tumor boundaries are firmed for edge correction phase, after drawing diverse lines from the tumor center at relevant angles. Each of the new regions is annexed to the core region to achieve a segmented tumor surface by meeting certain conditions.

RESULTS

The multipoint-growth-starting-point grouping fashioned a desired consequence in the precise delineation of the tumor. The proposed algorithm enhanced tumor identification by more than 16% with a reasonable accuracy acceptance rate. At the same time, it largely assurances the independence of the last outcome from the starting point. By significance difference of p < 0.05, the dice coefficients were 0.80 ± 0.02 and 0.92 ± 0.03, respectively, for primary and enhanced algorithms. Lung area determination alongside automatic thresholding and also starting from several points along with edge improvement may reduce human errors in radiologists' interpretation of tumor areas and selection of the algorithm's starting point.

CONCLUSIONS

The proposed algorithm enhanced tumor detection by more than 18% with a sufficient acceptance ratio of accuracy. Since the enhanced algorithm is independent of matrix size and image thickness, it is very likely that it can be easily applied to other contiguous tumor images.

TRIAL REGISTRATION

PAZHOUHAN, PAZHOUHAN98000032. Registered 4 January 2021, http://pazhouhan.gerums.ac.ir/webreclist/view.action?webreclist_code=19300.

Development of lung segmentation method in x-ray images of children based on TransResUNet

Background

Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.

Objective

In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.

Methods

The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.

Results

Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.

Conclusions

This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest X-ray Scans

Background and Motivation: COVID-19 has resulted in a massive loss of life during the last two years. The current imaging-based diagnostic methods for COVID-19 detection in multiclass pneumonia-type chest X-rays are not so successful in clinical practice due to high error rates. Our hypothesis states that if we can have a segmentation-based classification error rate <5%, typically adopted for 510 (K) regulatory purposes, the diagnostic system can be adapted in clinical settings. Method: This study proposes 16 types of segmentation-based classification deep learning-based systems for automatic, rapid, and precise detection of COVID-19. The two deep learning-based segmentation networks, namely UNet and UNet+, along with eight classification models, namely VGG16, VGG19, Xception, InceptionV3, Densenet201, NASNetMobile, Resnet50, and MobileNet, were applied to select the best-suited combination of networks. Using the cross-entropy loss function, the system performance was evaluated by Dice, Jaccard, area-under-the-curve (AUC), and receiver operating characteristics (ROC) and validated using Grad-CAM in explainable AI framework. Results: The best performing segmentation model was UNet, which exhibited the accuracy, loss, Dice, Jaccard, and AUC of 96.35%, 0.15%, 94.88%, 90.38%, and 0.99 (p-value <0.0001), respectively. The best performing segmentation-based classification model was UNet+Xception, which exhibited the accuracy, precision, recall, F1-score, and AUC of 97.45%, 97.46%, 97.45%, 97.43%, and 0.998 (p-value <0.0001), respectively. Our system outperformed existing methods for segmentation-based classification models. The mean improvement of the UNet+Xception system over all the remaining studies was 8.27%. Conclusion: The segmentation-based classification is a viable option as the hypothesis (error rate <5%) holds true and is thus adaptable in clinical practice.

Ultrasound Lung Image under Artificial Intelligence Algorithm in Diagnosis of Neonatal Respiratory Distress Syndrome

In order to analyze the application of ultrasonic lung imaging diagnosis model based on artificial intelligence algorithm in neonatal respiratory distress syndrome (NRDS), an ultrasonic lung imaging diagnosis model based on a deep residual network (DRN) was proposed. In this study, 90 premature infants in the hospital were selected as the research object and divided into the experimental group (45 cases) and control group (45 cases) according to whether or not they have NRDS. DRN was compared with the deep residual network (DRWSR) based on wavelet domain, deep residual network detection with normalization framework (Fisher-DRN), and distorted image edge detection preprocessor (DIEDP). Then, it was applied to the diagnosis of NRDS. The clinical data and ultrasound imaging results of infants with NRDS and ordinary premature infants were compared. The results showed that the gestational age, birth weight, and Apgar scores of the NRDS group were remarkably lower than those of ordinary children (P < 0.05). In addition, the segmentation accuracy, image feature extraction accuracy, algorithm convergence, and time loss of the DRN algorithm were better than the other three algorithms, and the differences were considerable (P < 0.05). In children with NRDS, the positive rate of abnormal pleural line, disappearance of A line, appearance of B line, and alveolar interstitial syndrome (AIS) test in the results of lung ultrasound examination in children with NRDS were all 100%. The lung consolidation became 70.8%, and the white lung-like change was 50.1%, both of which were higher than those of ordinary preterm infants, and the differences were considerable (P < 0.05). The diagnostic model of this study predicted that the AUC area of grade 1-2, grade 2-3, and grade 3-4 NRDS were 0.962, 0.881, and 0.902, respectively. To sum up, the ultrasound lung imaging diagnosis model based on the DRN algorithm had good diagnostic performance in children with NRDS and can provide useful information for clinical NRDS diagnosis and treatment.

Segmentation and Quantitative Analysis of Photoacoustic Imaging: A Review

Photoacoustic imaging is an emerging biomedical imaging technique that combines optical contrast and ultrasound resolution to create unprecedented light absorption contrast in deep tissue. Thanks to its fusional imaging advantages, photoacoustic imaging can provide multiple structural and functional insights into biological tissues such as blood vasculatures and tumors and monitor the kinetic movements of hemoglobin and lipids. To better visualize and analyze the regions of interest, segmentation and quantitative analyses were used to extract several biological factors, such as the intensity level changes, diameter, and tortuosity of the tissues. Over the past 10 years, classical segmentation methods and advances in deep learning approaches have been utilized in research investigations. In this review, we provide a comprehensive review of segmentation and quantitative methods that have been developed to process photoacoustic imaging in preclinical and clinical experiments. We focus on the parametric reliability of quantitative analysis for semantic and instance-level segmentation. We also introduce the similarities and alternatives of deep learning models in qualitative measurements using classical segmentation methods for photoacoustic imaging.

Pediatric chest radiograph interpretation: how far has artificial intelligence come? A systematic literature review

Most artificial intelligence (AI) studies have focused primarily on adult imaging, with less attention to the unique aspects of pediatric imaging. The objectives of this study were to (1) identify all publicly available pediatric datasets and determine their potential utility and limitations for pediatric AI studies and (2) systematically review the literature to assess the current state of AI in pediatric chest radiograph interpretation. We searched PubMed, Web of Science and Embase to retrieve all studies from 1990 to 2021 that assessed AI for pediatric chest radiograph interpretation and abstracted the datasets used to train and test AI algorithms, approaches and performance metrics. Of 29 publicly available chest radiograph datasets, 2 datasets included solely pediatric chest radiographs, and 7 datasets included pediatric and adult patients. We identified 55 articles that implemented an AI model to interpret pediatric chest radiographs or pediatric and adult chest radiographs. Classification of chest radiographs as pneumonia was the most common application of AI, evaluated in 65% of the studies. Although many studies report high diagnostic accuracy, most algorithms were not validated on external datasets. Most AI studies for pediatric chest radiograph interpretation have focused on a limited number of diseases, and progress is hindered by a lack of large-scale pediatric chest radiograph datasets.

A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image analysis, leaving several important questions unanswered. As the first step in this direction, we conduct a systematic study on the transferability of models pre-trained on iNat2021, the most recent large-scale fine-grained dataset, and 14 top self-supervised ImageNet models on 7 diverse medical tasks in comparison with the supervised ImageNet model. Furthermore, we present a practical approach to bridge the domain gap between natural and medical images by continually (pre-)training supervised ImageNet models on medical images. Our comprehensive evaluation yields new insights: (1) pre-trained models on fine-grained data yield distinctive local representations that are more suitable for medical segmentation tasks, (2) self-supervised ImageNet models learn holistic features more effectively than supervised ImageNet models, and (3) continual pre-training can bridge the domain gap between natural and medical images. We hope that this large-scale open evaluation of transfer learning can direct the future research of deep learning for medical imaging. As open science, all codes and pre-trained models are available on our GitHub page https://github.com/JLiangLab/BenchmarkTransferLearning.

Automated detection of acute respiratory distress syndrome from chest X-Rays using Directionality Measure and deep learning features

Acute respiratory distress syndrome (ARDS) is a life-threatening lung injury with global prevalence and high mortality. Chest x-rays (CXR) are critical in the early diagnosis and treatment of ARDS. However, imaging findings may not result in proper identification of ARDS due to a number of reasons, including nonspecific appearance of radiological features, ambiguity in a patient's case due to the pathological stage of the disease, and poor inter-rater reliability from interpretations of CXRs by multiple clinical experts. This study demonstrates the potential capability of methodologies in artificial intelligence, machine learning, and image processing to overcome these challenges and quantitatively assess CXRs for presence of ARDS. We propose and describe Directionality Measure, a novel feature engineering technique used to capture the "cloud-like" appearance of diffuse alveolar damage as a mathematical concept. This study also examines the effectiveness of using an off-the-shelf, pretrained deep learning model as a feature extractor in addition to standard features extracted from the histogram and gray-level co-occurrence matrix (GLCM). Data was collected from hospitalized patients at Michigan Medicine's intensive care unit and the cohort's inclusion criteria was specifically designed to be representative of patients at risk of developing ARDS. Multiple machine learning models were used to evaluate these features with 5-fold cross-validation and the final performance was reported on a hold-out, temporally distinct test set. With AdaBoost, Directionality Measure achieved an accuracy of 78% and AUC of 74% - outperforming classification results using features from the histogram (75% accuracy and 73% AUC), GLCM (76% accuracy and 73% AUC), and ResNet-50 (77% accuracy and 73% AUC). Further experimental results demonstrated that using all feature sets in combination achieved the best overall performance, yielding an accuracy of 83% and AUC of 79% with AdaBoost. These results demonstrate the potential capability of using the proposed methodologies to complement current clinical analysis for detection of ARDS from CXRs.

Automatic Lung Segmentation Algorithm on Chest X-ray Images Based on Fusion Variational Auto-Encoder and Three-Terminal Attention Mechanism

Automatic segmentation of the lungs in Chest X-ray images (CXRs) is a key step in the screening and diagnosis of related diseases. There are many opacities in the lungs in the CXRs of patients, which makes the lungs difficult to segment. In order to solve this problem, this paper proposes a segmentation algorithm based on U-Net. This article introduces variational auto-encoder (VAE) in each layer of the decoder-encoder. VAE can extract high-level semantic information, such as the symmetrical relationship between the left and right thoraxes in most cases. The fusion of the features of VAE and the features of convolution can improve the ability of the network to extract features. This paper proposes a three-terminal attention mechanism. The attention mechanism uses the channel and spatial attention module to automatically highlight the target area and improve the performance of lung segmentation. At the same time, the three-terminal attention mechanism uses the advanced semantics of high-scale features to improve the positioning and recognition capabilities of the attention mechanism, suppress background noise, and highlight target features. Experimental results on two different datasets show that the accuracy (ACC), recall (R), F1-Score and Jaccard values of the algorithm proposed in this paper are the highest on the two datasets, indicating that the algorithm in this paper is better than other state-of-the-art algorithms.