Slimmable transformer with hybrid axial-attention for medical image segmentation.

The transformer architecture has achieved remarkable success in medical image analysis owing to its powerful capability for capturing long-range dependencies. However, due to the lack of intrinsic inductive bias in modeling visual structural information, the transformer generally requires a large-scale pre-training schedule, limiting the clinical applications over expensive small-scale medical data. To this end, we propose a slimmable transformer to explore intrinsic inductive bias via position information for medical image segmentation. Specifically, we empirically investigate how different position encoding strategies affect the prediction quality of the region of interest (ROI) and observe that ROIs are sensitive to different position encoding strategies. Motivated by this, we present a novel Hybrid Axial-Attention (HAA) that can be equipped with pixel-level spatial structure and relative position information as inductive bias. Moreover, we introduce a gating mechanism to achieve efficient feature selection and further improve the representation quality over small-scale datasets. Experiments on LGG and COVID-19 datasets prove the superiority of our method over the baseline and previous works. Internal workflow visualization with interpretability is conducted to validate our success better; the proposed slimmable transformer has the potential to be further developed into a visual software tool for improving computer-aided lesion diagnosis and treatment planning.

Longitudinal Echocardiographic Follow-Up of a Pediatric Multisystem Inflammatory Syndrome Cohort.

OBJECTIVE: Significant involvement of the cardiovascular system is known in multisystem inflammatory syndrome in children (MIS-C). This study aimed to examine the recovery of affected cardiovascular parameters over a medium-term follow-up. METHODS: A cohort of 69 children was studied prospectively. Assessments of left ventricular (LV) function and coronary artery abnormalities (CAA) were conducted at admission, 1.5 months, and 3 months. Coronavirus Disease 2019 (COVID-19) antibody titers were assessed at these three time points. Echocardiographic and antibody parameters (rising/decreasing) were analyzed for correlation. Outcomes were assessed using logistic regression. RESULTS: At admission, among the 78.2% of patients who were tested, 88.9% tested positive for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). A quarter of the patients had pericardial effusion, and half had valvulitis. Decreased ejection fraction, global circumferential strain (GCS), and global longitudinal strain (GLS) were seen in 54.4%, 68.6%, and 35.8% of patients, respectively. CAAs were observed in 27.78% of patients. Systolic dysfunction was significantly associated with older age. During follow-up, severe LV dysfunction normalized within 6-7 weeks, while mild to moderate dysfunction reached normalcy by two weeks. Both GCS and GLS reached normalcy within a median of two weeks. Diastolic parameters recovered by six weeks. Most small and moderate coronary aneurysms resolved, but a giant aneurysm in an infant remained large even after 15 months. Trends in antibodies and ejection fraction (EF) at three months were significantly correlated. Admission EF, GLS (at 6 weeks) and deceleration time (at 3 months) were significantly associated with intensive care unit (ICU) admission. The median segmental strain of the cohort remained low in certain segments at three months. CONCLUSION: Smaller CAAs resolve, whereas giant CAAs persist. EF and GLS are important predictors of Pediatric Intensive Care Unit (PICU) stay. The residual impairment of median segmental strain and persistent diastolic dysfunction at three months indicate the need for long-term follow-up.

Target sign in COVID-19, radiological interpretation and diagnostic contribution of digital thoracic tomosynthesis.

INTRODUCTION: Our objectives are: To describe the radiological semiology, clinical-analytical features and prognosis related to the target sign (TS) in COVID-19. To determine whether digital thoracic tomosynthesis (DTT) improves the diagnostic ability of radiography. MATERIAL AND METHODS: Retrospective, descriptive, single-centre, case series study, accepted by our ethical committee. Radiological, clinical, analytical and follow-up characteristics of patients with COVID-19 and TS on radiography and DTT between November 2020 and January 2021 were analysed. RESULTS: Eleven TS were collected in 7 patients, median age 35 years, 57% male. All TS presented with a central nodule and a peripheral ring, and in at least 82%, the lung in between was of normal density. All TS were located in peripheral, basal regions and 91% in posterior regions. TS were multiple in 43%. Contiguous TS shared the peripheral ring. Other findings related to pneumonia were associated in 86% of patients. DTT detected 82% more TS than radiography. Only one patient underwent a CT angiography of the pulmonary arteries, positive for acute pulmonary thromboembolism. Seventy-one per cent presented with pleuritic pain. No distinctive laboratory findings or prognostic worsening were detected. CONCLUSIONS: TS in COVID-19 predominates in peripheral and declining regions and can be multiple. Pulmonary thromboembolism was detected in one case. It occurs in young people, frequently with pleuritic pain and does not worsen the prognosis. DTT detects more than 80 % of TS than radiography.

COVID-19 diagnostic prediction on chest CT scan images using hybrid quantum-classical convolutional neural network.

Notwithstanding the extensive research efforts directed towards devising a dependable approach for the diagnosis of coronavirus disease 2019 (COVID-19), the inherent complexity and capriciousness of the virus continue to pose a formidable challenge to the precise identification of affected individuals. In light of this predicament, it is essential to devise a model for COVID-19 prediction utilizing chest computed tomography (CT) scans. To this end, we present a hybrid quantum-classical convolutional neural network (HQCNN) model, which is founded on stochastic quantum circuits that can discern COVID-19 patients from chest CT images. Two publicly available chest CT image datasets were employed to evaluate the performance of our model. The experimental outcomes evinced diagnostic accuracies of 99.39% and 97.91%, along with precisions of 99.19% and 98.52%, respectively. These findings are indicative of the fact that the proposed model surpasses recently published works in terms of performance, thus providing a superior ability to precisely predict COVID-19 positive instances.Communicated by Ramaswamy H. Sarma.

Clinical and imaging features of patients with COVID-19 in a double-center cohort study.

INTRODUCTION: There is extensive published data on coronavirus disease 2019 (COVID-19). However, information on the effective factors that improve the pulmonary involvement of COVID-19 patients, and long-term clinical and imaging follow-up of these patients is limited. METHODOLOGY: This is a prospective cohort study on patients with COVID-19 who were hospitalized in two major academic hospitals in Yazd, Iran. The correlation between the baseline demographic and clinical/para-clinical data with the imaging resolution status at day 60 was assessed. RESULTS: 122 patients, including 65 males, with an average age of 53.43 years participated in this study. Age, gender, baseline oxygen saturation (O2Sat), and the percentage of lung involvement were the main prognostic factors. Our results suggest that with every year increase in age, the probability of complete imaging resolution decreases by 6.4%. In addition, women are 2.07 times more likely to recover completely. Moreover, each percent increase of baseline O2Sat makes the patients 15.4% more likely to fully recover. As the patients' shortness of breath increases, the probability of recovery decreases by 9.8%.;56.7% of patients who did not recover after 60 days had persistent shortness of breath, while only 21% of those who recovered had symptoms of dyspnea after day 60. CONCLUSIONS: Age, gender, baseline O2Sat, percentage of lung involvement, and shortness of breath were identified as the main risk factors in the recovery of patients with COVID-19. Long-term follow-up of patients with COVID-19, especially patients with high-risk factors, is necessary.

Consistency label-activated region generating network for weakly supervised medical image segmentation.

The current methods of auto-segmenting medical images are limited due to insufficient and ambiguous pathonmorphological labeling. In clinical practice, rough classification labels (such as disease or normal) are more commonly used than precise segmentation masks. However, there is still much to be explored regarding utilizing these weak clinical labels to accurately determine the lesion mask and guide medical image segmentation. In this paper, we proposed a weakly supervised medical image segmentation model to directly generate the lesion mask through a class activation map (CAM) guided cycle-consistency label-activated region transferring network. Cycle-consistency enforces that the mappings between the two domains should be reversible, which ensures that the original image can be reconstructed from the translated image. We developed a complementary branches fusion module to address the issue of blurry boundaries in CAM-guided segmentation. The complementary branch preserves the original semantic information of the non-lesion region and perfectly fuses the transferred feature of the lesion region with a complementary mask-constrained fake image generation process to clear the boundary of the lesion and non-lesion regions. This module allows the class transformation to focus solely on the label-activated region, resulting in more explicit segmentation. This model can accurately identify different region of medical images at the pixel-level while preserving the overall semantic structure semantion. It organizes disease labels and corresponding regions during image synthesis. Our method utilizes a joint discrimination strategy that significantly enhances the precision of the produced lesion mask. Extensive experiments of the proposed method on BraTs, ISIC and COVID-19 datasets demonstrate superior performance over existing state-of-the-art methods. The code and datasets are available at: https://github.com/mlcb-jlu/MedImgSeg.

Examining factors related to low performance of predicting remission in participants with major depressive disorder using neuroimaging data and other clinical features.

Major depressive disorder (MDD), a prevalent mental health issue, affects more than 8% of the US population, and almost 17% in the young group of 18-25 years old. Since Covid-19, its prevalence has become even more significant. However, the remission (being free of depression) rates of first-line antidepressant treatments on MDD are only about 30%. To improve treatment outcomes, researchers have built various predictive models for treatment responses and yet none of them have been adopted in clinical use. One reason is that most predictive models are based on data from subjective questionnaires, which are less reliable. Neuroimaging data are promising objective prognostic factors, but they are expensive to obtain and hence predictive models using neuroimaging data are limited and such studies were usually in small scale (N<100). In this paper, we proposed an advanced machine learning (ML) pipeline for small training dataset with large number of features. We implemented multiple imputation for missing data and repeated K-fold cross validation (CV) to robustly estimate predictive performances. Different feature selection methods and stacking methods using 6 general ML models including random forest, gradient boosting decision tree, XGBoost, penalized logistic regression, support vector machine (SVM), and neural network were examined to evaluate the model performances. All predictive models were compared using model performance metrics such as accuracy, balanced accuracy, area under ROC curve (AUC), sensitivity and specificity. Our proposed ML pipeline was applied to a training dataset and obtained an accuracy and AUC above 0.80. But such high performance failed while applying our ML pipeline using an external validation dataset from the EMBARC study which is a multi-center study. We further examined the possible reasons especially the site heterogeneity issue.

Point-of-care lung ultrasound predicts hyperferritinemia and hospitalization, but not elevated troponin in SARS-CoV-2 viral pneumonitis in children.

SARS-CoV-2 often causes viral pneumonitis, hyperferritinemia, elevations in D-dimer, lactate dehydrogenase (LDH), transaminases, troponin, CRP, and other inflammatory markers. Lung ultrasound is increasingly used to diagnose and stratify viral pneumonitis severity. We retrospectively reviewed 427 visits in patients aged 14 days to 21 years who had had a point-of-care lung ultrasound in our pediatric emergency department from 30/November/2019 to 14/August/2021. Lung ultrasounds were categorized using a 6-point ordinal scale. Lung ultrasound abnormalities predicted increased hospitalization with a threshold effect. Increasingly abnormal laboratory values were associated with decreased discharge from the ED and increased admission to the ward and ICU. Among patients SARS-CoV-2 positive patients ferritin, LDH, and transaminases, but not CRP or troponin were significantly associated with abnormalities on lung ultrasound and also with threshold effects. This effect was not demonstrated in SARS-CoV-2 negative patients. D-Dimer, CRP, and troponin were sometimes elevated even when the lung ultrasound was normal.

MIS-Net: A deep learning-based multi-class segmentation model for CT images.

The accuracy of traditional CT image segmentation algorithms is hindered by issues such as low contrast and high noise in the images. While numerous scholars have introduced deep learning-based CT image segmentation algorithms, they still face challenges, particularly in achieving high edge accuracy and addressing pixel classification errors. To tackle these issues, this study proposes the MIS-Net (Medical Images Segment Net) model, a deep learning-based approach. The MIS-Net model incorporates multi-scale atrous convolution into the encoding and decoding structure with symmetry, enabling the comprehensive extraction of multi-scale features from CT images. This enhancement aims to improve the accuracy of lung and liver edge segmentation. In the evaluation using the COVID-19 CT Lung and Infection Segmentation dataset, the left and right lung segmentation results demonstrate that MIS-Net achieves a Dice Similarity Coefficient (DSC) of 97.61. Similarly, in the Liver Tumor Segmentation Challenge 2017 public dataset, the DSC of MIS-Net reaches 98.78.

Generalizable disease detection using model ensemble on chest X-ray images.

In the realm of healthcare, the demand for swift and precise diagnostic tools has been steadily increasing. This study delves into a comprehensive performance analysis of three pre-trained convolutional neural network (CNN) architectures: ResNet50, DenseNet121, and Inception-ResNet-v2. To ensure the broad applicability of our approach, we curated a large-scale dataset comprising a diverse collection of chest X-ray images, that included both positive and negative cases of COVID-19. The models' performance was evaluated using separate datasets for internal validation (from the same source as the training images) and external validation (from different sources). Our examination uncovered a significant drop in network efficacy, registering a 10.66% reduction for ResNet50, a 36.33% decline for DenseNet121, and a 19.55% decrease for Inception-ResNet-v2 in terms of accuracy. Best results were obtained with DenseNet121 achieving the highest accuracy at 96.71% in internal validation and Inception-ResNet-v2 attaining 76.70% accuracy in external validation. Furthermore, we introduced a model ensemble approach aimed at improving network performance when making inferences on images from diverse sources beyond their training data. The proposed method uses uncertainty-based weighting by calculating the entropy in order to assign appropriate weights to the outputs of each network. Our results showcase the effectiveness of the ensemble method in enhancing accuracy up to 97.38% for internal validation and 81.18% for external validation, while maintaining a balanced ability to detect both positive and negative cases.

CODENET: A deep learning model for COVID-19 detection.

Conventional COVID-19 testing methods have some flaws: they are expensive and time-consuming. Chest X-ray (CXR) diagnostic approaches can alleviate these flaws to some extent. However, there is no accurate and practical automatic diagnostic framework with good interpretability. The application of artificial intelligence (AI) technology to medical radiography can help to accurately detect the disease, reduce the burden on healthcare organizations, and provide good interpretability. Therefore, this study proposes a new deep neural network (CNN) based on CXR for COVID-19 diagnosis - CodeNet. This method uses contrastive learning to make full use of latent image data to enhance the model's ability to extract features and generalize across different data domains. On the evaluation dataset, the proposed method achieves an accuracy as high as 94.20%, outperforming several other existing methods used for comparison. Ablation studies validate the efficacy of the proposed method, while interpretability analysis shows that the method can effectively guide clinical professionals. This work demonstrates the superior detection performance of a CNN using contrastive learning techniques on CXR images, paving the way for computer vision and artificial intelligence technologies to leverage massive medical data for disease diagnosis.

Age and chest computed tomography severity score are predictors of long-COVID.

INTRODUCTION: About one-third of acute coronavirus disease 2019 (COVID-19) survivors have suffered from persisting symptoms called long-COVID. Clinical factors such as age and intensity (moderate or acute) of COVID-19 have been found to be associated with long-COVID. Many tissues might be damaged functionally or structurally during acute COVID-19 which can be detected by blood assays and chest computed tomography (CT). We aimed to evaluate the relationship between long-COVID and the initial findings of blood assays and chest CT as possible predictors. METHODOLOGY: The study included patients with acute COVID-19. Laboratory tests and chest CT were obtained from each patient at the time of admission to the hospital. Chest CT was evaluated for pneumonic involvement and severity score. Multivariable regression model was created to find the factors that were independently associated with long-COVID. RESULTS: There were 60 (38.2%) patients with long-COVID and 97 (61.8%) without. Baseline demographic, laboratory and chest CT parameters were similar in both groups, except for age, chronic lung disease and chest CT severity score (46.9 ± 15.1 years vs 52.6 ± 15.9 years, p = 0.03; 11.7% vs 3.1%, p = 0.03 and 10.3 ± 9.6 vs 6.5 ± 7.6, p = 0.02, respectively). In multivariable model, chest CT severity score (OR: 1.059, 95% CI: 1.002-1.119, p = 0.04) and age (OR: 0.953, 95% CI: 0.928-0.979, p < 0.001) were independently associated with long-COVID. CONCLUSIONS: Chest CT severity score and age were independently associated with long-COVID and may be used to predict the future risk of long-COVID.

Radiomics analysis for distinctive identification of COVID-19 pulmonary nodules from other benign and malignant counterparts.

This observational study investigated the potential of radiomics as a non-invasive adjunct to CT in distinguishing COVID-19 lung nodules from other benign and malignant lung nodules. Lesion segmentation, feature extraction, and machine learning algorithms, including decision tree, support vector machine, random forest, feed-forward neural network, and discriminant analysis, were employed in the radiomics workflow. Key features such as Idmn, skewness, and long-run low grey level emphasis were identified as crucial in differentiation. The model demonstrated an accuracy of 83% in distinguishing COVID-19 from other benign nodules and 88% from malignant nodules. This study concludes that radiomics, through machine learning, serves as a valuable tool for non-invasive discrimination between COVID-19 and other benign and malignant lung nodules. The findings suggest the potential complementary role of radiomics in patients with COVID-19 pneumonia exhibiting lung nodules and suspicion of concurrent lung pathologies. The clinical relevance lies in the utilization of radiomics analysis for feature extraction and classification, contributing to the enhanced differentiation of lung nodules, particularly in the context of COVID-19.

Enhancing medical image segmentation with a multi-transformer U-Net.

Various segmentation networks based on Swin Transformer have shown promise in medical segmentation tasks. Nonetheless, challenges such as lower accuracy and slower training convergence have persisted. To tackle these issues, we introduce a novel approach that combines the Swin Transformer and Deformable Transformer to enhance overall model performance. We leverage the Swin Transformer's window attention mechanism to capture local feature information and employ the Deformable Transformer to adjust sampling positions dynamically, accelerating model convergence and aligning it more closely with object shapes and sizes. By amalgamating both Transformer modules and incorporating additional skip connections to minimize information loss, our proposed model excels at rapidly and accurately segmenting CT or X-ray lung images. Experimental results demonstrate the remarkable, showcasing the significant prowess of our model. It surpasses the performance of the standalone Swin Transformer's Swin Unet and converges more rapidly under identical conditions, yielding accuracy improvements of 0.7% (resulting in 88.18%) and 2.7% (resulting in 98.01%) on the COVID-19 CT scan lesion segmentation dataset and Chest X-ray Masks and Labels dataset, respectively. This advancement has the potential to aid medical practitioners in early diagnosis and treatment decision-making.

Anomaly Detection for Medical Images Using Heterogeneous Auto-Encoder.

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples; 2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous Auto-Encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

CD-Net: Cascaded 3D Dilated convolutional neural network for pneumonia lesion segmentation.

COVID-19 is a global pandemic that has caused significant global, social, and economic disruption. To effectively assist in screening and monitoring diagnosed cases, it is crucial to accurately segment lesions from Computer Tomography (CT) scans. Due to the lack of labeled data and the presence of redundant parameters in 3D CT, there are still significant challenges in diagnosing COVID-19 in related fields. To address the problem, we have developed a new model called the Cascaded 3D Dilated convolutional neural network (CD-Net) for directly processing CT volume data. To reduce memory consumption when cutting volume data into small patches, we initially design a cascade architecture in CD-Net to preserve global information. Then, we construct a Multi-scale Parallel Dilated Convolution (MPDC) block to aggregate features of different sizes and simultaneously reduce the parameters. Moreover, to alleviate the shortage of labeled data, we employ classical transfer learning, which requires only a small amount of data while achieving better performance. Experimental results conducted on the different public-available datasets verify that the proposed CD-Net has reduced the negative-positive ratio and outperformed other existing segmentation methods while requiring less data.

Integrated assessment of computed tomography density in pectoralis and erector spinae muscles as a prognostic biomarker for coronavirus disease 2019.

BACKGROUND ＆ AIMS: Muscle quantification using chest computed tomography (CT) is a useful prognostic biomarker for coronavirus disease 2019 (COVID-19). However, no studies have evaluated the clinical course through comprehensive assessment of the pectoralis and erector spinae muscles. Therefore, we compared the impact of the areas and densities of these muscles on COVID-19 infection outcome. METHODS: This multicenter retrospective cohort study was conducted by the COVID-19 Task Force. A total of 1410 patients with COVID-19 were included, and data on the area and density of the pectoralis and erector spinae muscles on chest CT were collected. The impact of each muscle parameter on the clinical outcome of COVID-19 was stratified according to sex. The primary outcome was the percentage of patients with severe disease, including those requiring oxygen supplementation and those who died. Additionally, 167 patients were followed up for changes in muscle parameters at three months and for the clinical characteristics in case of reduced CT density. RESULTS: For both muscles, low density rather than muscle area was associated with COVID-19 severity. Regardless of sex, lower erector spinae muscle density was associated with more severe disease than pectoralis muscle density. The muscles were divided into two groups using the receiver operating characteristic curve of CT density, and the population was classified into four (Group A: high CT density for both muscles, Group B: low CT density for pectoralis and high for erector spinae muscle. Group C: high CT density for pectoralis and low for erector spinae muscle, Group D: low CT density for both muscles). In univariate analysis, Group D patients exhibited worse outcomes than Group A (OR: 2.96, 95% CI: 2.03-4.34 in men; OR: 3.02, 95% CI: 2.66-10.4 in women). Multivariate analysis revealed that men in Group D had a significantly more severe prognosis than those in Group A (OR: 1.82, 95% CI: 1.16-2.87). Moreover, Group D patients tended to have the highest incidence of other complications due to secondary infections and acute kidney injury during the clinical course. Longitudinal analysis of both muscle densities over three months revealed that patients with decreased muscle density over time were more likely to have severe cases than those who did not. CONCLUSIONS: Muscle density, rather than muscle area, predicts the clinical outcomes of COVID-19. Integrated assessment of pectoralis and erector spinae muscle densities demonstrated higher accuracy in predicting the clinical course of COVID-19 than individual assessments.

Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment.

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.

A methodical exploration of imaging modalities from dataset to detection through machine learning paradigms in prominent lung disease diagnosis: a review.

BACKGROUND: Lung diseases, both infectious and non-infectious, are the most prevalent cause of mortality overall in the world. Medical research has identified pneumonia, lung cancer, and Corona Virus Disease 2019 (COVID-19) as prominent lung diseases prioritized over others. Imaging modalities, including X-rays, computer tomography (CT) scans, magnetic resonance imaging (MRIs), positron emission tomography (PET) scans, and others, are primarily employed in medical assessments because they provide computed data that can be utilized as input datasets for computer-assisted diagnostic systems. Imaging datasets are used to develop and evaluate machine learning (ML) methods to analyze and predict prominent lung diseases. OBJECTIVE: This review analyzes ML paradigms, imaging modalities' utilization, and recent developments for prominent lung diseases. Furthermore, the research also explores various datasets available publically that are being used for prominent lung diseases. METHODS: The well-known databases of academic studies that have been subjected to peer review, namely ScienceDirect, arXiv, IEEE Xplore, MDPI, and many more, were used for the search of relevant articles. Applied keywords and combinations used to search procedures with primary considerations for review, such as pneumonia, lung cancer, COVID-19, various imaging modalities, ML, convolutional neural networks (CNNs), transfer learning, and ensemble learning. RESULTS: This research finding indicates that X-ray datasets are preferred for detecting pneumonia, while CT scan datasets are predominantly favored for detecting lung cancer. Furthermore, in COVID-19 detection, X-ray datasets are prioritized over CT scan datasets. The analysis reveals that X-rays and CT scans have surpassed all other imaging techniques. It has been observed that using CNNs yields a high degree of accuracy and practicability in identifying prominent lung diseases. Transfer learning and ensemble learning are complementary techniques to CNNs to facilitate analysis. Furthermore, accuracy is the most favored metric for assessment.

Evaluating a novel accelerated free-breathing late gadolinium enhancement imaging sequence for assessment of myocardial injury.

INTRODUCTION: Cardiac magnetic resonance imaging (MRI), including late gadolinium enhancement (LGE), plays an important role in the diagnosis and prognostication of ischemic and non-ischemic myocardial injury. Conventional LGE sequences require patients to perform multiple breath-holds and require long acquisition times. In this study, we compare image quality and assessment of myocardial LGE using an accelerated free-breathing sequence to the conventional standard-of-care sequence. METHODS: In this prospective cohort study, a total of 41 patients post Coronavirus 2019 (COVID-19) infection were included. Studies were performed on a 1.5 Tesla scanner with LGE imaging acquired using a conventional inversion recovery rapid gradient echo (conventional LGE) sequence followed by the novel accelerated free-breathing (FB-LGE) sequence. Image quality was visually scored (ordinal scale from 1 to 5) and compared between conventional and free-breathing sequences using the Wilcoxon rank sum test. Presence of per-segment LGE was identified according to the American Heart Association 16-segment myocardial model and compared across both conventional LGE and FB-LGE sequences using a two-sided chi-square test. The perpatient LGE extent was also evaluated using both sequences and compared using the Wilcoxon rank sum test. Interobserver variability in detection of per-segment LGE and per-patient LGE extent was evaluated using Cohen's kappa statistic and interclass correlation (ICC), respectively. RESULTS: The mean acquisition time for the FB-LGE sequence was 17 s compared to 413 s for the conventional LGE sequence (P < 0.001). Assessment of image quality was similar between both sequences (P = 0.19). There were no statistically significant differences in LGE assessed using the FB-LGE versus conventional LGE on a per-segment (P = 0.42) and per-patient (P = 0.06) basis. Interobserver variability in LGE assessment for FB-LGE was good for per-segment (= 0.71) and per-patient extent (ICC = 0.92) analyses. CONCLUSIONS: The accelerated FB-LGE sequence performed comparably to the conventional standard-of-care LGE sequence in a cohort of patients post COVID-19 infection in a fraction of the time and without the need for breath-holding. Such a sequence could impact clinical practice by increasing cardiac MRI throughput and accessibility for frail or acutely ill patients unable to perform breath-holding.