Chronic cavitary pulmonary aspergillosis: Serial clinical and CT findings correlated with antifungal treatment and patient response.

BACKGROUND: Chronic cavitary pulmonary aspergillosis (CCPA) is the most common form of chronic pulmonary aspergillosis. OBJECTIVE: We hypothesise that by observing serial clinical and CT findings of CCPA patients with antifungal therapy, factors helping predict responses to antifungal therapy could be withdrawn. METHODS: A total of 31 patients with CCPA who received antifungal therapy for greater than six months and who had serial CT studies were included. Clinical finding analyses were performed at initial and last follow-up CT acquisition dates. Clinical characteristics and CT features were compared between clinically improving or stable and deteriorating groups. RESULTS: With antifungal therapy, neutrophil-to-lymphocyte ratio (2.66 vs. 5.12, p = .038) and serum albumin (4.40 vs. 3.85 g/dl, p = .013) and CRP (1.10 vs. 42.80 mg/L, p = .007) were different between two groups. With antifungal therapy, meaningful CT change, regardless of clinical response grouping, was decrease in cavity wall thickness (from 13.70 mm to 8.28 mm, p < .001). But baseline (p = .668) and follow-up (p = .278) cavity wall thickness was not different between two groups. In univariate analysis, initial maximum diameter of cavity (p = .028; HR [0.983], 95% CI [0.967-0.998]) and concurrent NTM infection (p = .030; HR [0.20], 95% CI [0.05-0.86]) were related factors for poor clinical response. CONCLUSIONS: With antifungal therapy, cavities demonstrate wall thinning. Of all clinical and radiological findings and their changes, initial large cavity size and concurrent presence of NTM infection are related factors to poor response to antifungal therapy.

Acute Pulmonary Embolism and Chronic Thromboembolic Pulmonary Hypertension: Clinical and Serial CT Pulmonary Angiographic Features.

In acute pulmonary embolism (PE), circulatory failure and systemic hypotension are important clinically for predicting poor prognosis. While pulmonary artery (PA) clot loads can be an indicator of the severity of current episode of PE or treatment effectiveness, they may not be used directly as an indicator of right ventricular (RV) failure or patient death. In other words, pulmonary vascular resistance or patient prognosis may not be determined only with mechanical obstruction of PAs and their branches by intravascular clot loads on computed tomography pulmonary angiography (CTPA), but determined also with vasoactive amines, reflex PA vasoconstriction, and systemic arterial hypoxemia occurring during acute PE. Large RV diameter with RV/left ventricle (LV) ratio > 1.0 and/or the presence of occlusive clot and pulmonary infarction on initial CTPA, and clinically determined high baseline PA pressure and RV dysfunction are independent predictors of oncoming chronic thromboembolic pulmonary hypertension (CTEPH). In this pictorial review, authors aimed to demonstrate clinical and serial CTPA features in patients with acute massive and submassive PE and to disclose acute CTPA and clinical features that are related to the prediction of oncoming CTEPH.

Improving generalization performance of electrocardiogram classification models.

Objective.Recently, many electrocardiogram (ECG) classification algorithms using deep learning have been proposed. Because the ECG characteristics vary across datasets owing to variations in factors such as recorded hospitals and the race of participants, the model needs to have a consistently high generalization performance across datasets. In this study, as part of the PhysioNet/Computing in Cardiology Challenge (PhysioNet Challenge) 2021, we present a model to classify cardiac abnormalities from the 12- and the reduced-lead ECGs.Approach.To improve the generalization performance of our earlier proposed model, we adopted a practical suite of techniques, i.e. constant-weighted cross-entropy loss, additional features, mixup augmentation, squeeze/excitation block, and OneCycle learning rate scheduler. We evaluated its generalization performance using the leave-one-dataset-out cross-validation setting. Furthermore, we demonstrate that the knowledge distillation from the 12-lead and large-teacher models improved the performance of the reduced-lead and small-student models.Main results.With the proposed model, our DSAIL SNU team has received Challenge scores of 0.55, 0.58, 0.58, 0.57, and 0.57 (ranked 2nd, 1st, 1st, 2nd, and 2nd of 39 teams) for the 12-, 6-, 4-, 3-, and 2-lead versions of the hidden test set, respectively.Significance.The proposed model achieved a higher generalization performance over six different hidden test datasets than the one we submitted to the PhysioNet Challenge 2020.

CNN-based Two Step R Peak Detection Method: Combining Segmentation and Regression.

For semantic segmentation, U-Net provides an end-to-end trainable framework to detect multiple class objects from background. Due to its great achievements in computer vision tasks, U-Net has broadened its application to biomedical signal processing, especially, segmentation of waveforms in ECG signal. Despite its superior performance for QRS complex detection to other traditional signal processing methods, direct application of the U-Net to R peak detection has limitation since the U-Net structures tend to predict high probability around true peak. Such multiple detection results require additional process to determine a unique peak location in each QRS complex. In this study, we use a regression process to detect R peak instead of pixel-wise classification. Such regression process guarantees a unique peak location prediction. We collect data from resting ECG systems and wearable ECG devices as well as public ECG databases and the proposed model is trained on various combinations of the data sources. Especially, we investigate the robustness of the model for input data from the wearable devices when the model is trained by data from heterogeneous devices.

Study on the use of standard 12-lead ECG data for rhythm-type ECG classification problems.

BACKGROUND AND OBJECTIVES: Most deep-learning-related methodologies for electrocardiogram (ECG) classification are focused on finding an optimal deep-learning architecture to improve classification performance. However, in this study, we proposed a methodology for fusion of various single-lead ECG data as training data in the single-lead ECG classification problem. METHODS: We used a squeeze-and-excitation residual network (SE-ResNet) with 152 layers as the baseline model. We compared the performance of a 152-layer SE-ResNet trained on ECG signals from various leads of a standard 12-lead ECG system to that of a 152-layer SE-ResNet trained on only single-lead ECG data with the same lead information as the test set. The experiments were performed using five different types of rhythm-type single-lead ECG data obtained from Konkuk University Hospital in South Korea. RESULTS: Experiment results based on the combination from the relationship experiments of the leads showed that lead -aVR or II revealed the best classification performance. In case of -aVR, this model achieved a high F1 score for normal (98.7%), AF (98.2%), APC (95.1%), and VPC (97.4%), indicating its potential for practical use in the medical field. CONCLUSION: We concluded that the 152-layer SE-ResNet trained by fusion of single-lead ECGs had better classification performance than the 152-layer SE-ResNet trained on only single-lead ECG data, regardless of the single-lead ECG signal type. We also found that the best performance directions for single-lead ECG classification are Lead -aVR and II.