Radiological Cardiothoracic Ratio in Evidence-Based Medicine

Computer-aided assessment for enlarged fetal heart with deep learning model

Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learning approach using the You Only Look Once (YOLO) architecture to automate fetal heart enlargement assessment. Using a set of ultrasound videos, YOLOv8 with a CBAM module demonstrated superior performance compared to YOLOv11 with self-attention. Incorporating the ResNeXtBlock-a residual network with cardinality-additionally enhanced accuracy and prediction consistency. The model exhibits strong capability in detecting fetal heart enlargement, offering a reliable computer-aided tool for sonographers during prenatal screenings. Further validation is required to confirm its clinical applicability. By improving early and accurate detection, this approach has the potential to enhance prenatal care, facilitate timely interventions, and contribute to better neonatal health outcomes.

Designing a computer-assisted diagnosis system for cardiomegaly detection and radiology report generation

Chest X-ray (CXR) is a diagnostic tool for cardiothoracic assessment. They make up 50% of all diagnostic imaging tests. With hundreds of images examined every day, radiologists can suffer from fatigue. This fatigue may reduce diagnostic accuracy and slow down report generation. We describe a prototype computer-assisted diagnosis (CAD) pipeline employing computer vision (CV) and Natural Language Processing (NLP). It was trained and evaluated on the publicly available MIMIC-CXR dataset. We perform image quality assessment, view labelling, and segmentation-based cardiomegaly severity classification. We use the output of the severity classification for large language model-based report generation. Four board-certified radiologists assessed the output accuracy of our CAD pipeline. Across the dataset composed of 377,100 CXR images and 227,827 free-text radiology reports, our system identified 0.18% of cases with mixed-sex mentions, 0.02% of poor quality images (F1 = 0.81), and 0.28% of wrongly labelled views (accuracy 99.4%). We assigned views for 4.18% of images which have unlabelled views. Our binary cardiomegaly classification model has 95.2% accuracy. The inter-radiologist agreement on evaluating the generated report's semantics and correctness for radiologist-MIMIC is 0.62 (strict agreement) and 0.85 (relaxed agreement) similar to the radiologist-CAD agreement of 0.55 (strict) and 0.93 (relaxed). Our work found and corrected several incorrect or missing metadata annotations for the MIMIC-CXR dataset. The performance of our CAD system suggests performance on par with human radiologists. Future improvements revolve around improved text generation and the development of CV tools for other diseases.

Association between the Cardiothoracic Ratio on Chest X-rays and the Respiratory Function in Patients with Interstitial Lung Diseases: a Cross-sectional Study

Objective Patients with advanced interstitial lung disease (ILD) struggle to undergo spirometry to evaluate the respiratory function. The cardiothoracic ratio (CTR) on chest radiography can potentially reflect the lung volume; however, this has not yet been fully established. This study aimed to clarify the relationship between the CTR and the respiratory function in patients with interstitial lung diseases. Methods We reviewed 120 consecutive patients with idiopathic interstitial lung disease who were admitted to our department between April 2018 and March 2023 and who underwent chest radiography, spirometry, and echocardiography. A multiple linear regression analysis was used to identify the factors associated with the CTR. Correlations between the CTR and the respiratory or cardiac function were assessed using Pearson's correlation coefficient. Results A multiple linear regression analysis showed the percent vital capacity (β= -0.598, p<0.001), age (β=0.405, p<0.001), and female sex (β=0.177, p=0.047) to be independently associated with the CTR, whereas no relationship was observed between the left ventricular ejection fraction, body mass index, and smoking habits. The CTR was significantly negatively correlated with the vital capacity (r=-0.490, p<0.001). Conclusion An increased CTR might reflect a decreased vital capacity, but not a decreased cardiac function, in patients with interstitial lung diseases. Measuring the CTR can thus be beneficial for predicting progression in patients with ILD.

New parameter for QRS complex low voltage in chagasic cardiomyopathy: the ADOC index

BACKGROUND

Low QRS complex voltage is an important predictor of death in Chagas disease. However, the parameters applied to the low-voltage classification were described by the Minnesota Code and not specifically for Chagas disease. This study aimed to analyze low QRS voltage by determining the ADOC index and averages in the frontal and horizontal electrocardiographic planes, establishing possible clinical implications.

METHODS

A cross-sectional study of patients with Chagas disease was performed using the Mann-Whitney U test and Spearman's correlation. The amplitudes of each QRS were analyzed, and the sum of the DII and V5 derivations of the ADOC index and the arithmetic means of the QRS complexes in the frontal and horizontal planes were determined.

RESULTS

The ADOC index was correlated with the highest risk of stroke and death according to the Rassi score. The ADOC index (p=0.046) and mean mQRS were inversely proportional to the Rassi risk of death score (p=0.038). The ADOC index proved to be more sensitive (75.0%) and accurate (67.4%) in identifying patients at elevated death risk using the Rassi score. Finally, a positive correlation was observed between the QRSFm and QRSHm indicators and ADOC index (r=0.590 and r=0.857, respectively).

DISCUSSION

The ADOC index and mean of the QRS complexes are possible tools correlated with the Rassi score and risk of stroke in patients with Chagas disease.

Minimally invasive coronary artery bypass grafting via left anterior minithoracotomy: Setup, results, and evolution of a new surgical procedure

Objective

Minimally invasive total arterial coronary artery bypass grafting offers the advantages of total arterial revascularization through an anterolateral minithoracotomy. However, the procedure is technically challenging and associated with a learning curve. The purpose of our study was to evaluate the progress and development of our program over an 8-year period.

Methods

We collected prospective data on all patients who underwent procedure at our institution from January 2015 to December 2023. Our program underwent several modifications during this study period, including optimization of surgical exposure using various available instruments, efficient intraoperative time management, utilization of a standard technique for all off-pump coronary artery bypass procedures, and close team member mentoring. Changes in quality control consisted of transitioning from routine postoperative coronary imaging to clinically indicated imaging. The influence of these interventions was assessed by focusing on in-hospital mortality as the primary end point, and operative time and perioperative myocardial infarction as secondary end points, over 2 time periods consisting of patients operated on during the first and second 4-year study period (Group 1, n = 137 and Group 2, n = 142).

Results

A total of 279 consecutive patients underwent elective, total arterial minimally invasive total arterial coronary artery bypass grafting at our institution over the study period. The mean age of patients was 66 ± 7 years, with 86% being men (n = 241) and 33.1% having diabetes (n = 77). Triple vessel disease was present in 53% of the cohort (n = 123) and left main disease was prevalent in 43% of patients (n = 101). The overall 30-day mortality was 0.4% (n = 1). Compared with the initial 4-year period, the rate of perioperative myocardial infarction decreased 3-fold (4.3% vs 1.4%; P = .1) and there was a statistically significant reduction in operating time (275 ± 59.5 and 246 ± 72.6 minutes; P < .001) in the most recent group of patients.

Conclusions

Total arterial minimally invasive total arterial coronary artery bypass grafting is a feasible surgical approach that can be performed with very good results, even during the initial learning curve phase. An evolving educational program can provide a smooth transition from off-pump coronary artery bypass grafting to minimally invasive total arterial coronary artery bypass grafting, when performed in selected patients in high-volume cardiac centers.

Microcardia and cardiomegaly screening using postero-anterior chest X-ray (PA CXR) across university students in Ghana - a retrospective study

BACKGROUND

Microcardia and cardiomegaly are good diagnostic and prognostic tools for several diseases. This study investigated the distribution of microcardia and cardiomegaly among students of the University of Health and Allied Sciences (UHAS) in Ghana to determine the prevalence of microcardia and cardiomegaly across gender, and to evaluate the correlation between the presence of these heart conditions and age.

METHODS

This retrospective study involved a review of 4519 postero-anterior (PA) chest X-rays (CXRs) between 2020 and 2023. The CXRs were taken using a digital radiography machine. The CXRs were obtained on PA projection, with the students upright, on arrested inspiration and a source-to-detector distance of 180 cm. Only CXR images with no significant rotation (assessed using the distance between the medial ends of the clavicles and the vertebral spinous processes) and lung abnormalities were included in the study. The transverse cardiac diameter (TCD) and transverse thoracic diameter (TTD) were measured and cardiothoracic ratio (CTR) calculated for each CXR. The CTR was calculated as a ratio of TCD/TTD and categorised as microcardia (CTR < 0.42), normal heart size (0.42 < CTR ≤ 0.50) and cardiomegaly (0.50 < CTR ≤ 0.60). The data was analysed using the Statistical Package for the Social Sciences (SPSS) version 26 and descriptive and inferential statistics were conducted. The Mann-Whitney U Test was conducted to determine statistically significant differences in TCD, TTD and CTR across female and male students. Spearman's rho correlation was conducted to investigate the relationships between age and TCD, TTD and CTR.

RESULTS

The students were aged 15-37 years (mean = 19.60 ± 2.20) with a modal age of 18 years. The study included 2930 (64.84%) females and 1589 (35.16%) males. Most of the students [3384 (74.88%)] had normal heart sizes. However, 647 (14.32%) had microcardia whereas 488 (10.80%) had cardiomegaly. Out of the students suffering from cardiomegaly, 478 (97.95%) and 10 (2.05%) had mild/moderate and severe cardiomegaly respectively. Cardiomegaly was more common among the female students (p < 0.05) and those aged 15-22 years [418 (85.66%)]. There was no correlation between TCD, TTD and CTR and age [ r = 0.01, p = 0.42; r = 0.02, p = 0.17; r = 0.01, p = 0.66, respectively].

CONCLUSION

The majority of the students had normal heart sizes, but a few had microcardia and cardiomegaly. Cardiomegaly was more common among the female students. The presence of microcardia and cardiomegaly could have health implications for the students and increase their risks of cardiovascular diseases hence these students should be further screened medically for the underlying causes though they may be asymptomatic. Stakeholders in higher education and public health may find this study useful in developing strategies to minimise the prevalence of cardiac diseases and also improve treatment.

Preoperative anatomical landmarks and longitudinal HeartMate 3 pump position in X-rays: Relevance for adverse events

BACKGROUND

Left ventricular assist device (LVAD) malposition has been linked to hemocompatibility-related adverse events (HRAEs). This study aimed to identify preoperative anatomical landmarks and postoperative pump position, associated with HRAEs during LVAD support.

METHODS

Pre- and postoperative chest X-ray measures (≤14 days pre-implantation, first postoperative standing, 6, 12, 18, and 24 months post-implantation) were analyzed for their association with HRAEs over 24 months in 33 HeartMate 3 (HM3) patients (15.2% female, age 66 (9.5) years).

RESULTS

HM3 patients with any HRAE showed significantly lower preoperative distances between left ventricle and thoracic outline (dLVT) (25.3 ± 10.2 mm vs. 40.3 ± 15.5 mm, p = 0.004). A ROC-derived cutoff dLVT ≤ 29.2 mm provided 85.7% sensitivity and 72.2% specificity predicting any HRAE during HM3 support (76.2% (>29.2 mm) vs. 16.7% (≤29.2 mm) freedom from HRAE, p < 0.001) and significant differences in cardiothoracic ratio (0.58 ± 0.04 vs. 0.62 ± 0.04, p = 0.045). Postoperative X-rays indicated lower pump depths in patients with ischemic strokes (9.1 ± 16.2 mm vs. 38.0 ± 18.5 mm, p = 0.007), reduced freedom from any neurological event (pump depth ≤ 28.7 mm: 45.5% vs. 94.1%, p = 0.004), and a significant correlation between pump depth and inflow cannula angle (r = 0.66, p < 0.001). Longitudinal changes were observed in heart-pump width (F(4,60) = 5.61, p < 0.001).

CONCLUSION

Preoperative X-ray markers are associated with postoperative HRAE occurrence. Applying this knowledge in clinical practice may enhance risk stratification, guide therapy optimization, and improve HM3 recipient management.

RADIOGRAPHIC MEASUREMENT OF CARDIAC SIZE BY USING MULTIPLE SCALING SYSTEMS IN HEALTHY CAPTIVE AYE-AYES (DAUBENTONIA MADAGASCARIENSIS)

The aye-aye (Daubentonia madagascariensis) is an unusual lemur with a small population in human care. Cardiac pathologies, but not normal size parameters, have been reported in this species. This study aimed to determine whether radiographic cardiac scaling systems commonly used to evaluate heart size in domestic mammals have potential clinical application in aye-ayes. Selected cardiac silhouette, vertebral, and intrathoracic skeletal dimensions were measured retrospectively on paired sets of orthogonal thoracic radiographs collected during health examinations of aye-ayes maintained at three British zoos. Measurements from 21 healthy aye-ayes (10 males, 11 females) of varying ages were used to calculate reference intervals (RI) with 90% confidence intervals for vertebral heart scale in both right lateral (VHS-RLat) and ventrodorsal (VHS-VD) projections, a modified VHS (VHS-Mod), thoracic inlet heart size (TIHS), and cardiothoracic ratio (CTR). VHS-VD (9.49 ± 0.29) was slightly higher than VHS-RLat (9.32 ± 0.33; P = 0.08) and had the lowest coefficient of variation of the scaling indices; TIHS was 4.89 ± 0.36, VHS-Mod was 11.07 ± 0.49, and CTR was 0.53 ± 0.05. Thoracic depth-to-width ratio of aye-ayes ranged between 0.75 and 0.91, equivalent to an intermediate thoracic morphology in dogs. No scaling indices differed significantly by sex, age group, or thoracic morphology; however, VHS-Mod and CTR were significantly correlated with bodyweight (P = 0.0022 and P = 0.041, respectively) and CTR with age (P = 0.02). Summed cardiac dimensions demonstrated a near-linear relationship with bodyweight and T4 vertebral length (both P < 0.05), but not thoracic inlet length (P = 0.12). Analysis of measurements by using serial radiographs from hand-reared animals indicated potential utility of RI in aye-ayes >0.4 yr. Overall, results suggest VHS-VD and VHS-RLat are preferred cardiac scaling indices in aye-ayes. These data will aid zoo clinicians in the evaluation of cardiac size and identification of cardiomegaly in this endangered primate.

Deep learning prediction of survival in patients with heart failure using chest radiographs

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

Measurement of Cardiothoracic Ratio on Chest X-rays Using Artificial Intelligence-A Systematic Review and Meta-Analysis

Background: Chest X-rays (CXRs) are pivotal in clinical diagnostics, particularly in assessing cardiomegaly through the cardiothoracic ratio (CTR). This systematic review and meta-analysis evaluate the efficacy of artificial intelligence (AI) in automating CTR determination to enhance patient care and streamline diagnostic processes. They are concentrated on comparing the performance of AI models in determining the CTR against human assessments, identifying the most effective models for potential clinical implementation. This study was registered with PROSPERO (no. CRD42023437459). No funding was received. Methods: A comprehensive search of medical databases was conducted in June 2023. The search strategy adhered to the PICO framework. Inclusion criteria encompassed original articles from the last decade focusing on AI-assisted CTR assessment from standing-position CXRs. Exclusion criteria included systematic reviews, meta-analyses, conference abstracts, paediatric studies, non-original articles, and studies using imaging techniques other than X-rays. After initial screening, 117 articles were reviewed, with 14 studies meeting the final inclusion criteria. Data extraction was performed by three independent investigators, and quality assessment followed PRISMA 2020 guidelines, using tools such as the JBI Checklist, AMSTAR 2, and CASP Diagnostic Study Checklist. Risk of bias was assessed according to the Cochrane Handbook guidelines. Results: Fourteen studies, comprising a total of 70,472 CXR images, met the inclusion criteria. Various AI models were evaluated, with differences in dataset characteristics and AI technology used. Common preprocessing techniques included resizing and normalization. The pooled AUC for cardiomegaly detection was 0.959 (95% CI 0.944-0.975). The pooled standardized mean difference for CTR measurement was 0.0353 (95% CI 0.147-0.0760). Significant heterogeneity was found between studies (I2 89.97%, p < 0.0001), with no publication bias detected. Conclusions: Standardizing methodologies is crucial to avoid interpretational errors and advance AI in medical imaging diagnostics. Uniform reporting standards are essential for the further development of AI in CTR measurement and broader medical imaging applications.

Clinical domain knowledge-derived template improves post hoc AI explanations in pneumothorax classification

OBJECTIVE

Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement.

METHOD

We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of the explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det).

RESULTS

The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach.

CONCLUSIONS

In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.

Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection

Objectives: The purpose of this study is to evaluate the performance of our deep learning algorithm in calculating cardiothoracic ratio (CTR) and thus in the assessment of cardiomegaly or pericardial effusion occurrences on chest radiography (CXR). Methods: From a database of 8000 CXRs, 13 folders with a comparable number of images were created. Then, 1020 images were chosen randomly, in proportion to the number of images in each folder. Afterward, CTR was calculated using RadiAnt Digital Imaging and Communications in Medicine (DICOM) Viewer software (2023.1). Next, heart and lung anatomical areas were marked in 3D Slicer. From these data, we trained an AI model which segmented heart and lung anatomy and determined the CTR value. Results: Our model achieved an Intersection over Union metric of 88.28% for the augmented training subset and 83.06% for the validation subset. F1-score for subsets were accordingly 90.22% and 90.67%. In the comparative analysis of artificial intelligence (AI) vs. humans, significantly lower transverse thoracic diameter (TTD) (p < 0.001), transverse cardiac diameter (TCD) (p < 0.001), and CTR (p < 0.001) values obtained using the neural network were observed. Conclusions: Results confirm that there is a significant correlation between the measurements made by human observers and the neural network. After validation in clinical conditions, our method may be used as a screening test or advisory tool when a specialist is not available, especially on Intensive Care Units (ICUs) or Emergency Departments (ERs) where time plays a key role.

Evaluation of cardiothoracic ratio as a potential predictor of cardiovascular abnormalities in individuals with type II diabetes mellitus: a case-control study

Cardiovascular complications represent a significant health concern for individuals with diabetes mellitus. The relationship between diabetes and cardiovascular diseases is complex and multifaceted, involving a variety of pathophysiological mechanisms. This study aimed to investigate the potential role of the cardiothoracic ratio as a prognostic tool for cardiovascular disorders in patients with diabetes. A retrospective case-control study of 530 adult patients referred to a tertiary care hospital in Saudi Arabia was conducted. Medical records, including chest X-rays, were analyzed to determine the cardiothoracic ratio. Patients diagnosed with diabetes who experienced cardiac disorders had significantly higher cardiothoracic ratios compared to patients with diabetes alone and controls. HbA1c was significantly elevated among patients with diabetes and cardiovascular disorders (mean = 71.5 ± 25.43 mmol/mol) compared to the other patients. There was a significant positive correlation between the duration of diabetes and the cardiothoracic ratio (r = 0.64, P < 0.001). Furthermore, the cardiothoracic ratio above 0.51 was a good discriminator of cardiovascular disorders in patients with diabetes, with an area under the curve of 0.737, sensitivity of 97.1%, and specificity of 87.2%. This study provided comprehensive evidence supporting the association between cardiothoracic ratio and subsequent cardiovascular adverse outcomes in patients with diabetes. We recommend adopting the cardiothoracic ratio as a valuable prognostic tool for risk stratification among people with diabetes.

Utility of Recipient Cardiothoracic Ratio in Predicting Delayed Chest Closure after Heart Transplantation

BACKGROUND

 Predicted cardiac mass (PCM) has been well validated for size matching donor hearts to heart transplantation recipients. We hypothesized that cardiothoracic ratio (CTR) could be reflective of recipient-specific limits of oversizing, and sought to determine the utility of donor to recipient PCM ratio (PCMR) and CTR in predicting delayed chest closure after heart transplantation.

METHODS

 A retrospective review of prospectively collected data on 38 consecutive heart transplantations performed at our institution from 2017 to 2020 was performed. Donor and recipient PCM were estimated using Multi-Ethnic Study of Atherosclerosis predictive models. Receiver operating characteristic analysis was performed to determine the discriminatory power of the ratio of PCMR to CTR in predicting delayed sternal closure.

RESULTS

 Of the 38 patients, 71.1% (27/38) were male and the median age at transplantation was 58 (interquartile range [IQR]: 47-62) years. Ischemic cardiomyopathy was present in 31.6% of recipients (12/38). Median recipient CTR was 0.63 [IQR: 0.59-0.66]. Median donor to recipient PCMR was 1.07 [IQR: 0.96-1.19], which indicated 7% oversizing. Thirteen out of 38 (34.2%) underwent delayed sternal closure. Primary graft dysfunction occurred in 15.8% (6/38). PCMR/CTR showed good discriminatory power in predicting delayed sternal closure [area under the curve: 80.4% (65.3-95.6%)]. PCMR/CTR cut-off of 1.7 offered the best trade-off between the sensitivity (69.6%) and specificity (91.7%).

CONCLUSION

 CTR could be helpful in guiding the recipient-specific extent of oversizing donor hearts. Maintaining the ratio of PCMR to CTR below 1.7 could avoid excessive oversizing of the donor heart.

Diagnostic value of cardiothoracic ratio in patients with non-ischaemic cardiomyopathy: comparison to cardiovascular magnetic resonance imaging

PURPOSE

To determine the reliability of the cardiothoracic ratio (CTR) as a simple method to assess the cardiac size and function in patients with non-ischemic cardiomyopathy (NICM).

METHODS

In a sample of 91 patients (66 patients with diagnosed non-ischemic cardiomyopathy and 25 controls) we calculated the CTR on a posteroanterior chest radiograph and ventricular and atrial size based on accepted cardiovascular magnetic resonance (CMR) imaging values. Left and right ventricular ejection fraction was also calculated. The CTR and cardiac chamber size were compared between patients with NICM and healthy individuals. The distinction between normal and increased cardiac chamber size was made using published normal CMR reference values stratified by age and gender.

RESULTS

CTR values were higher in the NICM group (50.7±5.5 % Vs. 45.3±4.7 %, p<0.001). Likewise, LVEDVi, LV indexed mass, LA indexed volume, LA indexed area, and RA indexed area were higher, and LVEF and RVEF were lower in patients with non-ischemic cardiomyopathy (p < 0.05). In patients with non-ischemic cardiomyopathy, the greatest correlation between CTR and CMR values was with LVEDVi (ρ=0.4, p < 0.001), LA indexed volume (ρ=0.5, p < 0.001), LA indexed area (ρ=0.5, p < 0.001) and RA indexed area (ρ=0.4, p < 0.001). However, the correlation strength was only moderate.

CONCLUSION

Despite patients with NICM had higher CTR values than the control group, a substantial proportion of these patients showed normal CTRs (<50 %). This fact limits the usefulness of CTR to reliably predict NICM. Correlation between CTR and heart chamber dilation on CMR was only weak to moderate.

Correlations of sST2 and Gal-3 with Cardiothoracic Ratio in Patients with Chronic Kidney Disease

Chronic kidney disease (CKD) frequently correlates with cardiovascular complications. Soluble suppression of tumorigenicity 2 (sST2) and Galectin-3 (Gal-3) are emerging as cardiac markers with potential relevance in cardiovascular risk prediction. The cardiothoracic ratio (CTR), a metric easily obtainable from chest radiographs, has traditionally been used to assess cardiac size and the potential for cardiomegaly. Understanding the correlation between these cardiac markers and the cardiothoracic ratio (CTR) could provide valuable insights into the cardiovascular prognosis of CKD patients. This study aimed to explore the relationship between sST2, Gal-3, and the CTR in individuals with CKD. Plasma concentrations of sST2 and Gal-3 were assessed in a cohort of 123 CKD patients by enzyme-linked immunosorbent assay (ELISA). On a posterior-to-anterior chest X-ray view, the CTR was determined by comparing the widths of the heart to that of the thorax. The mean concentration of sST2 in the study participants ranged from 775.4 to 4475.6 pg/mL, and the mean concentration of Gal-3 ranged from 4.7 to 9796.0 ng/mL. Significant positive correlations were observed between sST2 and the CTR (r = 0.291, p < 0.001) and between Gal-3 and the CTR (r = 0.230, p < 0.01). Our findings indicate that elevated levels of sST2 and Gal-3 are associated with an increased CTR in CKD patients. This relationship may enable better cardiovascular risk evaluation for CKD patients. Further studies are warranted to explore the clinical implications of these associations.

Beat-to-beat alterations of acoustic intensity and frequency at the maximum power of heart sounds are associated with NT-proBNP levels

Background

Auscultatory features of heart sounds (HS) in patients with heart failure (HF) have been studied intensively. Recent developments in digital and electrical devices for auscultation provided easy listening chances to recognize peculiar sounds related to diastolic HS such as S3 or S4. This study aimed to quantitatively assess HS by acoustic measures of intensity (dB) and audio frequency (Hz).

Methods

Forty consecutive patients aged between 46 and 87 years (mean age, 74 years) with chronic cardiovascular disease (CVD) were enrolled in the present study after providing written informed consent during their visits to the Kitasato University Outpatient Clinic. HS were recorded at the fourth intercostal space along the left sternal border using a highly sensitive digital device. Two consecutive heartbeats were quantified on sound intensity (dB) and audio frequency (Hz) at the peak power of each spectrogram of S1-S4 using audio editing and recording application software. The participants were classified into three groups, namely, the absence of HF (n = 27), HF (n = 8), and high-risk HF (n = 5), based on the levels of NT-proBNP < 300, ≥300, and ≥900 pg/ml, respectively, and also the levels of ejection fraction (EF), such as preserved EF (n = 22), mildly reduced EF (n = 12), and reduced EF (n = 6).

Results

The intensities of four components of HS (S1-S4) decreased linearly (p < 0.02-0.001) with levels of body mass index (BMI) (range, 16.2-33.0 kg/m2). Differences in S1 intensity (ΔS1) and its frequency (ΔfS1) between two consecutive beats were non-audible level and were larger in patients with HF than those in patients without HF (ΔS1, r = 0.356, p = 0.024; ΔfS1, r = 0.356, p = 0.024). The cutoff values of ΔS1 and ΔfS1 for discriminating the presence of high-risk HF were 4.0 dB and 5.0 Hz, respectively.

Conclusions

Despite significant attenuations of all four components of HS by BMI, beat-to-beat alterations of both intensity and frequency of S1 were associated with the severity of HF. Acoustic quantification of HS enabled analyses of sounds below the audible level, suggesting that sound analysis might provide an early sign of HF.

Deep learning-based cardiothoracic ratio measurement on chest radiograph: accuracy improvement without self-annotation

Background

A reproducible and accurate automated approach to measuring cardiothoracic ratio on chest radiographs is warranted. This study aimed to develop a deep learning-based model for estimating the cardiothoracic ratio on chest radiographs without requiring self-annotation and to compare its results with those of manual measurements.

Methods

The U-net architecture was designed to segment the right and left lungs and the cardiac shadow, from chest radiographs. The cardiothoracic ratio was then calculated using these labels by a mathematical algorithm. The initial model of deep learning-based cardiothoracic ratio measurement was developed using open-source 247 chest radiographs that had already been annotated. The advanced model was developed using a training dataset of 729 original chest radiographs, the labels of which were generated by the initial model and then screened. The cardiothoracic ratio of the two models was estimated in an independent test set of 120 original cases, and the results were compared to those obtained through manual measurement by four radiologists and the image-reading reports.

Results

The means and standard deviations of the cardiothoracic ratio were 52.4% and 9.8% for the initial model, 51.0% and 9.3% for the advanced model, and 49.8% and 9.4% for the total of four manual measurements, respectively. The intraclass correlation coefficients (ICCs) of the cardiothoracic ratio ranged from 0.91 to 0.93 between the advanced model and the manual measurements, whereas those for the initial model and the manual measurements ranged from 0.77 to 0.82.

Conclusions

Deep learning-based cardiothoracic ratio estimation on chest radiographs correlated favorably with the results obtained through manual measurements by radiologists. When the model was trained on additional local images generated by the initial model, the correlation with manual measurement improved even more than the initial model alone.

The Performance of a Deep Learning-Based Automatic Measurement Model for Measuring the Cardiothoracic Ratio on Chest Radiographs

OBJECTIVE

Prior studies on models based on deep learning (DL) and measuring the cardiothoracic ratio (CTR) on chest radiographs have lacked rigorous agreement analyses with radiologists or reader tests. We validated the performance of a commercially available DL-based CTR measurement model with various thoracic pathologies, and performed agreement analyses with thoracic radiologists and reader tests using a probabilistic-based reference.

MATERIALS AND METHODS

This study included 160 posteroanterior view chest radiographs (no lung or pleural abnormalities, pneumothorax, pleural effusion, consolidation, and n = 40 in each category) to externally test a DL-based CTR measurement model. To assess the agreement between the model and experts, intraclass or interclass correlation coefficients (ICCs) were compared between the model and two thoracic radiologists. In the reader tests with a probabilistic-based reference standard (Dawid-Skene consensus), we compared diagnostic measures-including sensitivity and negative predictive value (NPV)-for cardiomegaly between the model and five other radiologists using the non-inferiority test.

RESULTS

For the 160 chest radiographs, the model measured a median CTR of 0.521 (interquartile range, 0.446-0.59) and a mean CTR of 0.522 ± 0.095. The ICC between the two thoracic radiologists and between the model and two thoracic radiologists was not significantly different (0.972 versus 0.959, p = 0.192), even across various pathologies (all p-values > 0.05). The model showed non-inferior diagnostic performance, including sensitivity (96.3% versus 97.8%) and NPV (95.6% versus 97.4%) (p < 0.001 in both), compared with the radiologists for all 160 chest radiographs. However, it showed inferior sensitivity in chest radiographs with consolidation (95.5% versus 99.9%; p = 0.082) and NPV in chest radiographs with pleural effusion (92.9% versus 94.6%; p = 0.079) and consolidation (94.1% versus 98.7%; p = 0.173).

CONCLUSION

While the sensitivity and NPV of this model for diagnosing cardiomegaly in chest radiographs with consolidation or pleural effusion were not as high as those of the radiologists, it demonstrated good agreement with the thoracic radiologists in measuring the CTR across various pathologies.

Hybrid Classical-Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays

Cardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication. Based on pre-trained DenseNet-121, we designed hybrid classical-quantum (CQ) transfer learning models to detect cardiomegaly in CXRs. Using Qiskit and PennyLane, we integrated a parameterized quantum circuit into a classic network implemented in PyTorch. We mined the CheXpert public repository to create a balanced dataset with 2436 posteroanterior CXRs from different patients distributed between cardiomegaly and the control. Using k-fold cross-validation, the CQ models were trained using a state vector simulator. The normalized global effective dimension allowed us to compare the trainability in the CQ models run on Qiskit. For prediction, ROC AUC scores up to 0.93 and accuracies up to 0.87 were achieved for several CQ models, rivaling the classical-classical (CC) model used as a reference. A trustworthy Grad-CAM++ heatmap with a hot zone covering the heart was visualized more often with the QC option than that with the CC option (94% vs. 61%, p < 0.001), which may boost the rate of acceptance by health professionals.

Validation of an Automated Cardiothoracic Ratio Calculation for Hemodialysis Patients

Cardiomegaly is associated with poor clinical outcomes and is assessed by routine monitoring of the cardiothoracic ratio (CTR) from chest X-rays (CXRs). Judgment of the margins of the heart and lungs is subjective and may vary between different operators.

METHODS

Patients aged > 19 years in our hemodialysis unit from March 2021 to October 2021 were enrolled. The borders of the lungs and heart on CXRs were labeled by two nephrologists as the ground truth (nephrologist-defined mask). We implemented AlbuNet-34, a U-Net variant, to predict the heart and lung margins from CXR images and to automatically calculate the CTRs.

RESULTS

The coefficient of determination (R²) obtained using the neural network model was 0.96, compared with an R² of 0.90 obtained by nurse practitioners. The mean difference between the CTRs calculated by the nurse practitioners and senior nephrologists was 1.52 ± 1.46%, and that between the neural network model and the nephrologists was 0.83 ± 0.87% (p < 0.001). The mean CTR calculation duration was 85 s using the manual method and less than 2 s using the automated method (p < 0.001).

CONCLUSIONS

Our study confirmed the validity of automated CTR calculations. By achieving high accuracy and saving time, our model can be implemented in clinical practice.

Cardiothoracic ratio values and trajectories are associated with risk of requiring dialysis and mortality in chronic kidney disease

BACKGROUND

The prognostic role of the cardiothoracic ratio (CTR) in chronic kidney disease (CKD) remains undetermined.

METHODS

We conducted a retrospective cohort study of 3117 patients with CKD aged 18-89 years who participated in an Advanced CKD Care Program in Taiwan between 2003 and 2017 with a median follow up of 1.3(0.7-2.5) and 3.3(1.8-5.3) (IQR) years for outcome of end-stage renal disease (ESRD) and overall death, respectively. We developed a machine learning (ML)-based algorithm to calculate the baseline and serial CTRs, which were then used to classify patients into trajectory groups based on latent class mixed modelling. Association and discrimination were evaluated using multivariable Cox proportional hazards regression analyses and C-statistics, respectively.

RESULTS

The median (interquartile range) age of 3117 patients is 69.5 (59.2-77.4) years. We create 3 CTR trajectory groups (low [30.1%], medium [48.1%], and high [21.8%]) for the 2474 patients with at least 2 CTR measurements. The adjusted hazard ratios for ESRD, cardiovascular mortality, and all-cause mortality in patients with baseline CTRs ≥0.57 (vs CTRs <0.47) are 1.35 (95% confidence interval, 1.06-1.72), 2.89 (1.78-4.71), and 1.50 (1.22-1.83), respectively. Similarly, greater effect sizes, particularly for cardiovascular mortality, are observed for high (vs low) CTR trajectories. Compared with a reference model, one with CTR as a continuous variable yields significantly higher C-statistics of 0.719 (vs 0.698, P = 0.04) for cardiovascular mortality and 0.697 (vs 0.693, P < 0.001) for all-cause mortality.

CONCLUSIONS

Our findings support the real-world prognostic value of the CTR, as calculated by a ML annotation tool, in CKD. Our research presents a methodological foundation for using machine learning to improve cardioprotection among patients with CKD.

Combined cardiomegaly and aortic arch calcification predict mortality in hemodialysis patients

INTRODUCTION

This study aimed to investigate the relationship between cardiomegaly and aortic arch calcification (AAC) and overall/cardiovascular mortality in hemodialysis patients.

METHODS

We conducted a retrospective cohort study and enrolled patients who underwent initial hemodialysis. Cardiomegaly and AAC were determined by chest radiography and classified into four groups according to cross-classification of cardiothoracic ratio (CTR) of 0.5 and lower/higher grade AAC (LGAAC/HGAAC). The relationship between these groups and mortality was then analyzed by Cox proportional hazards model.

RESULTS

In multivariate Cox regression analysis, those in CTR ≤ 0.5 and HGAAC [hazard ratio (95% confidence interval): 2.07 (1.14-3.77)], CTR > 0.5 & LGAAC [3.60 (2.07-6.25)] and CTR > 0.5 & HGAAC [3.42 (2.03-5.77)] were significantly associated with overall mortality; while those in CTR > 0.5 & LGAAC [2.81 (1.28-6.19)] and CTR > 0.5 & HGAAC [2.32 (1.09-4.95)] were significantly related to cardiovascular mortality.

CONCLUSION

Combined cardiomegaly and AAC predicted overall and cardiovascular mortality in hemodialysis patients.

Canine mitral valve size as measured by computed tomography

OBJECTIVE

To measure the mitral annulus in dogs. Our hypothesis was that mitral measurement would be possible and consistent among observers using CT.

SAMPLE

Thoracic CT scans of dogs without known heart disease.

PROCEDURES

Five trained investigators measured 4 aspects of the mitral valve and the fourth thoracic vertebrae (T4) length using multiplanar reformatting tools. Ten randomly chosen animals were measured by all investigators to determine interobserver reliability.

RESULTS

There were 233 CT scans eligible for inclusion. Dogs weighed 2 to 96 kg (mean, 28.1 kg), with a variety of breeds represented. Golden Retrievers (n = 28) and Labrador Retrievers (n = 37) were overrepresented. The intraclass correlations were all greater than 0.9, showing excellent agreement between observers. The means and SDs of each measurement were as follows: trigone-to-trigone distance, 17.2 ± 4.7 mm; the remaining circumference, 79.0 ± 17.5 mm; commissure-to-commissure distance, 30.8 ± 6.5 mm; septal leaflet-to-lateral leaflet distance, 26.3 ± 6.0 mm; T4 length, 16.9 ± 3.1 mm; and the total circumference normalized by T4, 5.7 ± 0.7 mm.

CLINICAL RELEVANCE

This study provides information that may help in the development of future treatment for mitral valve dysfunction and subsequent annular enlargement.

Influenza Type B Complicates a Previously Undiagnosed Case of Pericarditis

We report the first case of pericarditis exacerbation due to influenza B viral infection while emphasizing the importance of cardiac magnetic resonance (CMR) for the timely diagnosis and ruling out of non-effusive pericarditis in a patient with compatible, unexplained chest pain. The patient presented with left-sided chest pain that was partially relieved by leaning backward and noted persistent fatigue for several days. Pericardial friction rub, electrocardiogram (ECG), and echocardiogram abnormalities were not detected. After discharge on the morning following admission, fatigue and fever several minutes after physical exertion continued. The patient contracted influenza type B, leading to pneumonia and a second hospitalization, during which echocardiography showed moderate pericardial effusion. We conclude that the patient had pericarditis on the first admission because other compatible causes of chest pain were ruled out, symptoms were compatible with non-effusive pericarditis and could not be ruled out since CMR was not done, and the patient tested positive during his second admission for multiple known etiologic agents of pericarditis. We highlight the importance of CMR in screening patients presenting with chest pain of unknown origin to facilitate early detection and intervention.

Association of severe COVID-19 outcomes with radiological scoring and cardiomegaly: findings from the COVID-19 inpatients database, Japan

PURPOSE

We aimed to characterize novel coronavirus infections based on imaging [chest X-ray and chest computed tomography (CT)] at the time of admission.

MATERIALS AND METHODS

We extracted data from 396 patients with laboratory-confirmed COVID-19 who were managed at 68 hospitals in Japan from January 25 to September 2, 2020. Case patients were categorized as severe (death or treatment with invasive ventilation during hospitalization) and non-severe groups. The imaging findings of the groups were compared by calculating odds ratios (ORs) and 95% confidence intervals (95% CIs), adjusted for sex, age, and hospital size (and radiographic patient positioning for cardiomegaly). Chest X-ray and CT scores ranged from 0 to 72 and 0 to 20, respectively. Optimal cut-off values for these scores were determined by a receiver-operating characteristic (ROC) curve analysis.

RESULTS

The median age of the 396 patients was 48 years (interquartile range 28-65) and 211 (53.3%) patients were male. Thirty-two severe cases were compared to 364 non-severe cases. At the time of admission, abnormal lesions on chest X-ray and CT were mainly observed in the lower zone/lobe. Among severe cases, abnormal lesions were also seen in the upper zone/lobe. After adjustment, the total chest X-ray and CT score values showed a dose-dependent association with severe disease. For chest X-ray scores, the area under the ROC curve (AUC) was 0.91 (95% CI = 0.86-0.97) and an optimal cut-off value of 9 points predicted severe disease with 83.3% sensitivity and 84.7% specificity. For chest CT scores, the AUC was 0.94 (95% CI = 0.89-0.98) and an optimal cut-off value of 11 points predicted severe disease with 90.9% sensitivity and 82.2% specificity. Cardiomegaly was strongly associated with severe disease [adjusted OR = 24.6 (95% CI = 3.7-166.0)].

CONCLUSION

Chest CT and X-ray scores and the identification of cardiomegaly could be useful for classifying severe COVID-19 on admission.

Clinical Data, Chest Radiograph and Electrocardiography in the Screening for Left Ventricular Hypertrophy: The CAR2E2 Score

Left ventricular hypertrophy (LVH) is associated with adverse clinical outcomes and implicates clinical decision-making. The aim of our study was to assess the importance of different approaches in the screening for LVH. We included patients who underwent cardiac magnetic resonance (CMR) imaging and had available chest radiograph in medical documentation. Cardiothoracic ratio (CTR), transverse cardiac diameter (TCD), clinical and selected electrocardiographic (ECG)-LVH data, including the Peguero-Lo Presti criterion, were assessed. CMR−LVH was defined based on indexed left ventricular mass-to-body surface area. Receiver operating characteristics analyses showed that both the CTR and TCD (CTR: area under the curve: [AUC] = 0.857, p < 0.001; TCD: AUC = 0.788, p = 0.001) were predictors for CMR−LVH. However, analyses have shown that diagnoses made with TCD, but not CTR, were consistent with CMR−LVH. From the analyzed ECG−LVH criteria, the Peguero-Lo Presti criterion was the best predictor of LVH. The best sensitivity for screening for LVH was observed when the presence of heart failure, ≥40 years in age (each is assigned 1 point), increased TCD and positive Peguero-Lo Presti criterion (each is assigned 2 points) were combined (CAR2E2 score ≥ 3 points). CAR2E2 score may improve prediction of LVH compared to other approaches. Therefore, it may be useful in the screening for LVH in everyday clinical practice in patients with prevalent cardiovascular diseases.

Hypofractionated Whole-Breast Irradiation Focus on Coronary Arteries and Cardiac Toxicity-A Narrative Review

Breast cancer is the most common cancer among women worldwide, which is often treated with radiotherapy. Whole breast irradiation (WBI) is one of the most common types of irradiation. Hypo-fractionated WBI (HF-WBI) reduces the treatment time from 5 to 3 weeks. Recent radiobiological and clinical evidence recommended the use of HF-WBI regardless of the age or stage of disease, and it is proven that hypo-fractionation is non-inferior to conventional fractionation regimen irradiation. However, some studies report an increased incidence of heart-related deaths in the case of breast irradiation by hypo-fractionation, especially in patients with pre-existing cardiac risk factors at the time of treatment. Due to the new technical possibilities of radiotherapy techniques, HF-WBI can reduce the risk of cardiac toxicity by controlling the doses received both by the heart and by the anatomical structures of the heart. The radiobiological “double trouble”, in particular “treble trouble”, for hypo-fractionated regimen scan be avoided by improving the methods of heart sparing based on image-guided irradiation (IGRT) and by using respiration control techniques so that late cardiac toxicity is expected to be limited. However, long-term follow-up of patients treated with HF-WBI with modern radiotherapy techniques is necessary considering the progress of systemic therapy, which is associated with long-term survival, and also the cardiac toxicity of new oncological treatments. The still unknown effects of small doses spread in large volumes on lung tissue may increase the risk of second malignancy, but they can also be indirectly involved in the later development of a heart disease. It is also necessary to develop multivariable radiobiological models that include histological, molecular, clinical, and therapeutic parameters to identify risk groups and dosimetric tolerance in order to limit the incidence of late cardiac events. MR-LINAC will be able to offer a new standard for reducing cardiac toxicity in the future, especially in neoadjuvant settings for small tumors.

Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening

Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administering drugs and surgical treatments. In this study, we will establish a multilayer one-dimensional (1D) convolutional neural network (CNN)-based classifier for automatic cardiomegaly level screening based on chest X-ray (CXR) image classification in frontal posteroanterior view. Using two-round 1D convolutional processes in the convolutional pooling layer, two-dimensional (2D) feature maps can be converted into feature signals, which can enhance their characteristics for identifying normal condition and cardiomegaly levels. In the classification layer, a classifier based on gray relational analysis, which has a straightforward mathematical operation, is used to screen the cardiomegaly levels. Based on the collected datasets from the National Institutes of Health CXR image database, the proposed multilayer 1D CNN-based classifier with K-fold cross-validation has promising results for the intended medical purpose, with precision of 97.80%, recall of 98.20%, accuracy of 98.00%, and F1 score of 0.9799.

Associations between Chest CT Abnormalities and Clinical Features in Patients with the Severe Fever with Thrombocytopenia Syndrome

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus. It involves multiple organ systems, including the lungs. However, the significance of the lung involvement in SFTS remains unclear. In the present study, we aimed to investigate the relationship between the clinical findings and abnormalities noted in the chest computed tomography (CT) of patients with SFTS. The medical records of 22 confirmed SFTS patients hospitalized in five hospitals in Nagasaki, Japan, between April 2013 and September 2019, were reviewed retrospectively. Interstitial septal thickening and ground-glass opacity (GGO) were the most common findings in 15 (68.1%) and 12 (54.5%) patients, respectively, and lung GGOs were associated with fatalities. The SFTS patients with a GGO pattern were elderly, had a disturbance of the conscious and tachycardia, and had higher c-reactive protein levels at admission (p = 0.009, 0.006, 0.002, and 0.038, respectively). These results suggested that the GGO pattern in patients with SFTS displayed disseminated inflammation in multiple organs and that cardiac stress was linked to higher mortality. Chest CT evaluations may be useful for hospitalized patients with SFTS to predict their severity and as early triage for the need of intensive care.