Nomogram for preoperative differentiation of benign and malignant breast tumors using contrast-enhanced cone-beam breast CT (CE CB-BCT) quantitative imaging and assessment features.

PURPOSE: Breast cancer's impact necessitates refined diagnostic approaches. This study develops a nomogram using radiology quantitative features from contrast-enhanced cone-beam breast CT for accurate preoperative classification of benign and malignant breast tumors. MATERIAL AND METHODS: A retrospective study enrolled 234 females with breast tumors, split into training and test sets. Contrast-enhanced cone-beam breast CT-images were acquired using Koning Breast CT-1000. Quantitative assessment features were extracted via 3D-slicer software, identifying independent predictors. The nomogram was constructed to preoperative differentiation benign and malignant breast tumors. Calibration curve was used to assess whether the model showed favorable correspondence with pathological confirmation. Decision curve analysis confirmed the model's superiority. RESULTS: The study enrolled 234 female patients with a mean age of 50.2 years (SD ± 9.2). The training set had 164 patients (89 benign, 75 malignant), and the test set had 70 patients (29 benign, 41 malignant). The nomogram achieved excellent predictive performance in distinguishing benign and malignant breast lesions with an AUC of 0.940 (95% CI 0.900-0.940) in the training set and 0.970 (95% CI 0.940-0.970) in the test set. CONCLUSION: This study illustrates the effectiveness of quantitative radiology features derived from contrast-enhanced cone-beam breast CT in distinguishing between benign and malignant breast tumors. Incorporating these features into a nomogram-based diagnostic model allows for breast tumor diagnoses that are objective and possess good accuracy. The application of these insights could substantially increase reliability and efficacy in the management of breast tumors, offering enhanced diagnostic capability.

Analysis and recognition of post-exercise cardiac state based on heart sound features and cardiac troponin I.

PURPOSE: Excessive intensity exercises can bring irreversible damage to the heart. We explore whether heart sounds can evaluate cardiac function after high-intensity exercise and hope to prevent overtraining through the changes of heart sound in future training. METHODS: The study population consisted of 25 male athletes and 24 female athletes. All subjects were healthy and had no history of cardiovascular disease or family history of cardiovascular disease. The subjects were required to do high-intensity exercise for 3 days, with their blood sample and heart sound (HS) signals being collected and analysed before and after exercise. We then developed a Kernel extreme learning machine (KELM) model that can distinguish the state of heart by using the pre- and post-exercise data. RESULTS: There was no significant change in serum cardiac troponin I after 3 days of load cross-country running, which indicates that there was no myocardial injury after the race. The statistical analysis of time-domain characteristics and multi-fractal characteristic parameters of HS showed that the cardiac reserve capacity of the subjects was enhanced after the cross-country running, and the KELM is an effective classifier to recognize HS and the state of the heart after exercise. CONCLUSION: Through the results, we can draw the conclusion that this intensity of exercise will not cause profound damage to the athlete's heart. The findings of this study are of great significance for evaluating the condition of the heart with the proposed index of heart sound and prevention of excessive training that causes damage to the heart.

DARU-Net: A dual attention residual U-Net for uterine fibroids segmentation on MRI.

PURPOSE: Uterine fibroid is the most common benign tumor in female reproductive organs. In order to guide the treatment, it is crucial to detect the location, shape, and size of the tumor. This study proposed a deep learning approach based on attention mechanisms to segment uterine fibroids automatically on preoperative Magnetic Resonance (MR) images. METHODS: The proposed method is based on U-Net architecture and integrates two attention mechanisms: channel attention of squeeze-and-excitation (SE) blocks with residual connections, spatial attention of pyramid pooling module (PPM). We did the ablation study to verify the performance of these two attention mechanisms module and compared DARU-Net with other deep learning methods. All experiments were performed on a clinical dataset consisting of 150 cases collected from our hospital. Among them, 120 cases were used as the training set, and 30 cases are used as the test set. After preprocessing and data augmentation, we trained the network and tested it on the test dataset. We evaluated segmentation performance through the Dice similarity coefficient (DSC), precision, recall, and Jaccard index (JI). RESULTS: The average DSC, precision, recall, and JI of DARU-Net reached 0.8066 ± 0.0956, 0.8233 ± 0.1255, 0.7913 ± 0.1304, and 0.6743 ± 0.1317. Compared with U-Net and other deep learning methods, DARU-Net was more accurate and stable. CONCLUSION: This work proposed an optimized U-Net with channel and spatial attention mechanisms to segment uterine fibroids on preoperative MR images. Results showed that DARU-Net was able to accurately segment uterine fibroids from MR images.

Increased Internal Carotid Artery Tortuosity is a Risk Factor for Spontaneous Cervicocerebral Artery Dissection.

OBJECTIVE: Spontaneous cervicocerebral artery dissection (sCCD) is an important cause of ischaemic stroke that often occurs in young and middle aged patients. The purpose of this study was to investigate the correlation between tortuosity of the carotid artery and sCCD. METHODS: Patients with confirmed sCCD who underwent computed tomography angiography (CTA) were reviewed retrospectively. Age and sex matched patients having CTA were used as controls. The tortuosity indices of the cervical arteries were measured from the CTA images. The carotid siphon and the extracranial internal carotid artery (ICA) were evaluated according to morphological classification. The carotid siphons were classified into five types. The extracranial ICA was categorised as simple tortuosity, coiling or kinking. Independent risk factors for sCCD were investigated using multivariable analysis. RESULTS: The study included sixty-six patients with sCCD and 66 controls. There were no differences in vascular risk factors between the two groups. The internal carotid tortuosity index (ICTI) (25.24 ± 12.37 vs. 15.90 ± 8.55, respectively; p < .001) and vertebral tortuosity index (VTI) (median 11.28; interquartile range [IQR] 6.88, 18.80 vs. median 8.38; IQR 6.02, 12.20, respectively; p = .008) were higher in the patients with sCCD than in the controls. Type III and Type IV carotid siphons were more common in the patients with sCCD (p = .001 and p < .001, respectively). The prevalence of any vessel tortuosity, coiling and kinking of the extracranial ICA was higher in the patients with sCCD (p < .001, p = .018 and p = .006, respectively). ICTI (odds ratio [OR] 2.964; p = .026), VTI (OR 5.141; p = .009), and Type III carotid siphons (OR 4.654; p = .003) were independently associated with the risk of sCCD. CONCLUSION: Arterial tortuosity is associated with sCCD, and greater tortuosity of the cervical artery may indicate an increased risk of arterial dissection.

Prediction of exercise sudden death in rabbit exhaustive swimming using deep neural network.

BACKGROUND AND OBJECTIVE: Moderate exercise contributes to good health. However, excessive exercise may lead to cardiac fatigue, myocardial damage and even exercise sudden death. Monitoring the heart health has important implication to prevent exercise sudden death. Diagnosis methods such as electrocardiogram, echocardiogram, blood pressure and histological analysis have shown that arrhythmia and left ventricular fibrosis are early warning symptoms of exercise sudden death. Heart sounds (HS) can reflect the changes of cardiac valve, cardiac blood flow and myocardial function. Deep learning has drawn wide attention because of its ability to recognize disease. Therefore, a deep learning method combined with HS was proposed to predict exercise sudden death in New Zealand rabbits. The objective is to develop a method to predict exercise sudden death in New Zealand rabbits. METHODS: This paper proposed a method to predict exercise sudden death in New Zealand rabbits based on convolutional neural network (CNN) and gated recurrent unit (GRU). The weight-bearing exhaustive swimming experiment was conducted to obtain the HS of exercise sudden death and surviving New Zealand rabbits (n = 11/10) at four different time points. Then, the improved Viola integral method and double threshold method were employed to segment HS signals. The segmented HS frames at different time points were taken as the input of a combined CNN and GRU called CNN-GRU network to complete the prediction of exercise sudden death. RESULTS: In order to evaluate the performance of proposed network, CNN and GRU were used for comparison. When the fourth time point segmented HS frames were taken as input, the result shows that the proposed network has better performance with an accuracy of 89.57%, a sensitivity of 89.38% and a specificity of 92.20%. In addition, the segmented HS frames at different time points were input into CNN-GRU network, and the result shows that with the progress of the experiment, the prediction accuracy of exercise sudden death in New Zealand rabbits increased from 50.98 to 89.57%. CONCLUSION: The proposed network shows good performance in classifying HS, which proves the feasibility of deep learning in exploring exercise sudden death. Further, it may have important implications in helping humans explore exercise sudden death.

Nonenhanced MRI-based radiomics model for preoperative prediction of nonperfused volume ratio for high-intensity focused ultrasound ablation of uterine leiomyomas.

OBJECTIVES: To develop and assess nonenhanced MRI-based radiomics model for the preoperative prediction of nonperfused volume (NPV) ratio of uterine leiomyomas after high-intensity focused ultrasound (HIFU) treatment. METHODS: Two hundred and five patients with uterine leiomyomas treated by HIFU were enrolled and allocated to training (N =164) and testing cohorts (N = 41). Pyradiomics was used to extract radiomics features from T2-weighted images and apparent diffusion coefficient (ADC) map generated from diffusion-weighted imaging (DWI). The clinico-radiological model, radiomics model, and radiomics-clinical model which combined the selected radiomics features and clinical parameters were used to predict technical outcomes determined by NPV ratios where three classification groups were created (NPV ratio ≤ 50%, 50-80% or ≥ 80%). The receiver operating characteristic (ROC) curve, area under the curve (AUC), and calibration and decision curve analyses were performed to illustrate the prediction performance and clinical usefulness of model in the training and testing cohorts. RESULTS: The multi-parametric MRI-based radiomics model outperformed T2-weighted imaging (T2WI)-based radiomics model, which achieved an average AUC of 0.769 (95% confidence interval [CI], 0.701-0.842), and showed satisfactory prediction performance for NPV ratio classification. The radiomics-clinical model demonstrated best prediction performance for HIFU treatment outcome, with an average AUC of 0.802 (95% CI, 0.796-0.850) and an accuracy of 0.762 (95% CI, 0.698-0.815) in the testing cohort, compared to the clinico-radiological and radiomics models. The decision curve also indicated favorable clinical usefulness of the radiomics-clinical model. CONCLUSIONS: Nonenhanced MRI-based radiomics has potential in the preoperative prediction of NPV ratio for HIFU ablation of uterine leiomyomas.

COVID-19 pneumonia: CT findings of 122 patients and differentiation from influenza pneumonia.

OBJECTIVES: To investigate the clinical and chest CT characteristics of COVID-19 pneumonia and explore the radiological differences between COVID-19 and influenza. MATERIALS AND METHODS: A total of 122 patients (61 men and 61 women, 48 ± 15 years) confirmed with COVID-19 and 48 patients (23 men and 25 women, 47 ± 19 years) confirmed with influenza were enrolled in the study. Thin-section CT was performed. The clinical data and the chest CT findings were recorded. RESULTS: The most common symptoms of COVID-19 were fever (74%) and cough (63%), and 102 patients (83%) had Wuhan contact. Pneumonia in 50 patients with COVID-19 (45%) distributed in the peripheral regions of the lung, while it showed mixed distribution in 26 patients (74%) with influenza (p = 0.022). The most common CT features of the COVID-19 group were pure ground-glass opacities (GGO, 36%), GGO with consolidation (51%), rounded opacities (35%), linear opacities (64%), bronchiolar wall thickening (49%), and interlobular septal thickening (66%). Compared with the influenza group, the COVID-19 group was more likely to have rounded opacities (35% vs. 17%, p = 0.048) and interlobular septal thickening (66% vs. 43%, p = 0.014), but less likely to have nodules (28% vs. 71%, p < 0.001), tree-in-bud sign (9% vs. 40%, p < 0.001), and pleural effusion (6% vs. 31%, p < 0.001). CONCLUSIONS: There are significant differences in the CT manifestations of patients with COVID-19 and influenza. Presence of rounded opacities and interlobular septal thickening, with the absence of nodules and tree-in-bud sign, and with the typical peripheral distribution, may help us differentiate COVID-19 from influenza. KEY POINTS: • Typical CT features of COVID-19 include pure ground-glass opacities (GGO), GGO with consolidation, rounded opacities, bronchiolar wall thickening, interlobular septal thickening, and a peripheral distribution. • Presence of rounded opacities and interlobular septal thickening, with the absence of nodules and tree-in-bud sign, and with the typical peripheral distribution, may help us differentiate COVID-19 from influenza.

Cohort study of chest CT and clinical changes in 29 patients with coronavirus disease 2019 (COVID-19).

OBJECTIVES: To investigate the imaging findings and clinical time course of COVID-19 pneumonia. METHODS: A total of 113 baseline and follow-up CT scans from 24 January 2020 to 18 February 2020 were longitudinally collected from 29 confirmed COVID-19 patients in a single center. The changes in the clinical and laboratory characteristics, imaging features, lesion-to-muscle ratio (LMR), and pulmonary inflammation index (PII) at baseline, 1-6 days, 7-13 days, and ≥ 14 days were compared. RESULTS: Of the 29 COVID-19 patients enrolled, the baseline chest CT scan was obtained 3 ± 2 (0-9) days after the onset of symptoms, and each patient had an average of 4 ± 1 (3-5) CT scans with a mean interval of 5 ± 2 (1-14) days. The percentage of patients with fever, cough, shortness of breath, and myalgia obviously decreased at 7-13 days with regular treatment (p < 0.05). The lymphocyte count, C-reactive protein, interleukin-6, and oxygenation index worsened within 1-6 days but improved sharply at 7-13 days. Compared with those at the other three time points, the LMR, PII, and number of involved lobes at 1-6 days were the highest, and gradually improved after 7-13 days. CONCLUSIONS: Lung lesion development on chest CT reflects the clinical time course of COVID-19 progression over 1-6 days, followed by clinical improvement and the resorption of lesions. CT imaging may be indicated when patients fail to improve within a week of treatment, but repeated chest CT may be unnecessary when the patients show improvements clinically. KEY POINTS: • Chest CT reflects the development of coronavirus disease 2019 pneumonia (COVID-19). • COVID-19 usually shows progressive lesions over up to 9 days with subsequent resorption. • Unusual clinical time course of COVID-19 may indicate repeated chest CT.

Gated recurrent unit-based heart sound analysis for heart failure screening.

BACKGROUND: Heart failure (HF) is a type of cardiovascular disease caused by abnormal cardiac structure and function. Early screening of HF has important implication for treatment in a timely manner. Heart sound (HS) conveys relevant information related to HF; this study is therefore based on the analysis of HS signals. The objective is to develop an efficient tool to identify subjects of normal, HF with preserved ejection fraction and HF with reduced ejection fraction automatically. METHODS: We proposed a novel HF screening framework based on gated recurrent unit (GRU) model in this study. The logistic regression-based hidden semi-Markov model was adopted to segment HS frames. Normalized frames were taken as the input of the proposed model which can automatically learn the deep features and complete the HF screening without de-nosing and hand-crafted feature extraction. RESULTS: To evaluate the performance of proposed model, three methods are used for comparison. The results show that the GRU model gives a satisfactory performance with average accuracy of 98.82%, which is better than other comparison models. CONCLUSION: The proposed GRU model can learn features from HS directly, which means it can be independent of expert knowledge. In addition, the good performance demonstrates the effectiveness of HS analysis for HF early screening.

MRI evaluation of endopelvic fascial swelling and analysis of influencing factors in patients with uterine fibroids after high-intensity focused ultrasound ablation.

Purpose: To evaluate endopelvic fascial swelling in patients with uterine fibroids after high-intensity focused ultrasound (HIFU) ablation on magnetic resonance imaging (MRI) and investigate the factors that influence endopelvic fascial swelling.Methods: MRI and clinical data from 188 patients with uterine fibroids who were treated with HIFU were analyzed retrospectively. The patients were divided into a fascial swelling group and a non-swelling group, and the degree of swelling was graded. Fascial swelling was set as the dependent variable, and factors such as baseline characteristics and HIFU parameters, were set as the independent variables. The relationship between these variables and fascial swelling was analyzed by univariate and multivariate analyses. Correlations between the factors and the degree of fascial swelling were evaluated by Kruskal-Wallis test.Results: The univariate analysis revealed that the fibroid location, distance from the fibroid to the sacrum, sonication time, treatment time, treatment intensity, therapeutic dose (TD), and energy efficiency (EEF) all affected the endopelvic fascial swelling (p < 0.05). Subsequently, multivariate analysis showed that the distance from the fibroid to the sacrum was significantly correlated with fascial swelling (p < 0.05). Moreover, TD and sonication time were significantly positively correlated with the degree of fascial swelling (p < 0.05). The incidence of sacrococcygeal pain was significantly correlated with fascial swelling (p < 0.05).Conclusion: The distance from the fibroid to the sacrum was a protective factor for fascial swelling. TD and sonication time were significantly positively correlated with the degree of fascial swelling.

Intraventricular Hemorrhage Growth: Definition, Prevalence and Association with Hematoma Expansion and Prognosis.

BACKGROUND/OBJECTIVES: The objective of this study is to propose a definition of intraventricular hemorrhage (IVH) growth and to investigate whether IVH growth is associated with ICH expansion and functional outcome. METHODS: We performed a prospective observational study of ICH patients between July 2011 and March 2017 in a tertiary hospital. Patients were included if they had a baseline CT scan within 6 h after onset of symptoms and a follow-up CT within 36 h. IVH growth was defined as either any newly occurring intraventricular bleeding on follow-up CT scan in patients without baseline IVH or an increase in IVH volume ≥ 1 mL on follow-up CT scan in patients with initial IVH. Poor outcome was defined as modified Rankin Scale score of 3-6 at 90 days. The association between IVH growth and functional outcome was assessed by using multivariable logistic regression analysis. RESULTS: IVH growth was observed in 59 (19.5%) of 303 patients. Patients with IVH growth had larger baseline hematoma volume, higher NIHSS score and lower GCS score than those without. Of 44 patients who had concurrent IVH growth and hematoma growth, 41 (93.2%) had poor functional outcome at 3-month follow-up. IVH growth (adjusted OR 4.15, 95% CI 1.31-13.20; P = 0.016) was an independent predictor of poor functional outcome (mRS 3-6) at 3 months in multivariable analysis. CONCLUSION: IVH growth is not uncommon and independently predicts poor outcome in ICH patients. It may serve as a promising therapeutic target for intervention.

Primary solid lung cancerous nodules with different sizes: computed tomography features and their variations.

BACKGROUND: The computed tomography (CT) features of small solid lung cancers and their changing regularity as they grow have not been well studied. The purpose of this study was to analyze the CT features of solid lung cancerous nodules (SLCNs) with different sizes and their variations. METHODS: Between February 2013 and April 2018, a consecutive cohort of 224 patients (225 nodules) with confirmed primary SLCNs was enrolled. The nodules were divided into four groups based on tumor diameter (A: diameter ≤ 1.0 cm, 35 lesions; B: 1.0 cm < diameter ≤ 1.5 cm, 60 lesions; C: 1.5 cm < diameter ≤ 2.0 cm, 63 lesions; and D: 2.0 cm < diameter ≤ 3.0 cm, 67 lesions). CT features of nodules within each group were summarized and compared. RESULTS: Most nodules in different groups were located in upper lobes (groups A - D:50.8%-73.1%) and had a gap from the pleura (groups A - D:89.6%-100%). The main CT features of smaller (diameter ≤ 1 cm) and larger (diameter > 1 cm) nodules were significantly different. As nodule diameter increased, more lesions showed a regular shape, homogeneous density, clear but coarse tumor-lung interface, lobulation, spiculation, spinous protuberance, vascular convergence, pleural retraction, bronchial truncation, and beam-shaped opacity (p < 0.05 for all). The presence of halo sign in all groups was similar (17.5%-22.5%; p > 0.05). CONCLUSIONS: The CT features vary among SLCNs with different sizes. Understanding their changing regularity is helpful for identifying smaller suspicious malignant nodules and early determining their nature in follow-up.

Effect of Slab Thickness on the Detection of Pulmonary Nodules by Use of CT Maximum and Minimum Intensity Projection.

OBJECTIVE. The purpose of this study was to investigate the effect of slab thickness on the detection of pulmonary nodules by use of maximum-intensity-projection (MIP) and minimum-intensity-projection (MinIP) to process CT images. MATERIALS AND METHODS. Chest CT data of 221 patients with pulmonary nodules were retrospectively analyzed. Nodules were categorized into two groups according to density: solid nodules (SNs) and subsolid nodules (SSNs). Pulmonary nodules were independently evaluated by two radiologists using axial CT images with 1-mm and 5-mm section thickness and MIP and MinIP images. MIP images for SN detection and MinIP images for SSN detection were separately reconstructed with four (5, 10, 15, 20 mm) and three (3, 8, 15 mm) slab thicknesses. The numbers and locations of detected nodules were recorded, and interobserver agreement was assessed. For each reader, the differences in nodule detection rates were evaluated in different series of images. RESULTS. Among the different series of images, interobserver agreements for detecting nodules were all good to excellent (κ ≥ 0.687). For total SNs and SNs with a diameter < 5 mm, detection rates on 10-mm MIP images were significantly higher than in other series of images (reader 1, 84.5% and 83.8%; reader 2, 83.6% and 82.2%). For total SSNs and SSNs < 5 mm, detection rates on 3-mm MinIP images were significantly higher than those in other series of images, except for 1-mm (reader 1, 93.3% and 78.6%; reader 2, 95.0% and 81.0%). CONCLUSION. Ten-millimeter MIP images are extremely efficient for detecting SNs. Three-millimeter MinIP images are more useful for visualizing SSNs, the efficiency being comparable to that achieved by use of 1-mm axial images.

An Automatic Approach Using ELM Classifier for HFpEF Identification Based on Heart Sound Characteristics.

Heart failure with preserved ejection fraction (HFpEF) is a complex and heterogeneous clinical syndrome. For the purpose of assisting HFpEF diagnosis, a non-invasive method using extreme learning machine and heart sound (HS) characteristics was provided in this paper. Firstly, the improved wavelet denoising method was used for signal preprocessing. Then, the logistic regression based hidden semi-Markov model algorithm was utilized to locate the boundary of the first HS and the second HS, therefore, the ratio of diastolic to systolic duration can be calculated. Eleven features were extracted based on multifractal detrended fluctuation analysis to analyze the differences of multifractal behavior of HS between healthy people and HFpEF patients. Afterwards, the statistical analysis was implemented on the extracted HS characteristics to generate the diagnostic feature set. Finally, the extreme learning machine was applied for HFpEF identification by the comparison of performances with support vector machine. The result shows an accuracy of 96.32%, a sensitivity of 95.48% and a specificity of 97.10%, which demonstrates the effectiveness of HS for HFpEF diagnosis.

Optic radiations are thinner and show signs of iron deposition in patients with long-standing remitting-relapsing multiple sclerosis: an enhanced T2*-weighted angiography imaging study.

OBJECTIVE: This study aimed to investigate iron deposition and thickness and signal changes in optic radiation (OR) by enhanced T2*-weighted angiography imaging (ESWAN) in patients with relapsing-remitting multiple sclerosis (RRMS) with unilateral and bilateral lesions or no lesions. METHODS: Fifty-one RRMS patients (42 patients with a disease duration [DD] ≥ 2 years [group Mor], nine patients with a DD < 2 years [group Les]) and 51 healthy controls (group Con) underwent conventional magnetic resonance imaging (MRI) and ESWAN at 3.0 T. The mean phase value (MPV) of the OR was measured on the phase image, and thickness and signal changes of the OR were observed on the magnitude image. RESULTS: The average MPVs for the OR were 1,981.55 ± 7.75 in group Mor, 1,998.45 ± 2.01 in group Les, and 2,000.48 ± 5.53 in group Con. In group Mor, 28 patients with bilateral OR lesions showed bilateral OR thinning with a heterogeneous signal, and 14 patients with unilateral OR lesions showed ipsilateral OR thinning with a heterogeneous signal. In the remaining nine patients without OR lesions and in group Con, the bilateral OR had a normal appearance. In the patients, a negative correlation was found between DD and OR thickness and a positive correlation was found between MPV and OR thickness. CONCLUSIONS: We confirmed iron deposition in the OR in the RRMS patients, and the OR thickness was lower in the patients than in the controls. KEY POINTS: • Enhanced T 2* -weighted magnetic resonance angiography (ESWAN) provides new insights into multiple sclerosis (MS). • Focal destruction of the optic radiation (OR) is detectable by ESWAN. • Iron deposition in OR can be measured on ESWAN phase image in MS patients. • OR thickness was lower in the patients than in the controls. • Iron deposition and thickness changes of the OR are associated with disease duration.

Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors.

BACKGROUND: Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively. PURPOSE: To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively. METHODS: The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed. RESULTS: The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p = 0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891). CONCLUSION: In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

Boundary attention with multi-task consistency constraints for semi-supervised 2D echocardiography segmentation.

The 2D echocardiography semantic automatic segmentation technique is important in clinical applications for cardiac function assessment and diagnosis of cardiac diseases. However, automatic segmentation of 2D echocardiograms also faces the problems of loss of image boundary information, loss of image localization information, and limitations in data acquisition and annotation. To address these issues, this paper proposes a semi-supervised echocardiography segmentation method. It consists of two models: (1) a boundary attention transformer net (BATNet) and (2) a multi-task level semi-supervised model with consistency constraints on boundary features (semi-BATNet). BATNet is able to capture the location and spatial information of the input feature maps by using the self-attention mechanism. The multi-task level semi-supervised model with boundary feature consistency constraints (semi-BATNet) encourages consistent predictions of boundary features at different scales from the student and teacher networks to calculate the multi-scale consistency loss for unlabeled data. The proposed semi-BATNet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and self-collected echocardiography dataset from the First Affiliated Hospital of Chongqing Medical University. Experimental results on the CAMUS dataset showed that when only 25% of the images are labeled, the proposed method greatly improved the segmentation performance by utilizing unlabeled images, and it also outperformed five state-of-the-art semi-supervised segmentation methods. Moreover, when only 50% of the images labeled, semi-BATNet achieved the Dice coefficient values of 0.936, the Jaccard similarity of 0.881 on self-collected echocardiography dataset. Semi-BATNet can complete a more accurate segmentation of cardiac structures in 2D echocardiograms, indicating that it has the potential to accurately and efficiently assist cardiologists.

Detection of Coronary Artery Disease Based on Clinical Phonocardiogram and Multiscale Attention Convolutional Compression Network.

Heart sound is an important physiological signal that contains rich pathological information related with coronary stenosis. Thus, some machine learning methods are developed to detect coronary artery disease (CAD) based on phonocardiogram (PCG). However, current methods lack sufficient clinical dataset and fail to achieve efficient feature utilization. Besides, the methods require complex processing steps including empirical feature extraction and classifier design. To achieve efficient CAD detection, we propose the multiscale attention convolutional compression network (MACCN) based on clinical PCG dataset. Firstly, PCG dataset including 102 CAD subjects and 82 non-CAD subjects was established. Then, a multiscale convolution structure was developed to catch comprehensive heart sound features and a channel attention module was developed to enhance key features in multiscale attention convolutional block (MACB). Finally, a separate downsampling block was proposed to reduce feature losses. MACCN combining the blocks can automatically extract features without empirical and manual feature selection. It obtains good classification results with accuracy 93.43%, sensitivity 93.44%, precision 93.48%, and F1 score 93.42%. The study implies that MACCN performs effective PCG feature mining aiming for CAD detection. Further, it integrates feature extraction and classification and provides a simplified PCG processing case.

Integrating intratumoral and peritumoral radiomics with deep transfer learning for DCE-MRI breast lesion differentiation: A multicenter study comparing performance with radiologists.

PURPOSE: To conduct the fusion of radiomics and deep transfer learning features from the intratumoral and peritumoral areas in breast DCE-MRI images to differentiate between benign and malignant breast tumors, and to compare the diagnostic accuracy of this fusion model against the assessments made by experienced radiologists. MATERIALS AND METHODS: This multi-center study conducted a retrospective analysis of DCE-MRI images from 330 women diagnosed with breast cancer, with 138 cases categorized as benign and 192 as malignant. The training and internal testing sets comprised 270 patients from center 1, while the external testing cohort consisted of 60 patients from center 2. A fusion feature set consisting of radiomics features and deep transfer learning features was constructed from both intratumoral (ITR) and peritumoral (PTR) areas. The Least absolute shrinkage and selection operator (LASSO) based support vector machine was chosen as the classifier by comparing its performance with five other machine learning models. The diagnostic performance and clinical usefulness of fusion model were verified and assessed through the area under the receiver operating characteristics (ROC) and decision curve analysis. Additionally, the performance of the fusion model was compared with the diagnostic assessments of two experienced radiologists to evaluate its relative accuracy. The study strictly adhered to CLEAR and METRICS guidelines for standardization to ensure rigorous and reproducible methods. RESULTS: The findings show that the fusion model, utilizing radiomics and deep transfer learning features from the ITR and PTR, exhibited exceptional performance in classifying breast tumors, achieving AUCs of 0.950 in the internal testing set and 0.921 in the external testing set. This performance significantly surpasses that of models relying on singular regional radiomics or deep transfer learning features alone. Moreover, the fusion model demonstrated superior diagnostic accuracy compared to the evaluations conducted by two experienced radiologists, thereby highlighting its potential to support and enhance clinical decision-making in the differentiation of benign and malignant breast tumors. CONCLUSION: The fusion model, combining multi-regional radiomics with deep transfer learning features, not only accurately differentiates between benign and malignant breast tumors but also outperforms the diagnostic assessments made by experienced radiologists. This underscores the model's potential as a valuable tool for improving the accuracy and reliability of breast tumor diagnosis.

CTR > 0.7 predicts the subgroup of lung adenocarcinomas ≤ 2 cm at risk of poor outcome treated by sublobar resection compared to lobar resection.

BACKGROUND: A standard surgical procedure for patients with small early-stage lung adenocarcinomas remains unknown. Hence, we aim in this study to assess the clinical utility of the consolidation-to-tumor ratio (CTR) when treating patients with small (2 cm) early stage lung cancers. METHODS: A retrospective cohort of 298 sublobar resection and 266 lobar resection recipients for early stage lung adenocarcinoma ≤ 2 cm was assembled from the First Affiliated Hospital of Chongqing Medical University between 2016 and 2019. To compare survival rates among the different groups, Kaplan-Meier curves were calculated, and the log-rank test was used. A multivariate Cox proportional hazard model was constructed utilizing variables that were significant in univariate analysis of survival. RESULTS: In the study, 564 patients were included, with 298 patients (52.8%) undergoing sublobar resection and 266 patients (47.2%) undergoing lobar resection. Regarding survival results, there was no significant difference in the 5-year overall survival (OS, P = 0.674) and 5-year recurrence-free survival (RFS, P = 0.253) between the two groups. Cox regression analyses showed that CTR ≥ 0.75(P < 0.001), age > 56 years (P = 0.007), and sublobar resection(P = 0.001) could predict worse survival. After examining survival results based on CTR categorization, we segmented the individuals into three categories: CTR<0.7, 0.7 ≤ CTR<1, and CTR = 1.The lobar resection groups had more favorable clinical outcomes than the sublobar resection groups in both the 0.7 ≤ CTR < 1(RFS: P < 0.001, OS: P = 0.001) and CTR = 1(RFS: P = 0.001, OS: P = 0.125). However, for patients with 0 ≤ CTR < 0.7, no difference in either RFS or OS was found between the lobar resection and sublobar resection groups, all of which had no positive events. Patients with a CTR between 0.7 and 1 who underwent lobar resection had similar 5-year RFS and OS rates compared to those with a CTR between 0 and 0.7 who underwent sublobar resection (100% vs. 100%). Nevertheless, a CTR of 1 following lobar resection resulted in notably reduced RFS and OS when compared to a CTR between 0.7 and 1 following lobar resection (P = 0.005 and P = 0.016, respectively). CONCLUSION: Lobar resection is associated with better long-term survival outcomes than sublobar resection for small lung adenocarcinomas ≤ 2 cm and CTR ≥ 0.7.