Publications by authors named "Ensheng Xue"
Main Objectives: We aimed at comparing intratumoral and peritumoral deep learning, radiomics, and fusion models in predicting KRAS mutations in rectal cancer using endorectal ultrasound imaging.
Methods: This study included 304 patients with rectal cancer from Fujian Medical University Union Hospital. The patients were randomly divided into a training group (213 patients) and a test group (91 patients) at a 7:3 ratio.
Article Synopsis
- The study aimed to evaluate the effectiveness of strain elastography (SE) in improving the categorization of ultrasound Breast Imaging Reporting and Data System (BI-RADS) 3 and 4a lesions, potentially reducing unnecessary biopsies.
- A total of 4,371 patients were analyzed, using various methods to combine BI-RADS with elasticity scores and strain ratios, which showed improved diagnostic performance compared to BI-RADS alone.
- The findings suggested that downgrading only BI-RADS 4a lesions might be sufficient for maintaining a high diagnostic accuracy, thereby decreasing false-positive rates in breast biopsies.
Article Synopsis
- - The multi-attention guided UNet (MAUNet) is proposed for improved segmentation of thyroid nodules, addressing challenges due to their varying sizes and positions using a multi-scale cross attention (MSCA) module for better feature extraction.
- - A dual attention (DA) module enhances information sharing between the encoder and decoder in the UNet architecture, further refining segmentation results.
- - Extensive tests on ultrasound images from 17 hospitals reveal that MAUNet achieves high Dice scores (around 0.9) and outperforms existing segmentation methods, demonstrating effective generalization across diverse datasets while maintaining patient privacy through federal learning.
Purpose: To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).
Methods: A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set.
Purpose: To investigate the value of shear-wave elastography (SWE) in assessing the response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer.
Methods: In this study, 455 participants with locally advanced rectal cancer who underwent nCRT at our hospital between September 2021 and December 2022 were prospectively enrolled. The participants were randomly divided into training and test cohorts in a 3:2 ratio.
Objective: This study aimed to develop an ultrasomics model for predicting lymph node metastasis preoperative in patients with gastric cancer (GC).
Methods: This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software.
Purpose: To assess the predictive value of an ultrasound-based radiomics-clinical nomogram for grading residual cancer burden (RCB) in breast cancer patients.
Methods: This retrospective study of breast cancer patients who underwent neoadjuvant therapy (NAC) and ultrasound scanning between November 2020 and July 2023. First, a radiomics model was established based on ultrasound images.
Article Synopsis
- The study aimed to create and validate a predictive model for cytokeratin 7 (CK7) expression in clear cell renal cell carcinoma (ccRCC) using various ultrasound diagnostic methods.
- It involved 157 patients and used both univariate and multivariate logistic regression analyses to identify key factors influencing CK7 positivity, concluding that age, wash-in pattern, and enhancement homogeneity were significant indicators.
- The predictive model demonstrated strong accuracy with ROC curve areas of 0.812 for the training group and 0.792 for the testing group, indicating its clinical utility in predicting CK7 expression in ccRCC patients.
Article Synopsis
- The study investigates how contrast-enhanced ultrasound (CEUS) can be used to diagnose and grade bladder urothelial carcinoma (BUC) by analyzing data from 173 patients with bladder lesions.
- Results showed clear differences in blood flow and CEUS enhancement between BUC and benign lesions, with specific metrics (like the H/T ratio) effectively distinguishing between high and low grades of BUC.
- The findings suggest that using CEUS along with time-intensity curve analysis significantly enhances the diagnostic precision for identifying BUC and its severity.
Article Synopsis
- The study aimed to create a predictive model using ultrasound features, radiomics, and machine learning to assess the risk of post-surgical recurrence in gastrointestinal stromal tumors (GISTs).
- A total of 230 patients were analyzed, with radiomic and ultrasound features selected and processed through various machine learning algorithms to predict GIST risk.
- The models, particularly logistic regression and support vector machine, showed high accuracy and outperformed a radiologist's subjective assessment, demonstrating the potential of machine learning in predicting GIST malignancy risk.
Background: Clear cell renal cell carcinoma (CCRCC) comprises 70%-80% of RCCs. The World Health Organization/International Society of Urology Pathology (WHO/ISUP) classification is the most important prognostic factor for CCRCC. By evaluating the variations of tumor microvascular density, contrast-enhanced ultrasound (CEUS) can noninvasively predict the WHO/ISUP grade of CCRCC, and provide the appropriate treatment plan before clinical operation.
View Article and Find Full Text PDFObjective: Pre-operative differentiation between pleomorphic adenoma (PA) and Warthin's tumor (WT) of the major salivary glands is crucial for treatment decisions. The purpose of this study was to develop and validate a nomogram incorporating clinical, conventional ultrasound (CUS) and shear wave elastography (SWE) features to differentiate PA from WT.
Methods: A total of 113 patients with histological diagnosis of PA or WT of the major salivary glands treated at Fujian Medical University Union Hospital were enrolled in training cohort ( = 75; PA = 41, WT = 34) and validation cohort ( = 38; PA = 22, WT = 16).
Objective: We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs).
Methods: A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features.
Objective: The goals of this study were to determine whether contrast-enhanced ultrasound (CEUS) imaging could be used for assessment of chronic alcohol-induced testicular damage (CAITD) and to explore the relationships between the laboratory and pathological findings of CAITD and the quantitative parameters of CEUS.
Methods: Thirty-six rabbits were randomly divided into a chronic ethanol exposure (CEE) group and negative control (NC) group, which were further randomly divided into six groups with equal numbers of rabbits by period of exposure (30 d, 60 d, 90 d). All rabbits underwent conventional US and CEUS imaging at the end of the induction period.
Biomedical image segmentation and classification are critical components in a computer-aided diagnosis system. However, various deep convolutional neural networks are trained by a single task, ignoring the potential contribution of mutually performing multiple tasks. In this paper, we propose a cascaded unsupervised-based strategy to boost the supervised CNN framework for automated white blood cell (WBC) and skin lesion segmentation and classification, called CUSS-Net.
View Article and Find Full Text PDFObjectives: To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously.
Methods: This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously.
A Super-resolution Guided Network for Improving Automated Thyroid Nodule Segmentation.
Comput Methods Programs Biomed
December 2022
Article Synopsis
- A thyroid nodule is a lump in the thyroid gland that can indicate early thyroid cancer, and accurate segmentation of these nodules in ultrasound images is crucial for diagnosis and treatment.
- The authors developed a new framework that includes a super-resolution reconstruction network to enhance image quality and an N-shape network for effective segmentation, utilizing advanced techniques like atrous spatial pyramid pooling and a parallel atrous convolution module.
- Their method demonstrated superior performance on the UTNI-2021 dataset, achieving high metrics such as a Dice value of 91.9% and outperforming existing techniques in ultrasound image segmentation.
Article Synopsis
- Medical image segmentation is critical for computer-aided diagnosis, particularly for early thyroid disease detection using ultrasound images.
- The paper introduces a new dense fully convolutional neural network called N-Net, which incorporates a multi-scale input layer, an attention guidance module, and a stackable dilated convolution (SDC) block.
- Experimental results indicate that N-Net achieves superior performance in thyroid nodule segmentation compared to existing state-of-the-art methods, evaluated on relevant datasets.
Background: Studies on deep learning (DL)-based models in breast ultrasound (US) remain at the early stage due to a lack of large datasets for training and independent test sets for verification. We aimed to develop a DL model for differentiating benign from malignant breast lesions on US using a large multicenter dataset and explore the model's ability to assist the radiologists.
Methods: A total of 14,043 US images from 5012 women were prospectively collected from 32 hospitals.
Automated thyroid nodule classification in ultrasound images is an important way to detect thyroid nodules and to make a more accurate diagnosis. In this paper, we propose a novel deep convolutional neural network (CNN) model, called n-ClsNet, for thyroid nodule classification. Our model consists of a multi-scale classification layer, multiple skip blocks, and a hybrid atrous convolution (HAC) block.
View Article and Find Full Text PDFBackground: To assess the performance of conventional ultrasound (US) combined with strain elastography (SE) in the Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions on mammography.
Materials And Methods: Women with breast lesions identified as having mammography BI-RADS 4 lesions and underwent US examination were included in China. US features and US BI-RADS assessment were recorded in real-time and prospectively reported.
Objectives: To explore and establish a reliable and noninvasive ultrasound model for predicting the biological risk of gastrointestinal stromal tumors (GISTs).
Materials And Methods: We retrospectively reviewed 266 patients with pathologically-confirmed GISTs and 191 patients were included. Data on patient sex, age, tumor location, biological risk classification, internal echo, echo homogeneity, boundary, shape, blood flow signals, presence of necrotic cystic degeneration, long diameter, and short/long (S/L) diameter ratio were collected.