Publications by authors named "Liu Shunli"

Background: To construct and assess a deep learning (DL) signature that employs computed tomography imaging to predict the expression status of programmed cell death ligand 1 in patients with bladder cancer (BCa).

Methods: This retrospective study included 190 patients from two hospitals who underwent surgical removal of BCa (training set/external validation set, 127/63). We used convolutional neural network and radiomics machine learning technology to generate prediction models.

View Article and Find Full Text PDF

Background: Medical image segmentation is an essential component of computer-aided diagnosis. While U-Net has been widely used in this field, its performance can be limited by incomplete feature information transfer and the imbalance between foreground and background pixel classes in medical images.

Purpose: To improve feature utilization and address challenges, such as missing target regions and insufficient edge detail preservation, this study proposes a segmentation method that integrates path enhancement, residual attention, and zone-based chunking training.

View Article and Find Full Text PDF

Background: Adhesive small bowel obstruction (ASBO) is a common emergency that requires prompt medical attention, and the timing of surgical intervention poses a considerable challenge. Although computed tomography (CT) is widely used, its effectiveness in accurately identifying bowel strangulation is limited. The potential of radiomics models to predict the necessity for surgical resection in ASBO cases is not yet fully explored.

View Article and Find Full Text PDF

Rationale And Objectives: To develop and validate a radiomics signature, utilizing baseline and restaging CT, for preoperatively predicting progression-free survival (PFS) after neoadjuvant chemotherapy (NAC) in locally advanced gastric cancer (LAGC).

Methods: A total of 316 patients with LAGC who received NAC followed by gastrectomy were retrospectively included in this single-center study; these patients were split into two cohorts, one for training (n = 243) and the other for validation (n = 73), based on the different districts of our hospital. A total of 1316 radiomics features were extracted from the volume of interest of the gastric-cancer lesion on venous phase CT images.

View Article and Find Full Text PDF

ATP-binding cassette (ABC) transporters hydrolyse ATP to transport various substrates. Previous studies have shown that ABC transporters are responsible for transporting plant hormones and heavy metals, thus contributing to plant immunity. Herein, we identified a wheat G-type ABC transporter, TaABCG2-5B, that responds to salicylic acid (SA) treatment and is induced by Fusarium graminearum, the primary pathogen causing Fusarium head blight (FHB).

View Article and Find Full Text PDF
Article Synopsis
  • This study aimed to develop and validate a dual-energy computed tomography-based radiomics model to differentiate between patients with gout flares and those without, addressing a current research gap.
  • It involved analyzing data from 200 patients, including 150 with past gout flares, to extract and evaluate specific radiomic features related to tophi in the foot joints, utilizing advanced statistical methods for model development.
  • The comprehensive model, which combined optimal radiomic features and key clinical factors like disease duration and hypertension, showed strong predictive performance, outperforming individual models in clinical relevance and accuracy.
View Article and Find Full Text PDF

Background: Early prediction of lymph node status after neoadjuvant chemotherapy (NAC) facilitates promptly optimization of treatment strategies. This study aimed to develop and validate a deep learning network (DLN) using baseline computed tomography images to predict lymph node metastasis (LNM) after NAC in patients with locally advanced gastric cancer (LAGC).

Methods: A total of 1205 LAGC patients were retrospectively recruited from three hospitals between January 2013 and March 2023, constituting a training cohort, an internal validation cohort, and two external validation cohorts.

View Article and Find Full Text PDF

Background: Pancreatic hamartoma, a rare benign non-neoplastic condition, presents challenges in differentiating from other pancreatic diseases due to its atypical imaging and unreliable biopsy results. In this study, we present a case of pancreatic hamartoma and conduct a comprehensive review of relevant literature to outline its characteristic features, aiming to underscore its clinical relevance and implications.

Case Presentation: A 63-year-old man presented with a pancreatic mass, discovered during evaluation of abdominal pain and distension.

View Article and Find Full Text PDF

Rationale And Objectives: This meta-analysis aimed to assess the diagnostic accuracy of multiparametric MRI (mpMRI) in detecting suspected prostate cancer (PCa) in biopsy-naive men.

Materials And Methods: PubMed, Scopus, and the Cochrane Library databases were systematically searched for studies published from January 2013 to April 2024. Sixteen studies comprising 4973 patients met the inclusion criteria.

View Article and Find Full Text PDF
Article Synopsis
  • Accurately predicting how patients with gastric cancer will respond to chemotherapy can help tailor treatments and improve survival rates.
  • Researchers studied 151 gastric cancer patients who received chemotherapy and surgery, using imaging data to develop a machine learning model for prediction.
  • A new model, called the combined radiopathomics nomogram (RPN), showed high accuracy in predicting treatment responses, surpassing previous models and offering promising benefits for personalized cancer treatment.
View Article and Find Full Text PDF

Problem: Previous studies had confirmed that some deep learning models had high diagnostic performance in staging liver fibrosis. However, training efficiency of models predicting liver fibrosis need to be improved to achieve rapid diagnosis and precision medicine.

Aim: The deep learning framework of EfficientNetV2-S was noted because of its faster training speed and better parameter efficiency compared with other models.

View Article and Find Full Text PDF

Background: Contrast-enhanced CT scans provide a means to detect unsuspected colorectal cancer. However, colorectal cancers in contrast-enhanced CT without bowel preparation may elude detection by radiologists. We aimed to develop a deep learning (DL) model for accurate detection of colorectal cancer, and evaluate whether it could improve the detection performance of radiologists.

View Article and Find Full Text PDF

Aims: To develop and evaluate machine learning models using tumor and nodal radiomics features for predicting the response to neoadjuvant chemotherapy (NAC) and recurrence risk in locally advanced gastric cancer (LAGC).

Background: Early and accurate response prediction is vital to stratify LAGC patients and select proper candidates for NAC.

Objective: A total of 218 patients with LAGC undergoing NAC followed by gastrectomy were enrolled in our study and were randomly divided into a training cohort (n = 153) and a validation cohort (n = 65).

View Article and Find Full Text PDF

Unlabelled: While neonatal necrotising enterocolitis (NEC) is associated with high mortality rates in newborns, survivors can face long-term sequelae. However, the relationship between NEC and neurodevelopmental impairment (NDI) in preterm infants remains unclear. To explore the relationship between neonatal NEC and neurodevelopmental outcomes in preterm infants, we searched PubMed, EMBASE, and the Cochrane Library from their inception to February 2024 for relevant studies.

View Article and Find Full Text PDF
Article Synopsis
  • The study investigates the effectiveness of a new automatic segmentation model, AttSEResUNet, for identifying rectal cancer in MRI scans, aiming to improve efficiency for doctors.
  • A total of 65 rectal cancer patients were included, with their MRI images divided into training and validation sets, and multiple models compared based on segmentation accuracy and inter-observer consistency.
  • Results showed AttSEResUNet achieved a perfect lesion recognition rate and outperformed other models, with performance matching that of experienced radiologists, indicating it could be a reliable tool for tumor contouring.
View Article and Find Full Text PDF

Pigments derived from red pepper fruits are widely used in food and cosmetics as natural colorants. Nitrogen (N) is a key nutrient affecting plant growth and metabolism; however, its regulation of color-related metabolites in pepper fruit has not been fully elucidated. This study analyzed the effects of N supply (0, 250, and 400 kg N ha) on the growth, fruit skin color, and targeted and non-target secondary metabolites of field-grown pepper fruits at the mature red stage.

View Article and Find Full Text PDF

Objectives: To develop and compare radiomics model and fusion model based on multiple MR parameters for staging liver fibrosis in patients with chronic liver disease.

Materials And Methods: Patients with chronic liver disease who underwent multiparametric abdominal MRI were included in this retrospective study. Multiparametric MR images were imported into 3D-Slicer software for drawing bounding boxes on MR images.

View Article and Find Full Text PDF

Objective: To develop novel multiparametric models based on computed tomography enterography (CTE) scores to identify endoscopic activity and surgical risk in patients with Crohn's disease (CD).

Methods: We analyzed 171 patients from 3 hospitals. Correlations between CTE outcomes and endoscopic scores were assessed using Spearman's rank correlation analysis.

View Article and Find Full Text PDF

With the development of deep learning, the methods based on transfer learning have promoted the progress of medical image segmentation. However, the domain shift and complex background information of medical images limit the further improvement of the segmentation accuracy. Domain adaptation can compensate for the sample shortage by learning important information from a similar source dataset.

View Article and Find Full Text PDF

An acousto-optic reconfigurable filter (AORF) is proposed and demonstrated based on vector mode fusion in dispersion-compensating fiber (DCF). With multiple acoustic driving frequencies, the resonance peaks of different vector modes in the same scalar mode group can be effectively fused into a single peak, which is utilized to obtain arbitrary reconfiguration of the proposed filter. In the experiment, the bandwidth of the AORF can be electrically tuned from 5 nm to 18 nm with superposition of different driving frequencies.

View Article and Find Full Text PDF

Bottom-up self-assembly is regarded as an alternative way to manufacture series of microstructures in many fields, especially chiral microstructures, which attract tremendous attention because of their optical micromanipulations and chiroptical spectroscopies. However, most of the self-assembled microstructures cannot be tuned after processing, which largely hinders their broad applications. Here, we demonstrate a promising manufacturing strategy for switchable microstructures by combining the flexibility of femtosecond laser printing induced capillary force self-assembly and the temperature-responsive characteristics of smart hydrogels.

View Article and Find Full Text PDF
Article Synopsis
  • The study explored how to combine radiomics and morphological features from computed tomography enterography (CTE) to create a noninvasive grading model for assessing mucosal activity and surgery risk in Crohn's disease (CD) patients.
  • A total of 167 patients were analyzed using a support vector machine (SVM) classifier to evaluate the Simple Endoscopic Score for Crohn's Disease (SES-CD), achieving high predictive accuracy with area under the curve (AUC) values.
  • The findings suggest that integrating luminal and mesenteric radiomics can effectively grade CD activity and develop a reliable model to predict the necessity for surgery, enhancing patient management.
View Article and Find Full Text PDF

Objectives: This study evaluated the ability of a preoperative contrast-enhanced CT (CECT)-based radiomics nomogram to differentiate benign and malignant primary retroperitoneal tumors (PRT).

Methods: Images and data from 340 patients with pathologically confirmed PRT were randomly placed into training (n = 239) and validation sets (n = 101). Two radiologists independently analyzed all CT images and made measurements.

View Article and Find Full Text PDF

Vortex beams, which intrinsically possess optical orbital angular momentum (OAM), are considered as one of the promising chiral light waves for classical optical communications and quantum information processing. For a long time, it has been an expectation to utilize artificial three-dimensional (3D) chiral metamaterials to manipulate the transmission of vortex beams for practical optical display applications. Here, we demonstrate the concept of selective transmission management of vortex beams with opposite OAM modes assisted by the designed 3D chiral metahelices.

View Article and Find Full Text PDF