Yi-Yang Liu

Liu HY, et al. World J Mens Health. 2026 ;44:e46. https://doi.org/10.5534/wjmh.250053

This paper studies the multirobot cooperative localization problem under resource-constrained scenarios, such as the limited communication bandwidth and battery capacity. Multirobot cooperative localization heavily relies on inter-robot communication, and it is challenging to ensure high localization accuracy when the communication bandwidth is constrained. To deal with this issue, a new distributed event-triggered unscented Kalman filter cooperative localization (ETUKF CL) approach is proposed in this paper, where an event-triggered mechanism is introduced to reduce the communication and energy cost. The proposed algorithm significantly reduces communication resource consumption while maintaining high positioning accuracy. Simulation results demonstrate the effectiveness of the proposed cooperative localization algorithm.

Kidney–ureter–bladder (KUB) imaging is used as a frontline investigation for patients with suspected renal stones. In this study, we designed a computer-aided diagnostic system for KUB imaging to assist clinicians in accurately diagnosing urinary tract stones. The image dataset used for training and testing the model comprised 485 images provided by Kaohsiung Chang Gung Memorial Hospital. The proposed system was divided into two subsystems, 1 and 2. Subsystem 1 used Inception-ResNetV2 to train a deep learning model on preprocessed KUB images to verify the improvement in diagnostic accuracy with image preprocessing. Subsystem 2 trained an image segmentation model using the ResNet hybrid, U-net, to accurately identify the contours of renal stones. The performance was evaluated using a confusion matrix for the classification model. We conclude that the model can assist clinicians in accurately diagnosing renal stones via KUB imaging. Therefore, the proposed system can assist doctors in diagnosis, reduce patients’ waiting time for CT scans, and minimize the radiation dose absorbed by the body.

In recent years, deep learning technology for clinical diagnosis has progressed considerably, and the value of medical imaging continues to increase. In the past, clinicians evaluated medical images according to their individual expertise. In contrast, the application of artificial intelligence technology for automatic analysis and diagnostic assistance to support clinicians in evaluating medical information more efficiently has become an important trend. In this study, we propose a machine learning architecture designed to segment images of retinal blood vessels based on an improved U-Net neural network model. The proposed model incorporates a residual module to extract features more effectively, and includes a full-scale skip connection to combine low level details with high-level features at different scales. The results of an experimental evaluation show that the model was able to segment images of retinal vessels accurately. The proposed method also outperformed several existing models on the benchmark datasets DRIVE and ROSE, including U-Net, ResUNet, U-Net3+, ResUNet++, and CaraNet.

Kidney–ureter–bladder (KUB) imaging is a radiological examination with a low cost, low radiation, and convenience. Although emergency room clinicians can arrange KUB images easily as a first-line examination for patients with suspicious urolithiasis, interpreting the KUB images correctly is difficult for inexperienced clinicians. Obtaining a formal radiology report immediately after a KUB imaging examination can also be challenging. Recently, artificial-intelligence-based computer-aided diagnosis (CAD) systems have been developed to help clinicians who are not experts make correct diagnoses for further treatment more effectively. Therefore, in this study, we proposed a CAD system for KUB imaging based on a deep learning model designed to help first-line emergency room clinicians diagnose urolithiasis accurately. A total of 355 KUB images were retrospectively collected from 104 patients who were diagnosed with urolithiasis at Kaohsiung Chang Gung Memorial Hospital. Then, we trained a deep learning model with a ResNet architecture to classify KUB images in terms of the presence or absence of kidney stones with this dataset of pre-processed images. Finally, we tuned the parameters and tested the model experimentally. The results show that the accuracy, sensitivity, specificity, and F1-measure of the model were 0.977, 0.953, 1, and 0.976 on the validation set and 0.982, 0.964, 1, and 0.982 on the testing set, respectively. Moreover, the results demonstrate that the proposed model performed well compared to the existing CNN-based methods and was able to detect urolithiasis in KUB images successfully. We expect the proposed approach to help emergency room clinicians make accurate diagnoses and reduce unnecessary radiation exposure from computed tomography (CT) scans, along with the associated medical costs.

We introduced a novel surgery that combines ultrasound guidance, miniaturization and Galdakao-modified supine Valdivia (GMSV) position in percutaneous nephrolithotomy (PCNL) and evaluated the safety and efficacy. This retrospective, single-center study retrospectively reviewed 150 patients who underwent ultrasound-guided mini-PCNL in the GMSV position from November 2019 to March 2022. All perioperative parameters were collected. Stone-free status was defined as no residual stones or clinically insignificant residual fragments (CIRF) 2). The mean S.T.O.N.E. score was 7.61, including 36 patients (24%) with scores ≥9. The mean operative time was 66.22 min, and the success rate of renal access creation in the first attempt was 88.7%. One hundred and forty (93.3%) patients were stone free. The mean decrease in Hemoglobin was 1.04 g/dL, and no patient needed a blood transfusion. Complications included transient hematuria (n = 13, 8.7%), bladder blood clot retention (n = 2, 1.3%), fever (n = 15, 10%) and sepsis (n = 2, 1.3%). Totally X-ray-free ultrasound-guided mini-PCNL in the GMSV position is feasible, safe and effective for patients with upper urinary tract stones, indicating the synergistic and complementary effects of the three novel techniques.

Many recent named entity recognition (NER) studies criticize flat NER for its non-overlapping assumption, and switch to investigating nested NER. However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly. This study proposes a new subtask, nested-from-flat NER, which corresponds to a realistic application scenario: given data annotated with flat entities only, one may still desire the trained model capable of recognizing nested entities. To address this task, we train span-based models and deliberately ignore the spans nested inside labeled entities, since these spans are possibly unlabeled entities. With nested entities removed from the training data, our model achieves 54.8%, 54.2% and 41.1% F1 scores on the subset of spans within entities on ACE 2004, ACE 2005 and GENIA, respectively. This suggests the effectiveness of our approach and the feasibility of the task. In addition, the model's performance on flat entities is entirely unaffected. We further manually annotate the nested entities in the test set of CoNLL 2003, creating a nested-from-flat NER benchmark. Analysis results show that the main challenges stem from the data and annotation inconsistencies between the flat and nested entities.

Image recognition has been applied to many fields, but it is relatively rarely applied to medical images. Recent significant deep learning progress for image recognition has raised strong research interest in medical image recognition. First of all, we found the prediction result using the VGG16 model on failed pneumonia X-ray images. Thus, this paper proposes IVGG13 (Improved Visual Geometry Group-13), a modified VGG16 model for classification pneumonia X-rays images. Open-source thoracic X-ray images acquired from the Kaggle platform were employed for pneumonia recognition, but only a few data were obtained, and datasets were unbalanced after classification, either of which can result in extremely poor recognition from trained neural network models. Therefore, we applied augmentation pre-processing to compensate for low data volume and poorly balanced datasets. The original datasets without data augmentation were trained using the proposed and some well-known convolutional neural networks, such as LeNet AlexNet, GoogLeNet and VGG16. In the experimental results, the recognition rates and other evaluation criteria, such as precision, recall and f-measure, were evaluated for each model. This process was repeated for augmented and balanced datasets, with greatly improved metrics such as precision, recall and F1-measure. The proposed IVGG13 model produced superior outcomes with the F1-measure compared with the current best practice convolutional neural networks for medical image recognition, confirming data augmentation effectively improved model accuracy.

Objectives: To identify predictive factors of biochemical recurrence for patients undergoing high‐intensity focused ultrasound treatment for localized prostate cancer.Methods: We retrospectively identified patients receiving whole‐gland prostate ablation with high‐intensity focused ultrasound for localized prostate cancer from 2009 to 2015. All the patients received pre‐high‐intensity focused ultrasound radical transurethral resection of the prostate. We included perioperative parameters as follows: age, preoperative prostate volume, stage of operation, initial prostate‐specific antigen, T stage, postoperative prostate‐specific antigen nadir, Gleason score, time to prostate‐specific antigen nadir and the presence of prostate‐specific antigen biochemical recurrence. Multivariable Cox regression and Kaplan–Meier analysis were used for investigating predictors of recurrence, and receiver operating characteristic analysis was used for the cut‐off values of prostate‐specific antigen nadir.Results: Among 182 patients, 26.9% had prostate‐specific antigen biochemical recurrence after high‐intensity focused ultrasound during the median follow‐up period of 32.21 months. Gleason score ≥7 (Gleason score 7, hazard ratio 2.877, P = 0.027), stage ≥T2b (T2b, hazard ratio 3.16, P = 0.027) and prostate‐specific antigen nadir (hazard ratio 1.11, P < 0.001) were statistically significant, whereas there was no significance in prostate volume and initial prostate‐specific antigen. We posit that a cut‐off level of prostate‐specific antigen nadir 0.43 ng/mL might be considered as an independent predictive factor for prostate‐specific antigen biochemical recurrence in high‐intensity focused ultrasound patients in multivariate analysis (P < 0.001, hazard ratio 7.39, 95% confidence interval 3.56–15.37), and created a new nadir‐related prediction model for biochemical recurrence prediction.Conclusions: Postoperative prostate‐specific antigen nadir of 0.43 ng/mL can be considered an important predictive factor for biochemical recurrence in primary whole‐prostate gland high‐intensity focused ultrasound treatment, and the nadir‐related prediction model might provide a reference for early salvage treatment. Furthermore, Gleason score ≥7, stage ≥T2b might be associated with unfavorable outcomes, although prostate volume and higher initial prostate‐specific antigen appear not to be associated with biochemical recurrence for the high‐intensity focused ultrasound treatment.