Searcharxiv⌕ Search

arXiv subjects

Yun-Chien Cheng

Publications and source records attributed to Yun-Chien Cheng.

15 recordsLinked to original sources
arXiv2026

Low-Temperature Co-Fired Ceramics for a Sustainable Planar Plasma Jet with Homogeneous Plasma in Large Treatment Areas for Biomedical Applications

This study presents a portable planar argon-based plasma jet designed for large-area biomedical applications, with an emphasis on uniform discharge, stability, and safety. The device incorporates interchangeable rear and side inlet gas adapters with restriction plates and channels to equalize gas flow, while electrodes are encapsulated in low-temperature co-fired ceramics to reduce degradation and arcing during repeated operation. Flow simulations were conducted for multiple channel configurations to ensure laminar gas distribution and uniform plasma generation. Device performance and safety were evaluated using the kinPen MED as a reference standard. Electrical characteristics, optical emission, discharge uniformity, temperature, gas velocity, ozone generation, UV irradiance, and leakage current were systematically measured. The plasma exhibited stable voltage, current, and power after an initial warm-up period. Temperatures stabilized within minutes, with the rear-inlet configuration demonstrating lower operating temperatures due to higher outlet gas velocity. Ozone levels remained below established safety limits, while UV exposure constrained allowable treatment times. Leakage current decreased with increasing distance and approached safety thresholds at short separations. These results demonstrate that the proposed planar plasma jet provides stable, uniform plasma delivery while meeting key safety requirements, supporting its potential for clinical and biomedical use.

physics.plasm-ph↗
arXiv2026

Non-thermal Atmospheric Pressure Plasma Combined with Benzoyl Peroxide to Enhance the Inhibition of Bacteria

This study aims to verify whether combining non-thermal equilibrium atmospheric pressure plasma with benzoyl peroxide (BPO) can enhance the inhibition of bacteria. This work involves not only adjusting the parameters of the plasma device, such as increasing the power supply voltage, modifying the working gas flow rate, as well as incorporating a specific proportion of oxygen to the working gas, but also aims to combine plasma with BPO to inactivate bacteria. An optical emission spectroscopy was utilized to determine the optimal working gas flow rate and oxygen mixing ratio for the experimental setup. Additionally, surface temperature and ultraviolet (UV) emission measurements were also performed to characterize the physical properties of the plasma treatment. Although the precise chemical mechanisms between plasma and BPO have yet to be fully elucidated, bacterial inactivation experiments on Escherichia coli demonstrated that the addition of BPO indeed enhanced the sterilization efficacy of plasma treatment.

physics.plasm-ph↗
arXiv2026

Rise Time Effects of a Portable Inductive Energy Storage Pulse Generator on NO Production in Spark Discharges

This study investigates pulse waveform adjustment in a portable inductive energy storage (IES) pulsed power system and its effect on nitric oxide (NO) generation in atmospheric spark discharges. While previous studies have focused on pulse energy, pulse width, and repetition rate, the role of rise time remains insufficiently explored. Existing pulse generators with adjustable rise time are also bulky and unsuitable for portable applications. To address these limitations, this study examines rise time control strategies within a compact IES architecture and employs a parallel high-voltage capacitor to generate adjustable waveforms. Optical emission spectroscopy was used to measure excited N2 and NO gamma emissions, and a NO analyzer was used to monitor NO concentration. In addition, electron excitation temperature, plasma-absorbed power, and rotational temperature were estimated to clarify the influence of waveform characteristics on plasma chemistry. The results show that although rise time can be adjusted, it is coupled with pulse width and input energy in the system. Comparative analysis of spectral intensities, NO concentration, electron excitation temperature, and absorbed energy indicates that NO production depends primarily on energy input rather than rise time. Electrode temperature varies only minimally under different waveform conditions, suggesting that NO formation is mainly influenced by electron impact and ionization processes. This work proposes a portable and simplified IES-based high-voltage pulsed power generator, identifies the constraints associated with rise time control, and demonstrates the feasibility of waveform adjustment. The findings clarify the dominant mechanisms governing NO generation and provide a reference for the design of future portable plasma-based NO production systems.

physics.plasm-ph↗
arXiv2026

Using Unsupervised Domain Adaptation Semantic Segmentation for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiogram (CTPA) Images

While deep learning has demonstrated considerable promise in computer-aided diagnosis for pulmonary embolism (PE), practical deployment in Computed Tomography Pulmonary Angiography (CTPA) is often hindered by "domain shift" and the prohibitive cost of expert annotations. To address these challenges, an unsupervised domain adaptation (UDA) framework is proposed, utilizing a Transformer backbone and a Mean-Teacher architecture for cross-center semantic segmentation. The primary focus is placed on enhancing pseudo-label reliability by learning deep structural information within the feature space. Specifically, three modules are integrated and designed for this task: (1) a Prototype Alignment (PA) mechanism to reduce category-level distribution discrepancies; (2) Global and Local Contrastive Learning (GLCL) to capture both pixel-level topological relationships and global semantic representations; and (3) an Attention-based Auxiliary Local Prediction (AALP) module designed to reinforce sensitivity to small PE lesions by automatically extracting high-information slices from Transformer attention maps. Experimental validation conducted on cross-center datasets (FUMPE and CAD-PE) demonstrates significant performance gains. In the FUMPE -> CAD-PE task, the IoU increased from 0.1152 to 0.4153, while the CAD-PE -> FUMPE task saw an improvement from 0.1705 to 0.4302. Furthermore, the proposed method achieved a 69.9% Dice score in the CT -> MRI cross-modality task on the MMWHS dataset without utilizing any target-domain labels for model selection, confirming its robustness and generalizability for diverse clinical environments.

eess.IV↗
arXiv2026

Active Learning-Driven Lightweight YOLOv9: Enhancing Efficiency in Smart Agriculture

This study addresses the demand for real-time detection of tomatoes and tomato flowers by agricultural robots deployed on edge devices in greenhouse environments. Under practical imaging conditions, object detection systems often face challenges such as large scale variations caused by varying camera distances, severe occlusion from plant structures, and highly imbalanced class distributions. These factors make conventional object detection approaches that rely on fully annotated datasets difficult to simultaneously achieve high detection accuracy and deployment efficiency. To overcome these limitations, this research proposes an active learning driven lightweight object detection framework, integrating data analysis, model design, and training strategy. First, the size distribution of objects in raw agricultural images is analyzed to redefine an operational target range, thereby improving learning stability under real-world conditions. Second, an efficient feature extraction module is incorporated to reduce computational cost, while a lightweight attention mechanism is introduced to enhance feature representation under multi-scale and occluded scenarios. Finally, an active learning strategy is employed to iteratively select high-information samples for annotation and training under a limited labeling budget, effectively improving the recognition performance of minority and small-object categories. Experimental results demonstrate that, while maintaining a low parameter count and inference cost suitable for edge-device deployment, the proposed method effectively improves the detection performance of tomatoes and tomato flowers in raw images. Under limited annotation conditions, the framework achieves an overall detection accuracy of 67.8% mAP, validating its practicality and feasibility for intelligent agricultural applications.

eess.IV↗
arXiv2025

Using Few-Shot Learning to Classify Primary Lung Cancer and Other Malignancy with Lung Metastasis in Cytological Imaging via Endobronchial Ultrasound Procedures

This study presents a computer-aided diagnosis (CAD) system to assist early detection of lung metastases during endobronchial ultrasound (EBUS) procedures, significantly reducing follow-up time and enabling timely treatment. Due to limited cytology images and morphological similarities among cells, classifying lung metastases is challenging, and existing research rarely targets this issue directly.To overcome data scarcity and improve classification, the authors propose a few-shot learning model using a hybrid pretrained backbone with fine-grained classification and contrastive learning. Parameter-efficient fine-tuning on augmented support sets enhances generalization and transferability. The model achieved 49.59% accuracy, outperforming existing methods. With 20 image samples, accuracy improved to 55.48%, showing strong potential for identifying rare or novel cancer types in low-data clinical environments.

eess.IV↗
arXiv2024

Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method

This study aims to develop an auxiliary diagnostic system for classifying abnormal lung respiratory sounds, enhancing the accuracy of automatic abnormal breath sound classification through an innovative multi-label learning approach and multi-head attention mechanism. Addressing the issue of class imbalance and lack of diversity in existing respiratory sound datasets, our study employs a lightweight and highly accurate model, using a two-dimensional label set to represent multiple respiratory sound characteristics. Our method achieved a 59.2% ICBHI score in the four-category task on the ICBHI2017 dataset, demonstrating its advantages in terms of lightweight and high accuracy. This study not only improves the accuracy of automatic diagnosis of lung respiratory sound abnormalities but also opens new possibilities for clinical applications.

cs.SD↗
arXiv2024

Towards Enhanced Analysis of Lung Cancer Lesions in EBUS-TBNA -- A Semi-Supervised Video Object Detection Method

This study aims to establish a computer-aided diagnostic system for lung lesions using endobronchial ultrasound (EBUS) to assist physicians in identifying lesion areas. During EBUS-transbronchial needle aspiration (EBUS-TBNA) procedures, hysicians rely on grayscale ultrasound images to determine the location of lesions. However, these images often contain significant noise and can be influenced by surrounding tissues or blood vessels, making identification challenging. Previous research has lacked the application of object detection models to EBUS-TBNA, and there has been no well-defined solution for the lack of annotated data in the EBUS-TBNA dataset. In related studies on ultrasound images, although models have been successful in capturing target regions for their respective tasks, their training and predictions have been based on two-dimensional images, limiting their ability to leverage temporal features for improved predictions. This study introduces a three-dimensional video-based object detection model. It first generates a set of improved queries using a diffusion model, then captures temporal correlations through an attention mechanism. A filtering mechanism selects relevant information from previous frames to pass to the current frame. Subsequently, a teacher-student model training approach is employed to further optimize the model using unlabeled data. By incorporating various data augmentation and feature alignment, the model gains robustness against interference. Test results demonstrate that this model, which captures spatiotemporal information and employs semi-supervised learning methods, achieves an Average Precision (AP) of 48.7 on the test dataset, outperforming other models. It also achieves an Average Recall (AR) of 79.2, significantly leading over existing models.

eess.IV↗
arXiv2023

Using Spatio-Temporal Dual-Stream Network with Self-Supervised Learning for Lung Tumor Classification on Radial Probe Endobronchial Ultrasound Video

The purpose of this study is to develop a computer-aided diagnosis system for classifying benign and malignant lung lesions, and to assist physicians in real-time analysis of radial probe endobronchial ultrasound (EBUS) videos. During the biopsy process of lung cancer, physicians use real-time ultrasound images to find suitable lesion locations for sampling. However, most of these images are difficult to classify and contain a lot of noise. Previous studies have employed 2D convolutional neural networks to effectively differentiate between benign and malignant lung lesions, but doctors still need to manually select good-quality images, which can result in additional labor costs. In addition, the 2D neural network has no ability to capture the temporal information of the ultrasound video, so it is difficult to obtain the relationship between the features of the continuous images. This study designs an automatic diagnosis system based on a 3D neural network, uses the SlowFast architecture as the backbone to fuse temporal and spatial features, and uses the SwAV method of contrastive learning to enhance the noise robustness of the model. The method we propose includes the following advantages, such as (1) using clinical ultrasound films as model input, thereby reducing the need for high-quality image selection by physicians, (2) high-accuracy classification of benign and malignant lung lesions can assist doctors in clinical diagnosis and reduce the time and risk of surgery, and (3) the capability to classify well even in the presence of significant image noise. The AUC, accuracy, precision, recall and specificity of our proposed method on the validation set reached 0.87, 83.87%, 86.96%, 90.91% and 66.67%, respectively. The results have verified the importance of incorporating temporal information and the effectiveness of using the method of contrastive learning on feature extraction.

eess.IV↗
arXiv2022

Detecting Pulmonary Embolism from Computed Tomography Using Convolutional Neural Network

The clinical symptoms of pulmonary embolism (PE) are very diverse and non-specific, which makes it difficult to diagnose. In addition, pulmonary embolism has multiple triggers and is one of the major causes of vascular death. Therefore, if it can be detected and treated quickly, it can significantly reduce the risk of death in hospitalized patients. In the detection process, the cost of computed tomography pulmonary angiography (CTPA) is high, and angiography requires the injection of contrast agents, which increase the risk of damage to the patient. Therefore, this study will use a deep learning approach to detect pulmonary embolism in all patients who take a CT image of the chest using a convolutional neural network. With the proposed pulmonary embolism detection system, we can detect the possibility of pulmonary embolism at the same time as the patient's first CT image, and schedule the CTPA test immediately, saving more than a week of CT image screening time and providing timely diagnosis and treatment to the patient.

eess.IV↗
arXiv2022

Computerized Tomography Pulmonary Angiography Image Simulation using Cycle Generative Adversarial Network from Chest CT imaging in Pulmonary Embolism Patients

The purpose of this research is to develop a system that generates simulated computed tomography pulmonary angiography (CTPA) images clinically for pulmonary embolism diagnoses. Nowadays, CTPA images are the gold standard computerized detection method to determine and identify the symptoms of pulmonary embolism (PE), although performing CTPA is harmful for patients and also expensive. Therefore, we aim to detect possible PE patients through CT images. The system will simulate CTPA images with deep learning models for the identification of PE patients' symptoms, providing physicians with another reference for determining PE patients. In this study, the simulated CTPA image generation system uses a generative antagonistic network to enhance the features of pulmonary vessels in the CT images to strengthen the reference value of the images and provide a basis for hospitals to judge PE patients. We used the CT images of 22 patients from National Cheng Kung University Hospital and the corresponding CTPA images as the training data for the task of simulating CTPA images and generated them using two sets of generative countermeasure networks. This study is expected to propose a new approach to the clinical diagnosis of pulmonary embolism, in which a deep learning network is used to assist in the complex screening process and to review the generated simulated CTPA images, allowing physicians to assess whether a patient needs to undergo detailed testing for CTPA, improving the speed of detection of pulmonary embolism and significantly reducing the number of undetected patients.

eess.IV↗
arXiv2022

Feature-enhanced Adversarial Semi-supervised Semantic Segmentation Network for Pulmonary Embolism Annotation

This study established a feature-enhanced adversarial semi-supervised semantic segmentation model to automatically annotate pulmonary embolism lesion areas in computed tomography pulmonary angiogram (CTPA) images. In current studies, all of the PE CTPA image segmentation methods are trained by supervised learning. However, the supervised learning models need to be retrained and the images need to be relabeled when the CTPA images come from different hospitals. This study proposed a semi-supervised learning method to make the model applicable to different datasets by adding a small amount of unlabeled images. By training the model with both labeled and unlabeled images, the accuracy of unlabeled images can be improved and the labeling cost can be reduced. Our semi-supervised segmentation model includes a segmentation network and a discriminator network. We added feature information generated from the encoder of segmentation network to the discriminator so that it can learn the similarity between predicted mask and ground truth mask. This HRNet-based architecture can maintain a higher resolution for convolutional operations so the prediction of small PE lesion areas can be improved. We used the labeled open-source dataset and the unlabeled National Cheng Kung University Hospital (NCKUH) (IRB number: B-ER-108-380) dataset to train the semi-supervised learning model, and the resulting mean intersection over union (mIOU), dice score, and sensitivity achieved 0.3510, 0.4854, and 0.4253, respectively on the NCKUH dataset. Then, we fine-tuned and tested the model with a small amount of unlabeled PE CTPA images from China Medical University Hospital (CMUH) (IRB number: CMUH110-REC3-173) dataset. Comparing the results of our semi-supervised model with the supervised model, the mIOU, dice score, and sensitivity improved from 0.2344, 0.3325, and 0.3151 to 0.3721, 0.5113, and 0.4967, respectively.

eess.IV↗
arXiv2022

Convolutional Neural Network for Early Pulmonary Embolism Detection via Computed Tomography Pulmonary Angiography

This study was conducted to develop a computer-aided detection (CAD) system for triaging patients with pulmonary embolism (PE). The purpose of the system was to reduce the death rate during the waiting period. Computed tomography pulmonary angiography (CTPA) is used for PE diagnosis. Because CTPA reports require a radiologist to review the case and suggest further management, this creates a waiting period during which patients may die. Our proposed CAD method was thus designed to triage patients with PE from those without PE. In contrast to related studies involving CAD systems that identify key PE lesion images to expedite PE diagnosis, our system comprises a novel classification-model ensemble for PE detection and a segmentation model for PE lesion labeling. The models were trained using data from National Cheng Kung University Hospital and open resources. The classification model yielded 0.73 for receiver operating characteristic curve (accuracy = 0.85), while the mean intersection over union was 0.689 for the segmentation model. The proposed CAD system can distinguish between patients with and without PE and automatically label PE lesions to expedite PE diagnosis

eess.IV↗
arXiv2021

The interpretation of endobronchial ultrasound image using 3D convolutional neural network for differentiating malignant and benign mediastinal lesions

The purpose of this study is to differentiate malignant and benign mediastinal lesions by using the three-dimensional convolutional neural network through the endobronchial ultrasound (EBUS) image. Compared with previous study, our proposed model is robust to noise and able to fuse various imaging features and spatiotemporal features of EBUS videos. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a diagnostic tool for intrathoracic lymph nodes. Physician can observe the characteristics of the lesion using grayscale mode, doppler mode, and elastography during the procedure. To process the EBUS data in the form of a video and appropriately integrate the features of multiple imaging modes, we used a time-series three-dimensional convolutional neural network (3D CNN) to learn the spatiotemporal features and design a variety of architectures to fuse each imaging mode. Our model (Res3D_UDE) took grayscale mode, Doppler mode, and elastography as training data and achieved an accuracy of 82.00% and area under the curve (AUC) of 0.83 on the validation set. Compared with previous study, we directly used videos recorded during procedure as training and validation data, without additional manual selection, which might be easier for clinical application. In addition, model designed with 3D CNN can also effectively learn spatiotemporal features and improve accuracy. In the future, our model may be used to guide physicians to quickly and correctly find the target lesions for slice sampling during the inspection process, reduce the number of slices of benign lesions, and shorten the inspection time.

eess.IV↗