Biocybernetics and Biomedical Engineering最新文献_第7页

System and approach to detecting of gastric slow wave and environmental noise suppression based on optically pumped magnetometer 基于光泵磁力计的胃慢波检测和环境噪声抑制系统与方法

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-12-06 DOI: 10.1016/j.bbe.2023.11.004

Shuang Liang , Kexin Gao , Junhuai He , Yikang Jia , Hongchen Jiao , Lishuang Feng

{"title":"System and approach to detecting of gastric slow wave and environmental noise suppression based on optically pumped magnetometer","authors":"Shuang Liang , Kexin Gao , Junhuai He , Yikang Jia , Hongchen Jiao , Lishuang Feng","doi":"10.1016/j.bbe.2023.11.004","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.11.004","url":null,"abstract":"<div><p><span>Gastric slow waves (SWs) are commonly used for the quantitative assessment of gastric functional disorders. Compared with surface electrogastrography, using of magnetic signals to record SWs can achieve higher-quality signal recording. In this study, we discovered that optically pumped </span>magnetometers<span><span> (OPM) based on the spin exchange relaxation-free method have comparable weak magnetic detection capabilities to superconducting quantum interference devices but without liquid helium cooling. However, owing to the inevitable interference of low-frequency environmental drift, the characteristic features of SW are obscured, greatly increasing the difficulty in detecting gastric magnetic signals. Therefore, in this study, we constructed an OPM Magnetogastrography (OPM-MGG). We proposed an </span>adaptive filtering<span><span> architecture combined with environmental drift suppression and a non-stationary signal decomposition method<span> for extracting SW signals. Through controlled human experiments, the results demonstrated that our testing system successfully extracted SW signals in the frequency range of 2–4 cycles per minute. The extracted SW signals exhibited consistent power and time–frequency characteristics with the reported results. This study validates the feasibility of (1) using the OPM-MGG system for capturing SW signals and (2) the proposed processing strategies for identifying ultralow-frequency SW signals. In conclusion, the OPM-MGG system and the signal extraction strategies developed in this study have the potential to provide a wearable technology for bioweak </span></span>magnetic field measurements, offering new opportunities for both research and clinical applications.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138490667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel deep learning-based approach for prediction of neonatal respiratory disorders from chest X-ray images 一种基于深度学习的胸部X射线图像预测新生儿呼吸系统疾病的新方法

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.08.004

Ayse Erdogan Yildirim , Murat Canayaz

{"title":"A novel deep learning-based approach for prediction of neonatal respiratory disorders from chest X-ray images","authors":"Ayse Erdogan Yildirim , Murat Canayaz","doi":"10.1016/j.bbe.2023.08.004","DOIUrl":"10.1016/j.bbe.2023.08.004","url":null,"abstract":"<div><p><span>In recent years, many diseases can be diagnosed in a short time with the use of deep learning models in the field of medicine. Most of the studies in this area focus on adult or </span>pediatric patients<span><span><span>. However, deep learning studies for the diagnosis of diseases in neonatal are not sufficient. Also, since it is known that respiratory disorders such as pneumonia have a large place among the causes of neonatal death, early and accurate diagnosis of respiratory diseases in neonates is crucial. For this reason, our study aims to detect the presence of respiratory disorders through the developed deep-learning approach using chest X-ray images of patients hospitalized in the Neonatal </span>Intensive Care Unit. Accordingly, the enhanced version of C+EffxNet, the new hybrid deep learning model, is designed to predict respiratory disorders in neonates. In this version, the features selected by </span>PCA<span> are combined as 100, 200, and 300, then the binary classification process was carried out. In the study, the accuracy and kappa value were obtained as 0.965, and 0.904, respectively before feature merging, while these values were obtained as 0.977, and 0.935 after feature merging. This method, which was developed for the diagnosis of respiratory disorders in neonates, was also subsequently applied to a chest X-ray dataset that is frequently used in the literature for the diagnosis of pediatric pneumonia. For this data set, while the accuracy was 0.992, the kappa value was 0.982. The results obtained confirm the success of the proposed method for both datasets.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49483878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Surgical phase classification and operative skill assessment through spatial context aware CNNs and time-invariant feature extracting autoencoders 基于空间上下文感知cnn和时不变特征提取自编码器的手术阶段分类和手术技能评估

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.001

Chakka Sai Pradeep, Neelam Sinha

{"title":"Surgical phase classification and operative skill assessment through spatial context aware CNNs and time-invariant feature extracting autoencoders","authors":"Chakka Sai Pradeep, Neelam Sinha","doi":"10.1016/j.bbe.2023.10.001","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.10.001","url":null,"abstract":"<div><p>Automated surgical video analysis promises improved healthcare. We propose novel spatial context aware combined loss function for end-to-end Encoder-Decoder training for Surgical Phase Classification (SPC) on laparoscopic cholecystectomy (LC) videos. Proposed loss function leverages on fine-grained class activation maps obtained from fused multi-layer Layer-CAM for supervised learning of SPC, obtaining improved Layer-CAM explanations. Post classification, we introduce graph theory to incorporate known hierarchies of surgical phases. We report peak SPC accuracy of 96.16%, precision of 94.08% and recall of 90.02% on public dataset Cholec80, with 7 phases. Our proposed method utilizes just 73.5% of parameters as against existing state-of-the-art methodology, achieving improvement of 0.5% in accuracy, 1.76% in precision with comparable recall, with an order less standard deviation. We also propose DNN based surgical skill assessment methodology. This approach utilizes surgical phase prediction scores from the final fully-connected layer of spatial-context aware classifier to form multi-channel temporal signal of surgical phases. Time-invariant representation is obtained from this temporal signal through time- and frequency-domain analyses. Autoencoder based time-invariant features are utilized for reconstruction and identification of prominent peaks in dissimilarity curves. We devise a surgical skill measure (SSM) based on spatial-context aware temporal-prominence-of-peaks curve. SSM values are expected to be high when executed skillfully, aligning with expert assessed GOALS metric. We illustrate this trend on Cholec80 and m2cai16-tool datasets, in comparison with GOALS metric. Concurrence in the trend of SSM with respect to GOALS metric is obtained on these test videos, making it a promising step towards automated surgical skill assessment.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block 基于偶极子特征成像和嵌入挤压-激励块的混合CNN的运动图像解码

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.004

Linlin Wang , Mingai Li

{"title":"Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block","authors":"Linlin Wang , Mingai Li","doi":"10.1016/j.bbe.2023.10.004","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.10.004","url":null,"abstract":"<div><p><span><span>Motor imagery (MI) decoding is the core of an intelligent rehabilitation system in brain computer interface<span>, and it has a potential advantage by using source signals, which have higher spatial resolution and the same time resolution compared to scalp electroencephalography (EEG). However, how to delve and utilize the personalized frequency characteristic of dipoles for improving decoding performance has not been paid sufficient attention. In this paper, a novel dipole feature imaging (DFI) and a hybrid </span></span>convolutional neural network (HCNN) with an embedded squeeze-and-excitation block (SEB), denoted as DFI-HCNN, are proposed for decoding MI tasks. EEG source </span>imaging technique<span><span><span> is used for brain source estimation, and each sub-band spectrum powers of all dipoles are calculated through frequency analysis and band division. Then, the 3D space information of dipoles is retrieved, and by using azimuthal equidistant projection algorithm it is transformed to a </span>2D plane, which is combined with </span>nearest neighbor interpolation to generate multi sub-band dipole feature images. Furthermore, a HCNN is designed and applied to the ensemble of sub-band dipole feature images, from which the importance of sub-bands is acquired to adjust the corresponding attentions adaptively by SEB. Ten-fold cross-validation experiments on two public datasets achieve the comparatively higher decoding accuracies of 84.23% and 92.62%, respectively. The experiment results show that DFI is an effective feature representation, and HCNN with an embedded SEB can enhance the useful frequency information of dipoles for improving MI decoding.</span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138423191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated detection of crystalline retinopathy via fundus photography using multistage generative adversarial networks 利用多阶段生成对抗网络通过眼底摄影自动检测结晶性视网膜病变

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.005

Eun Young Choi , Seung Hoon Han , Ik Hee Ryu , Jin Kuk Kim , In Sik Lee , Eoksoo Han , Hyungsu Kim , Joon Yul Choi , Tae Keun Yoo

{"title":"Automated detection of crystalline retinopathy via fundus photography using multistage generative adversarial networks","authors":"Eun Young Choi , Seung Hoon Han , Ik Hee Ryu , Jin Kuk Kim , In Sik Lee , Eoksoo Han , Hyungsu Kim , Joon Yul Choi , Tae Keun Yoo","doi":"10.1016/j.bbe.2023.10.005","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.10.005","url":null,"abstract":"<div><h3>Purpose</h3><p>Crystalline retinopathy is characterized by reflective crystal deposits in the macula and is caused by various systemic conditions including hereditary, toxic, and embolic etiologies. Herein, we introduce a novel application of deep learning with a multistage generative adversarial network (GAN) to detect crystalline retinopathy using fundus photography.</p></div><div><h3>Methods</h3><p>The dataset comprised major classes (healthy retina, diabetic retinopathy, exudative age-related macular degeneration, and drusen) and a crystalline retinopathy class (minor set). To overcome the limited data on crystalline retinopathy, we proposed a novel multistage GAN framework. The GAN was retrained after CutMix combination by inputting the GAN-generated synthetic data as new inputs to the original training data. After the multistage CycleGAN augmented the data for crystalline retinopathy, we built a deep-learning classifier model for detection.</p></div><div><h3>Results</h3><p>Using the multistage CycleGAN facilitated realistic fundus photography synthesis with the characteristic features of retinal crystalline deposits. The proposed method outperformed typical transfer learning, prototypical networks, and knowledge distillation for both multiclass and binary classifications. The final model achieved an area under the curve of the receiver operating characteristics of 0.962 for internal validation and 0.987 for external validation for the detection of crystalline retinopathy.</p></div><div><h3>Conclusion</h3><p>We introduced a deep learning approach for detecting crystalline retinopathy, a potential biomarker of underlying systemic pathological conditions. Our approach enables realistic pathological image synthesis and more accurate prediction of crystalline retinopathy, an essential but minor retinal condition.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91993363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

End-to end decision support system for sleep apnea detection and Apnea-Hypopnea Index calculation using hybrid feature vector and Machine learning 基于混合特征向量和机器学习的睡眠呼吸暂停检测和呼吸暂停低通气指数计算的端到端决策支持系统

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.002

Recep Sinan Arslan , Hasan Ulutas , Ahmet Sertol Köksal , Mehmet Bakir , Bülent Çiftçi

{"title":"End-to end decision support system for sleep apnea detection and Apnea-Hypopnea Index calculation using hybrid feature vector and Machine learning","authors":"Recep Sinan Arslan , Hasan Ulutas , Ahmet Sertol Köksal , Mehmet Bakir , Bülent Çiftçi","doi":"10.1016/j.bbe.2023.10.002","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.10.002","url":null,"abstract":"<div><p>Sleep apnea is a disease that occurs due to the decrease in oxygen saturation in the blood and directly affects people's lives. Detection of sleep apnea is crucial for assessing sleep quality. It is also an important parameter in the diagnosis of various other diseases (diabetes, chronic kidney disease, depression, and cardiological diseases). Recent studies show that detection of sleep apnea can be done via signal processing, especially EEG and ECG signals. However, the detection accuracy needs to be improved. In this paper, a ML model is used for the detection of sleep apnea using 19 static sensor data and 2 dynamic data (Sleep score and Arousal). The sensor data is recorded as a discrete signal and the sleep process is divided into 4.8 M segments. In this work, 19 different sensor data sets were recorded with polysomnography (PSG). These data sets have been used to perform sleep scoring. Then, arousal status marking is done. Model training was carried out with the feature vector consisting of 21 data obtained. Tests were performed with eight different machine learning techniques on a unique dataset consisting of 113 patients. After all, it was automatically determined whether people were diseased (a kind of apnea) or healthy. The proposed model had an average accuracy of 97.27%, while the recall, precision, and f-score values were 99.18%, 95.32%, and 97.20%, respectively. After all, the model that less feature engineering, less complex classification model, higher dataset usage, and higher classification performance has been revealed.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49766939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to “Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images” [Biocybern. Biomed. Eng. 43(3) (2023) 586–602] 用于超声图像中前列腺精确分割的多级全卷积网络》[Biocybern. Biomed. Eng. 43(3) (2023) 586-602] 更正

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.003

Yujie Feng , Chukwuemeka Clinton Atabansi , Jing Nie , Haijun Liu , Hang Zhou , Huai Zhao , Ruixia Hong , Fang Li , Xichuan Zhou

引用次数: 0

Simulation on human respiratory motion dynamics and platform construction 人体呼吸运动动力学仿真及平台搭建

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.09.002

Yudong Bao , Xu Li , Wen Wei , Shengquan Qu , Yang Zhan

{"title":"Simulation on human respiratory motion dynamics and platform construction","authors":"Yudong Bao , Xu Li , Wen Wei , Shengquan Qu , Yang Zhan","doi":"10.1016/j.bbe.2023.09.002","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.09.002","url":null,"abstract":"<div><p><span>Bronchoscopy has a crucial role in the current treatment of lung diseases, and it is typical of interventional medical instruments led by manual intervention. The scientific study of bronchoscopy is now of primary importance in eliminating problems associated with manual intervention by scientific means. However, for its intervention environment, the trachea is often treated statically, without considering the effect of tracheal deformation on bronchoscopic intervention during respiratory motion. Therefore its findings can deviate from practical application. Thus, studying kinetic problems in respiratory motion is of great importance. This paper developed a mathematical model of </span>mechanical properties<span> of respiratory motion to express respiratory force from the perspective of dynamics of respiratory motion. The dynamical model<span><span><span> was solved using MATLAB. Then, a </span>finite element model of respiratory motion was built using Mimics, and the results of respiratory force solution were used as the load of model for dynamics simulation in ABAQUS. Then, a human–computer interaction platform was designed in MATLAB APP Designer to realize </span>parametric<span> calculation and fitting of respiratory force, and a personalized human respiratory motion dynamics simulation was completed in conjunction with ABAQUS. Finally, experimental validation of the interactive platform was performed using pulmonary function test data from three patients. Validation analysis by respiration striving solution, kinetic simulation and experiment found that Dynamical model and simulation results can be better adapted to the individualized study of human respiratory motion dynamics.</span></span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134657766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A dual-stage transformer and MLP-based network for breast ultrasound image segmentation 基于双级变压器和mlp网络的乳腺超声图像分割

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.09.001

Guidi Lin , Mingzhi Chen , Minsheng Tan , Lingna Chen , Junxi Chen

{"title":"A dual-stage transformer and MLP-based network for breast ultrasound image segmentation","authors":"Guidi Lin , Mingzhi Chen , Minsheng Tan , Lingna Chen , Junxi Chen","doi":"10.1016/j.bbe.2023.09.001","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.09.001","url":null,"abstract":"<div><p><span>Automatic segmentation of breast lesions from ultrasound images plays an important role in computer-aided breast cancer diagnosis. Many deep learning<span> methods based on convolutional neural networks (CNNs) have been proposed for </span></span>breast ultrasound<span> image segmentation. However, breast ultrasound image segmentation is still challenging due to ambiguous lesion boundaries. We propose a novel dual-stage framework based on Transformer and Multi-layer perceptron<span><span><span> (MLP) for the segmentation of breast lesions. We combine the Swin Transformer block with an efficient pyramid squeezed attention block in a parallel design and introduce bi-directional interactions across branches, which can efficiently extract multi-scale long-range dependencies to improve the segmentation performance and robustness of the model. Furthermore, we introduce tokenized MLP block in the MLP stage to extract global contextual information while retaining fine-grained information to segment more complex breast lesions. We have conducted extensive experiments with state-of-the-art methods on three breast ultrasound datasets, including BUSI, BUL, and MT_BUS datasets. The dice coefficient reached 0.8127 ± 0.2178, and the intersection over union reached 0.7269 ± 0.2370 on </span>benign lesions<span> when the Hausdorff distance was maintained at 3.75 ± 1.83. The dice coefficient of malignant lesions is improved by 3.09% for BUSI dataset. The segmentation results on the BUL and MT_BUS datasets also show that our proposed model achieves better segmentation results than other methods. Moreover, the external experiments indicate that the proposed model provides better generalization capability for breast lesion segmentation. The dual-stage scheme and the proposed Transformer module achieve the fine-grained local information and long-range dependencies to relieve the burden of </span></span>radiologists.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated detection of multi-class urinary sediment particles: An accurate deep learning approach 多类尿液沉淀物颗粒的自动检测:一种精确的深度学习方法

IF 6.4 2区医学

Biocybernetics and Biomedical Engineering Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.09.003

He Lyu , Fanxin Xu , Tao Jin , Siyi Zheng , Chenchen Zhou , Yang Cao , Bin Luo , Qinzhen Huang , Wei Xiang , Dong Li

{"title":"Automated detection of multi-class urinary sediment particles: An accurate deep learning approach","authors":"He Lyu , Fanxin Xu , Tao Jin , Siyi Zheng , Chenchen Zhou , Yang Cao , Bin Luo , Qinzhen Huang , Wei Xiang , Dong Li","doi":"10.1016/j.bbe.2023.09.003","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.09.003","url":null,"abstract":"<div><p>Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0