Imaging and Radiation Research最新文献

Performance evaluation of YOLOv5 and YOLOv8 models in car detection YOLOv5 和 YOLOv8 模型在汽车检测中的性能评估

Imaging and Radiation Research Pub Date : 2024-07-01 DOI: 10.24294/irr.v6i2.5757

Fatma Nur Kılıçkaya, Murat Taşyürek, Celal Öztürk

{"title":"Performance evaluation of YOLOv5 and YOLOv8 models in car detection","authors":"Fatma Nur Kılıçkaya, Murat Taşyürek, Celal Öztürk","doi":"10.24294/irr.v6i2.5757","DOIUrl":"https://doi.org/10.24294/irr.v6i2.5757","url":null,"abstract":"Vehicle detection stands out as a rapidly developing technology today and is further strengthened by deep learning algorithms. This technology is critical in traffic management, automated driving systems, security, urban planning, environmental impacts, transportation, and emergency response applications. Vehicle detection, which is used in many application areas such as monitoring traffic flow, assessing density, increasing security, and vehicle detection in automatic driving systems, makes an effective contribution to a wide range of areas, from urban planning to security measures. Moreover, the integration of this technology represents an important step for the development of smart cities and sustainable urban life. Deep learning models, especially algorithms such as You Only Look Once version 5 (YOLOv5) and You Only Look Once version 8 (YOLOv8), show effective vehicle detection results with satellite image data. According to the comparisons, the precision and recall values of the YOLOv5 model are 1.63% and 2.49% higher, respectively, than the YOLOv8 model. The reason for this difference is that the YOLOv8 model makes more sensitive vehicle detection than the YOLOv5. In the comparison based on the F1 score, the F1 score of YOLOv5 was measured as 0.958, while the F1 score of YOLOv8 was measured as 0.938. Ignoring sensitivity amounts, the increase in F1 score of YOLOv8 compared to YOLOv5 was found to be 0.06%.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"105 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141695486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Classification of some epidemics through microscopic images by using deep learning. Comparison 利用深度学习通过显微图像对一些流行病进行分类。比较

Imaging and Radiation Research Pub Date : 2024-05-22 DOI: 10.24294/irr.v6i1.5451

Laura Brito, Roberto Rodríguez

引用次数: 0

Generation of PAS-Stained images of glomerular tissue units using a generative adversarial network with spectral normalization colorization method 利用生成式对抗网络和光谱归一化着色法生成肾小球组织单位的 PAS 染色图像

Imaging and Radiation Research Pub Date : 2024-02-28 DOI: 10.24294/irr.v6i1.4085

Jincheng Peng, Guoyue Chen, K. Saruta, Y. Terata

{"title":"Generation of PAS-Stained images of glomerular tissue units using a generative adversarial network with spectral normalization colorization method","authors":"Jincheng Peng, Guoyue Chen, K. Saruta, Y. Terata","doi":"10.24294/irr.v6i1.4085","DOIUrl":"https://doi.org/10.24294/irr.v6i1.4085","url":null,"abstract":"In recent years, the pathological diagnosis of glomerular diseases typically involves the study of glomerular his-to pathology by specialized pathologists, who analyze tissue sections stained with Periodic Acid-Schiff (PAS) to assess tissue and cellular abnormalities. In recent years, the rapid development of generative adversarial networks composed of generators and discriminators has led to further developments in image colorization tasks. In this paper, we present a generative adversarial network by Spectral Normalization colorization designed for color restoration of grayscale images depicting glomerular cell tissue elements. The network consists of two structures: the generator and the discriminator. The generator incorporates a U-shaped decoder and encoder network to extract feature information from input images, extract features from Lab color space images, and predict color distribution. The discriminator network is responsible for optimizing the generated colorized images by comparing them with real stained images. On the Human Biomolecular Atlas Program (HubMAP)—Hacking the Kidney FTU segmentation challenge dataset, we achieved a peak signal-to-noise ratio of 29.802 dB, along with high structural similarity results as other colorization methods. This colorization method offers an approach to add color to grayscale images of glomerular cell tissue units. It facilitates the observation of physiological information in pathological images by doctors and patients, enabling better pathological-assisted diagnosis of certain kidney diseases.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"89 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140421093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Innovative frontiers: Post-quantum perspectives in healthcare and medical imaging 创新前沿：医疗保健和医学成像中的后量子视角

Imaging and Radiation Research Pub Date : 2024-02-19 DOI: 10.24294/irr.v6i1.3852

D. J. Herzog, Nitsa J Herzog

{"title":"Innovative frontiers: Post-quantum perspectives in healthcare and medical imaging","authors":"D. J. Herzog, Nitsa J Herzog","doi":"10.24294/irr.v6i1.3852","DOIUrl":"https://doi.org/10.24294/irr.v6i1.3852","url":null,"abstract":"The growth of computer power is crucial for the development of contemporary information technologies. Artificial intelligence is a powerful instrument for every aspect of contemporary science, the economy, and society as a whole. Further growth in computing potential opens new prospects for biomedicine and healthcare. The promising works on quantum computing make it possible to increase computing power exponentially. While conventional computing relies on the formula with 2n bits, the simplified vision of quantum computer power is 2N, where N is a number of logical qubits. With thousandfold or more improvements in computing performance, there will be realistic options for quick protein, genes and other organic molecules 3D fold discoveries, empowering pharmaceutics and biomedical research. Personalized blockchain-based healthcare will become a reality. Medical imaging and instant healthcare data analysis will significantly speed up diagnostics and treatment control. Biomedical digital twin usage will give useful tools to any healthcare practitioner, with options for intraoperative AR and VR micro-manipulations. Nanoscale intrabody bots will be instantly customized and AI-controlled. The smart environment will be enriched with multiple sensors and actuators, giving real control of the air, water, food, and physical health factors. All these possibilities are quickly achievable only in the case of realistic quantum computing options. Even with the ability to reach this stage, there will be questions for the stability of post-quantum society: privacy, ethical issues, and quantum computing control uncertainty. General solutions to these queries will give clues for post-quantum healthcare.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"112 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140451388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermal imaging for cancer detection 用于癌症检测的热成像

Imaging and Radiation Research Pub Date : 2023-11-09 DOI: 10.24294/irr.v6i1.2638

Ashwani Kumar Aggarwal

引用次数: 0

Automatic segmentation of intracranial hemorrhage using coarse and fine deep learning models 基于粗、细深度学习模型的颅内出血自动分割

Imaging and Radiation Research Pub Date : 2023-10-31 DOI: 10.24294/irr.v6i1.3088

Abdul Qayyum, Mohamed Khan Afthab Ahamed Khan, Rana Umar Mukhtar, Moona Mazher, Mastaneh Mokayef, Chun Kit Ang, Lim Wei Hong

{"title":"Automatic segmentation of intracranial hemorrhage using coarse and fine deep learning models","authors":"Abdul Qayyum, Mohamed Khan Afthab Ahamed Khan, Rana Umar Mukhtar, Moona Mazher, Mastaneh Mokayef, Chun Kit Ang, Lim Wei Hong","doi":"10.24294/irr.v6i1.3088","DOIUrl":"https://doi.org/10.24294/irr.v6i1.3088","url":null,"abstract":"To save patients’ lives, it is important to go for an early diagnosis of intracranial hemorrhage (ICH). For diagnosing ICH, the widely used method is non-contrast computed tomography (NCCT). It has fast acquisition and availability in medical emergency facilities. To predict hematoma progression and mortality, it is important to estimate the volume of intracranial hemorrhage. Radiologists can manually delineate the ICH region to estimate the hematoma volume. This process takes time and undergoes inter-rater variability. In this research paper, we develop and discuss a fine segmentation model and a coarse model for intracranial hemorrhage segmentations. Basically, two different models are discussed for intracranial hemorrhage segmentation. We trained a 2DDensNet in the first model for coarse segmentation and cascaded the coarse segmentation mask output in the fine segmentation model along with input training samples. A nnUNet model is trained in the second fine stage and will use the segmentation labels of the coarse model with true labels for intracranial hemorrhage segmentation. An optimal performance for intracranial hemorrhage segmentation solution is obtained.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"53 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135976810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The need of a proof-of-concept in artificial intelligence-based health-related quality of life instruments in veterinary medicine 兽医学中基于人工智能的健康相关生命质量仪器的概念验证需求

Imaging and Radiation Research Pub Date : 2023-10-25 DOI: 10.24294/irr.v6i1.2201

Jeff M. Perez

引用次数: 0

Using cloud computing to increase authentication and security in an IoT-enabled cancer predicative model 在支持物联网的癌症预测模型中，使用云计算来提高身份验证和安全性

Imaging and Radiation Research Pub Date : 2023-10-09 DOI: 10.24294/irr.v6i1.2567

Nahla F. Omran

{"title":"Using cloud computing to increase authentication and security in an IoT-enabled cancer predicative model","authors":"Nahla F. Omran","doi":"10.24294/irr.v6i1.2567","DOIUrl":"https://doi.org/10.24294/irr.v6i1.2567","url":null,"abstract":"Cloud computing, machine learning, the Internet of Things, deep learning, and artificial intelligence are used in a variety of areas, including healthcare, transportation, smart cities, and agriculture, to create beneficial results for a variety of challenges in today’s world. This paper focuses on one of these applications in the cloud computing and IoMT domains. Several sensors were implanted in the human body to gather patient-specific information, such as body measurements temp deviations, and many other factors that contribute to changes in blood cells that develop into malignant cells. The major goal of this project is to create a cancer prediction system that uses the IoT to extract information from blood results in order to determine whether they are normal or abnormal. Furthermore, the findings of cancer patients’ blood tests are encrypted and saved in the cloud for quick access by a doctor or healthcare worker through the Internet to handle patient data in a secure manner. The AES technique is used for encryption and decryption in order to offer authentication and security when dealing with cancer patients. Because all of the required cancer treatment information is stored on the cloud, the main focus is on properly handling healthcare data for patients while they are away from home. Using virtual machines, the work completion time is decreased from 450 to 170 min. Simulations are used to test the proposed model’s performance, and the results show that it outperforms alternative options significantly.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135095193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lowering head computed tomography radiation dose for craniosynostosis: An institutional change and review of literature 降低颅缝闭闭的头部计算机断层扫描辐射剂量:制度变化和文献回顾

Imaging and Radiation Research Pub Date : 2023-08-15 DOI: 10.24294/irr.v7i1.2218

Luke Bauerle, Steven H. Lin, Cody Tucker, R. Eskandari

{"title":"Lowering head computed tomography radiation dose for craniosynostosis: An institutional change and review of literature","authors":"Luke Bauerle, Steven H. Lin, Cody Tucker, R. Eskandari","doi":"10.24294/irr.v7i1.2218","DOIUrl":"https://doi.org/10.24294/irr.v7i1.2218","url":null,"abstract":"Definitive diagnosis of Craniosynostosis (CS) with computed tomography (CT) is readily available, however, exposure to ionizing radiation is often a hard stop for parents and practitioners. Lowering head CT radiation exposure helps mitigate risks and improves diagnostic utilization. The purpose of the study is to quantify radiation exposure from head CT in patients with CS using a ‘new’ (ultra-low dose) protocol; compare prior standard CT protocol; summarize published reports on cumulative radiation doses from pediatric head CT scans utilizing other low-dose protocols. A retrospective study was conducted on patients undergoing surgical correction of CS, aged less than 2 years, between August 2014 and February 2022. Cumulative effective dose (CED) in mSv was calculated, descriptive statistics were performed, and mean ± SD was reported. A literature search was conducted describing cumulative radiation exposure from head CT in pediatric patients and analyzed for ionizing radiation measurements. Forty-four patients met inclusion criteria: 17 females and 27 males. Patients who obtained head CT using the ‘New’ protocol resulted in lower CED exposure of 0.32 mSv ± 0.07 compared to the prior standard protocol at 5.25 mSv ± 2.79 (p < 0.0001). Five studies specifically investigated the reduction of ionizing radiation from CT scans in patients with CS via the utilization of low-dose CT protocols. These studies displayed overall CED values ranging from 0.015 mSv to 0.77 mSv. Our new CT protocol resulted in 94% reduction of ionizing radiation. Ultra-low dose CT protocols provide similar diagnostic data without loss of bone differentiation in CS and can be easily incorporated into the workflow of a children’s hospital.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116210371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lowering head computed tomography radiation dose for craniosynostosis: An institutional change and review of literature 降低颅缝闭闭的头部计算机断层扫描辐射剂量:制度变化和文献回顾

Imaging and Radiation Research Pub Date : 2023-08-15 DOI: 10.24294/irr.v6i1.2218

Luke Bauerle, Steven Lin, Cody Tucker, Ramin Eskandari

{"title":"Lowering head computed tomography radiation dose for craniosynostosis: An institutional change and review of literature","authors":"Luke Bauerle, Steven Lin, Cody Tucker, Ramin Eskandari","doi":"10.24294/irr.v6i1.2218","DOIUrl":"https://doi.org/10.24294/irr.v6i1.2218","url":null,"abstract":"Definitive diagnosis of Craniosynostosis (CS) with computed tomography (CT) is readily available, however, exposure to ionizing radiation is often a hard stop for parents and practitioners. Lowering head CT radiation exposure helps mitigate risks and improves diagnostic utilization. The purpose of the study is to quantify radiation exposure from head CT in patients with CS using a ‘new’ (ultra-low dose) protocol; compare prior standard CT protocol; summarize published reports on cumulative radiation doses from pediatric head CT scans utilizing other low-dose protocols. A retrospective study was conducted on patients undergoing surgical correction of CS, aged less than 2 years, between August 2014 and February 2022. Cumulative effective dose (CED) in mSv was calculated, descriptive statistics were performed, and mean ± SD was reported. A literature search was conducted describing cumulative radiation exposure from head CT in pediatric patients and analyzed for ionizing radiation measurements. Forty-four patients met inclusion criteria: 17 females and 27 males. Patients who obtained head CT using the ‘New’ protocol resulted in lower CED exposure of 0.32 mSv ± 0.07 compared to the prior standard protocol at 5.25 mSv ± 2.79 (p < 0.0001). Five studies specifically investigated the reduction of ionizing radiation from CT scans in patients with CS via the utilization of low-dose CT protocols. These studies displayed overall CED values ranging from 0.015 mSv to 0.77 mSv. Our new CT protocol resulted in 94% reduction of ionizing radiation. Ultra-low dose CT protocols provide similar diagnostic data without loss of bone differentiation in CS and can be easily incorporated into the workflow of a children’s hospital.","PeriodicalId":153727,"journal":{"name":"Imaging and Radiation Research","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135114267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0