Portable ultrasound scanner for remote diagnosis

Ramesh, B.; Dusa, Chandrashekar; Akkala, Vivek; Krishna, D. V.; Ponduri, Harsha; Rajalakshmi, P.; Desai, U.B.

doi:10.1109/healthcom.2015.7454500

Cited by 5 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Step 4, the DL-CAD model uses CID H i to download the desensitized dataset and returns the diagnosis results to the hospital through the IPFS and a new unique CID M i . This framework is also helpful for individuals, such as when uploading a single pathological image and safely obtaining a diagnosis suggestion if they have an IoMT, e.g., a portable or ultraportable ultrasound scanner [35,36] , or checking their relevant medical history if they had ever changed a hospital. A detailed demonstration of this framework and examples of how it works can be found in the supplementary video.…”

Section: Deep Learning Blockchain Frameworkmentioning

confidence: 99%

Deep Learning Blockchain Integration Framework for Ureteropelvic Junction Obstruction Diagnosis Using Ultrasound Images

Guan,

Wen,

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

UreteroPelvic Junction Obstruction (UPJO) is a common hydronephrosis disease in children that can result in an even progressive loss of renal function. Ultrasonography is an economical, radiationless, noninvasive, and high noise preliminary diagnostic step for UPJO. Artificial intelligence has been widely applied to medical fields and can greatly assist doctors' diagnostic abilities. The demand for a highly secure network environment in transferring electronic medical data online, therefore, has led to the development of blockchain technology. In this study, we built and tested a framework that integrates a deep learning diagnosis model with blockchain technology. Our diagnosis model is a combination of an attention-based pyramid semantic segmentation network and a discrete wavelet transformation-processed residual classification network. We also compared the performance between benchmark models and our models. Our diagnosis model outperformed benchmarks on the segmentation task and classification task with MIoU = 87.93, MPA = 93.52, and accuracy = 91.77%. For the blockchain system, we applied the InterPlanetary File System protocol to build a secure and private sharing environment. This framework can automatically grade the severity of UPJO using ultrasound images, guarantee secure medical data sharing, assist in doctors' diagnostic ability, relieve patients' burden, and provide technical support for future federated learning and linkage of the Internet of Medical Things (IoMT).

show abstract

Section: Deep Learning Blockchain Frameworkmentioning

confidence: 99%

Deep Learning Blockchain Integration Framework for Ureteropelvic Junction Obstruction Diagnosis Using Ultrasound Images

Guan,

Wen,

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Two portable hand held ultrasound systems (Mindray DP-6600 FL, USA) were used in this study, one for each site. The device's manufacturer has indicated eFAST as one of its uses [19] and has been validated in previous studies [20] in addition to being suitable in rural areas where there could be electricity blackouts [21].…”

Section: Data Collection Proceduresmentioning

confidence: 99%

Efficacy of extended focused assessment with sonography for trauma using a portable handheld device for detecting hemothorax in a low resource setting; a multicenter longitudinal study

et al. 2022

View full text Add to dashboard Cite

Introduction Chest trauma is one of the most important and commonest injuries that require timely diagnosis, accounting for 25–50% of trauma related deaths globally. Although CT scan is the gold standard for detection of haemothorax, it is only useful in stable patients, and remains unavailable in most hospitals in low income countries. Where available, it is very expensive. Sonography has been reported to have high accuracy and sensitivity in trauma diagnosis but is rarely used in trauma patients in low income settings in part due to lack of the sonography machines and lack of expertise among trauma care providers. Chest X-ray is the most available investigation for chest injuries in low income countries. However it is not often safe to wheel seriously injured, unstable trauma patients to X-ray rooms. This study aimed at determining the efficacy of extended focused assessment with sonography for trauma (eFAST) in detection of haemothorax using thoracostomy findings as surrogate gold standard in a low resource setting. Methods This was an observational longitudinal study that enrolled 104 study participants with chest trauma. Informed consent was obtained from all participants. A questionnaire was administered and eFAST, chest X-ray and tube thoracotomy were done as indicated. Data were analysed using SPSS version 22. The sensitivity, specificity, predictive values, accuracy and area under the curve were determined using thoracostomy findings as the gold standard. Ethical approval for the study was obtained from the Research and Ethics Committee of Kampala International University Western Campus REC number KIU-2021-53. Results eFAST was found to be superior to chest X-ray with sensitivity of 96.1% versus 45.1% respectively. The accuracy was also higher for eFAST (96.4% versus 49.1%) but the specificity was the same at 100.0%. The area under the curve was higher for eFAST (0.980, P = 0.001 versus 0.725, P = 0.136). Combining eFAST and X-ray increased both sensitivity and accuracy. Conclusion This study revealed that eFAST was more sensitive at detecting haemothorax among chest trauma patients compared to chest X-ray. All patients presenting with chest trauma should have bedside eFAST for diagnosis of haemothorax.

show abstract

WebRTC based invariant scattering convolution network for automated validation of ultrasonic videos for IoT enabled tele-sonography

Ramesh

Rajalakshmi

2018

2018 IEEE 4th World Forum on Internet of Things (WF-IoT)

View full text Add to dashboard Cite

Portable ultrasound scanner for remote diagnosis

Cited by 5 publications

References 6 publications

Deep Learning Blockchain Integration Framework for Ureteropelvic Junction Obstruction Diagnosis Using Ultrasound Images

Deep Learning Blockchain Integration Framework for Ureteropelvic Junction Obstruction Diagnosis Using Ultrasound Images

Efficacy of extended focused assessment with sonography for trauma using a portable handheld device for detecting hemothorax in a low resource setting; a multicenter longitudinal study

WebRTC based invariant scattering convolution network for automated validation of ultrasonic videos for IoT enabled tele-sonography

Contact Info

Product

Resources

About