Objective: We developed an intelligent assistance system for shoulder ultrasound imaging, incorporating deep-learning algorithms to facilitate standard plane recognition and automatic tissue segmentation of the rotator cuff and its surrounding structures. We evaluated the system's performance using a dedicated data set of rotator cuff ultrasound images to assess its feasibility in clinical practice.
Methods: To fulfill the system's primary functions, we designed a standard plane recognition module based on the ResNet50 network and an automatic tissue segmentation module using the Mask R-CNN model. The modules were trained on carefully curated data sets. The standard plane recognition module automatically identifies a specific standard plane based on the ultrasound image characteristics. The automatic tissue segmentation module effectively delineates and segments anatomical structures within the identified standard plane.
Results: With the use of 59,265 shoulder joint ultrasound images, the standard plane recognition model achieved an impressive recognition accuracy of 94.9% in the test set, with an average precision rate of 96.4%, recall rate of 95.4% and F1 score of 95.9%. The automatic tissue segmentation model, tested on 1886 images, exhibited a commendable average intersection over union value of 96.2%, indicating robustness and accuracy. The model achieved mean intersection over union values exceeding 90.0% for all standard planes, indicating its effectiveness in precisely delineating the anatomical structures.
Conclusion: Our shoulder joint musculoskeletal intelligence system swiftly and accurately identifies standard planes and performs automatic tissue segmentation.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.ultrasmedbio.2023.10.010 | DOI Listing |
Crystals (Basel)
January 2018
National Institute of Standards and Technology (NIST), Boulder, CO 80305, USA.
While GaN nanowires (NWs) offer an attractive architecture for a variety of nanoscale optical, electronic, and mechanical devices, defects such as crystal polarity inversion domains (IDs) can limit device performance. Moreover, the formation of such defects during NW growth is not fully understood. In this study, we use transmission electron microscopy (TEM) and atom probe tomography (APT) to investigate the effects of sub-monolayer contamination at the regrowth interface in GaN NWs grown by selective-area molecular beam epitaxy (MBE).
View Article and Find Full Text PDFJ Magn Reson
January 2025
Center for Pulmonary Imaging Research (CPIR), Division of Pulmonary Medicine Cincinnati Children's Hospital Medical Center Cincinnati OH USA; Department of Pediatrics, University of Cincinnati OH USA; Department of Biomedical Engineering, University of Cincinnati OH USA; Imaging Research Center (IRC), Department of Radiology Cincinnati Children's Hospital Medical Center Cincinnati OH USA. Electronic address:
Harmonizing and validating Xe gas exchange imaging across multiple sites is hampered by a lack of a quantitative standard that 1) displays the unique spectral properties of Xe observed from human subjects in vivo and 2) has short enough T times to enable practical imaging. This work describes and demonstrates the development of two dissolved-phase, thermally polarized phantoms that mimic the in-vivo, red blood cell and membrane resonances of Xe dissolved in human lungs. Following optimization, combinations of two common organic solvents, acetone and dimethyl sulfoxide, resulted in two in-vivo-like dissolved-phase Xe phantoms yielding chemical shifts of 212.
View Article and Find Full Text PDFRev Sci Instrum
January 2025
Indian Institute of Science Education and Research, Thiruvananthapuram, Kerala 695551, India.
Quantum technology exploits fragile quantum electronic phenomena whose energy scales demand ultra-low electron temperature operation. The lack of electron-phonon coupling at cryogenic temperatures makes cooling the electrons down to a few tens of millikelvin a non-trivial task, requiring extensive efforts on thermalization and filtering high-frequency noise. Existing techniques employ bulky and heavy cryogenic metal-powder filters, which prove ineffective at sub-GHz frequency regimes and unsuitable for high-density quantum circuits such as spin qubits.
View Article and Find Full Text PDFBMC Surg
January 2025
Department of Obstetrics and Gynaecology, Krankenhaus Sachsenhausen, Frankfurt Am Main, Germany.
Background: Total laparoscopic hysterectomy (TLH) is nowadays the standard to treat benign and malignant disease occurring in the uterus, but the number of robotic-assisted surgeries is increasing worldwide. To facilitate the handling of sutures in a bi- and tri-dimensional plane, a new type of suture material has been developed, named barbed sutures, which are in use in different indications. In comparison to conventional suture materials, the barbs anchor the suture in the tissue, provide tissue approximation and prevent slippage without the need for knot tying.
View Article and Find Full Text PDFAJNR Am J Neuroradiol
January 2025
From the Department of Radiology, Medical Physics (MML, TJC), Department of Interventional Radiology (NS, GAC), Department of Surgery and Large Animal Studies (MAN), and the Department of Statistics (MG), University of Chicago, Chicago, IL, USA; Department of Anesthesiology (SPR), University of Illinois, Chicago, IL, USA; Department of Radiology (MSS), University of Massachusetts Chan Medical School, Worcester, MA, USA; Department of Radiology, Biomedical Engineering and Imaging Institute (Current affiliation MML), Icahn School of Medicine at Mount Sinai, New York, NY, USA; Mount Carmel Health Systems (Current affiliation GAC), Columbus, OH, USA.
Background And Purpose: In acute ischemic stroke, the amount of "local" CBF distal to the occlusion, i.e. all blood flow within a region whether supplied antegrade or delayed and dispersed through the collateral network, may contain valuable information regarding infarct growth rate and treatment response.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!