Jorden Hetherington1, Victoria Lessoway2, Vit Gunka3, Purang Abolmaesumi4, Robert Rohling4,5. 1. Department of Electrical and Computer Engineering, The University of British Columbia, 2332 Main Mall, Vancouver, BC, V6T 1Z4, Canada. jordenh@ece.ubc.ca. 2. Department of Ultrasound, BC Women's Hospital, 4500 Oak Street, Vancouver, BC, V6H 3N1, Canada. 3. Department of Obstetric Anesthesia, BC Women's Hospital, 4500 Oak Street, Vancouver, BC, V6H 3N1, Canada. 4. Department of Electrical and Computer Engineering, The University of British Columbia, 2332 Main Mall, Vancouver, BC, V6T 1Z4, Canada. 5. Department of Mechanical Engineering, The University of British Columbia, 2332 Main Mall, Vancouver, BC, V6T 1Z4, Canada.
Abstract
PURPOSE: Percutaneous spinal needle insertion procedures often require proper identification of the vertebral level to effectively and safely deliver analgesic agents. The current clinical method involves "blind" identification of the vertebral level through manual palpation of the spine, which has only 30% reported accuracy. Therefore, there is a need for better anatomical identification prior to needle insertion. METHODS: A real-time system was developed to identify the vertebral level from a sequence of ultrasound images, following a clinical imaging protocol. The system uses a deep convolutional neural network (CNN) to classify transverse images of the lower spine. Several existing CNN architectures were implemented, utilizing transfer learning, and compared for adequacy in a real-time system. In the system, the CNN output is processed, using a novel state machine, to automatically identify vertebral levels as the transducer moves up the spine. Additionally, a graphical display was developed and integrated within 3D Slicer. Finally, an augmented reality display, projecting the level onto the patient's back, was also designed. A small feasibility study [Formula: see text] evaluated performance. RESULTS: The proposed CNN successfully discriminates ultrasound images of the sacrum, intervertebral gaps, and vertebral bones, achieving 88% 20-fold cross-validation accuracy. Seventeen of 20 test ultrasound scans had successful identification of all vertebral levels, processed at real-time speed (40 frames/s). CONCLUSION: A machine learning system is presented that successfully identifies lumbar vertebral levels. The small study on human subjects demonstrated real-time performance. A projection-based augmented reality display was used to show the vertebral level directly on the subject adjacent to the puncture site.
PURPOSE: Percutaneous spinal needle insertion procedures often require proper identification of the vertebral level to effectively and safely deliver analgesic agents. The current clinical method involves "blind" identification of the vertebral level through manual palpation of the spine, which has only 30% reported accuracy. Therefore, there is a need for better anatomical identification prior to needle insertion. METHODS: A real-time system was developed to identify the vertebral level from a sequence of ultrasound images, following a clinical imaging protocol. The system uses a deep convolutional neural network (CNN) to classify transverse images of the lower spine. Several existing CNN architectures were implemented, utilizing transfer learning, and compared for adequacy in a real-time system. In the system, the CNN output is processed, using a novel state machine, to automatically identify vertebral levels as the transducer moves up the spine. Additionally, a graphical display was developed and integrated within 3D Slicer. Finally, an augmented reality display, projecting the level onto the patient's back, was also designed. A small feasibility study [Formula: see text] evaluated performance. RESULTS: The proposed CNN successfully discriminates ultrasound images of the sacrum, intervertebral gaps, and vertebral bones, achieving 88% 20-fold cross-validation accuracy. Seventeen of 20 test ultrasound scans had successful identification of all vertebral levels, processed at real-time speed (40 frames/s). CONCLUSION: A machine learning system is presented that successfully identifies lumbar vertebral levels. The small study on human subjects demonstrated real-time performance. A projection-based augmented reality display was used to show the vertebral level directly on the subject adjacent to the puncture site.
Authors: Hedyeh Rafii-Tari; Victoria A Lessoway; Allaudin A Kamani; Purang Abolmaesumi; Robert Rohling Journal: Ultrasound Med Biol Date: 2015-05-08 Impact factor: 2.998
Authors: Denis Tran; Allaudin A Kamani; Victoria A Lessoway; Carly Peterson; King Wei Hor; Robert N Rohling Journal: Anesth Analg Date: 2009-08 Impact factor: 5.108
Authors: Valentina Bellini; Emanuele Rafano Carnà; Michele Russo; Fabiola Di Vincenzo; Matteo Berghenti; Marco Baciarello; Elena Bignami Journal: Ann Transl Med Date: 2022-05