Toward Automated Tissue Classification For Markerless Orthopaedic Robotic Assistance

• doi: 10.1109/TMRB.2020.3031716
• title: Toward Automated Tissue Classification for Markerless Orthopaedic Robotic Assistance
• publisher: IEEE
• isbn:
• issn: 2576-3202
• rank: 3875
• access_type: LOCKED
• content_type: Journals
• abstract: A markerless computer aided orthopaedic platform will require a complex computer vision system to isolate and track rigid bodies used to localize a robot to a patient. Isolating rigid bodies such as bone requires accurate segmentation and this study explores using diffuse laser reflectivity to accurately classify tissue. Lasers (red at 650nm and infrared – IR – at 850nm) intersected four material types; cartilage, ligament, muscle and metal surgical tools within a controlled cadaveric setup. Images were captured with an infrared CMOS sensor, pre-processed to isolate laser centers, and resized to test information requirements. Images for both laser types were scaled from $5\times5$ pixels to $30\times30$ pixels and trained on a convolutional neural network, GoogLeNet. At sizes above $15\times15$ pixels, the IR laser had a higher classification accuracy, reaching 97.8% at $30\times30$ pixels, whereas the red laser peaked at 94.1%. It was shown as not possible to qualitatively identify materials that were not trained in the network based on their probability outputs. Further work will be performed to classify multiple points in a single scene as a step toward segmenting entire surgical views for markerless Computer Assisted Orthopedic Surgery (CAOS) systems.
• article_number: 9226506
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9226506
• html_url: https://ieeexplore.ieee.org/document/9226506/
• abstract_url: https://ieeexplore.ieee.org/document/9226506/
• publication_title: IEEE Transactions on Medical Robotics and Bionics
• conference_location:
• conference_dates:
• publication_number: 8253409
• is_number: 9267756
• publication_year: 2020
• publication_date: Nov. 2020
• start_page: 537
• end_page: 540
• citing_paper_count: 3
• citing_patent_count: 0
• download_count: 345
• insert_date: 20201016
• index_terms:
  • ieee_terms:
    • Biomedical imaging
    • Robot vision systems
    • Machine learning
    • Lasers
    • Machine vision
  • author_terms:
    • Biomedical imaging
    • robot vision systems
    • machine vision
    • machine learning
  • dynamic_index_terms:
    • Tissue Classification
    • Convolutional Neural Network
    • Classification Accuracy
    • Cartilage
    • Ligament
    • Rigid Body
    • Red Laser
    • Computer Vision System
    • Single Scene
    • Infrared Laser
    • Laser Reflection
    • Training Data
    • Pixel Size
    • Information Content
    • Surprisal
    • Spectral Bands
    • Beamwidth
    • Beam Diameter
• authors:
  • Author Name: Stephen G. Laws
    Affiliation: Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
    Author URL: https://ieeexplore.ieee.org/author/37088563094
    ID: 37088563094
    Order: 1
    Author Affiliations:
    • Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
  • Author Name: Spyridon Souipas
    Affiliation: Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
    Author URL: https://ieeexplore.ieee.org/author/37088563388
    ID: 37088563388
    Order: 2
    Author Affiliations:
    • Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
  • Author Name: Brian L. Davies
    Affiliation: Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
    Author URL: https://ieeexplore.ieee.org/author/37331829300
    ID: 37331829300
    Order: 3
    Author Affiliations:
    • Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
  • Author Name: Ferdinando Rodriguez y Baena
    Affiliation: Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.
    Author URL: https://ieeexplore.ieee.org/author/37294842800
    ID: 37294842800
    Order: 4
    Author Affiliations:
    • Mechatronics in Medicine Laboratory, Imperial College London, London, U.K.

Image Sensor

• sensor_type: CMOS
• resolution: 8 megapixels
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

Applications & Benefits

• cell_imaging: Image capture in cadaveric tissue samples for medical research in orthopaedics.
• benefits: Real-time classification of human tissue during surgical procedures.

Supporting Organizations

• supported_by: Imperial College Healthcare Tissue Bank, EPSRC

Manuscript Details

• publication_date: Nov. 2020

Relevancy Score

• score: 9
• missing_fields:
  • fill factor
  • quantum efficiency
  • reading speed
  • temporal noise
  • fixed-pattern noise
  • analog-to-digital conversion
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_24c70048-c902-4233-bc32-4bda95560039-toward_automated_tissue_classification_for_markerless_orthopaedic_robotic_assistance.json