{"id":2479,"date":"2024-05-03T20:49:24","date_gmt":"2024-05-03T20:49:24","guid":{"rendered":"https:\/\/labs.cs.queensu.ca\/perklab\/members\/christina-yan\/"},"modified":"2024-05-03T20:49:24","modified_gmt":"2024-05-03T20:49:24","slug":"christina-yan","status":"publish","type":"qsc_member","link":"https:\/\/labs.cs.queensu.ca\/perklab\/members\/christina-yan\/","title":{"rendered":"Christina Yan"},"content":{"rendered":"
\n
\n\t\t\n\t<\/div>\n
\n
\n

Christina Yan<\/h1>\n<\/div>\n
Undergraduate Student<\/div>\n
School of Computing<\/div>\n
Queen’s University<\/div>\n
Member from 2015<\/em> to 2019<\/em><\/div>\n
\n
\n\t\t\t<\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n
\n\tChristina started as a freshmen biomedical computing student at Queen’s. Her research projects have included ultrasound guided scoliosis monitoring and computer-aided navigation for breast cancer surgery. Having done a full-year industrial internship, she returned to the Perk Lab in Fall 2018 for doing her BSc hon’s thesis on develpment of a computer-assisted training system for endoscpic vein harvesting, co-supervised in the Perk Lab and in the Department of Surgery.
\n
<\/a><\/form>

Kamali, Shahrokh; Ungi, Tamas; Lasso, Andras; Yan, Christina; Lougheed, Matthew; Fichtinger, Gabor<\/p>

Localization of the transverse processes in ultrasound for spinal curvature measurement<\/a> Conference<\/span> <\/p>

SPIE Medical Imaging, <\/span>vol. 10135, <\/span>2017<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{Kamali2017a,
\r\ntitle = {Localization of the transverse processes in ultrasound for spinal curvature measurement},
\r\nauthor = {Shahrokh Kamali and Tamas Ungi and Andras Lasso and Christina Yan and Matthew Lougheed and Gabor Fichtinger},
\r\nurl = {http:\/\/proceedings.spiedigitallibrary.org\/proceeding.aspx?articleid=2615387
\r\nhttps:\/\/labs.cs.queensu.ca\/perklab\/wp-content\/uploads\/sites\/3\/2024\/02\/Kamali2017a.pdf},
\r\ndoi = {10.1117\/12.2256007},
\r\nyear  = {2017},
\r\ndate = {2017-02-01},
\r\nurldate = {2017-02-01},
\r\nbooktitle = {SPIE Medical Imaging},
\r\nvolume = {10135},
\r\npages = {101350I-101350I-7},
\r\nabstract = {<p>PURPOSE: In scoliosis monitoring, tracked ultrasound has been explored as a safer imaging alternative to traditional radiography. The use of ultrasound in spinal curvature measurement requires identification of vertebral landmarks such as transverse processes, but as bones have reduced visibility in ultrasound imaging, skeletal landmarks are typically segmented manually, which is an exceedingly laborious and long process. We propose an automatic algorithm to segment and localize the surface of bony areas in the transverse process for scoliosis in ultrasound.METHODS: The algorithm uses cascade of filters to remove low intensity pixels, smooth the image and detect bony edges. By applying first differentiation, candidate bony areas are classified. The average intensity under each area has a correlation with the possibility of a shadow, and areas with strong shadow are kept for bone segmentation. The segmented images are used to reconstruct a 3-D volume to represent the whole spinal structure around the transverse processes. RESULTS: A comparison between the manual ground truth segmentation and the automatic algorithm in 50 images showed 0.17 mm average difference. The time to process all 1,938 images was about 37 Sec. (0.0191 Sec. \/ Image), including reading the original sequence file.CONCLUSION: Initial experiments showed the algorithm to be sufficiently accurate and fast for segmentation transverse processes in ultrasound for spinal curvature measurement. An extensive evaluation of the method is currently underway on images from a larger patient cohort and using multiple observers in producing ground truth segmentation.<\/p>},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
<p>PURPOSE: In scoliosis monitoring, tracked ultrasound has been explored as a safer imaging alternative to traditional radiography. The use of ultrasound in spinal curvature measurement requires identification of vertebral landmarks such as transverse processes, but as bones have reduced visibility in ultrasound imaging, skeletal landmarks are typically segmented manually, which is an exceedingly laborious and long process. We propose an automatic algorithm to segment and localize the surface of bony areas in the transverse process for scoliosis in ultrasound.METHODS: The algorithm uses cascade of filters to remove low intensity pixels, smooth the image and detect bony edges. By applying first differentiation, candidate bony areas are classified. The average intensity under each area has a correlation with the possibility of a shadow, and areas with strong shadow are kept for bone segmentation. The segmented images are used to reconstruct a 3-D volume to represent the whole spinal structure around the transverse processes. RESULTS: A comparison between the manual ground truth segmentation and the automatic algorithm in 50 images showed 0.17 mm average difference. The time to process all 1,938 images was about 37 Sec. (0.0191 Sec. \/ Image), including reading the original sequence file.CONCLUSION: Initial experiments showed the algorithm to be sufficiently accurate and fast for segmentation transverse processes in ultrasound for spinal curvature measurement. An extensive evaluation of the method is currently underway on images from a larger patient cohort and using multiple observers in producing ground truth segmentation.<\/p><\/div>
Close<\/a><\/p><\/div>