Shahrokh Kamali
Graduate student (PhD)
Electrical Engineering
Dalhousie University
Shahrokh received his BSc in Electrical Engineering from Shiraz University, Shiraz, Iran and MASc in Electrical Engineering from Dalhousie University. He was a PhD student at Dalhousie University and a visiting student at the Perk Lab.
Pinter, Csaba; Travers, Bryan; Baum, Zachary M C; Kamali, Shahrokh; Ungi, Tamas; Lasso, Andras; Church, Ben; Fichtinger, Gabor
Real-time transverse process detection in ultrasound Conference
SPIE Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling, Houston, Texas, 2018.
@conference{Pinter2018,
title = {Real-time transverse process detection in ultrasound},
author = {Csaba Pinter and Bryan Travers and Zachary M C Baum and Shahrokh Kamali and Tamas Ungi and Andras Lasso and Ben Church and Gabor Fichtinger},
url = {https://labs.cs.queensu.ca/perklab/wp-content/uploads/sites/3/2024/02/Pinter2018.pdf},
year = {2018},
date = {2018-03-01},
urldate = {2018-03-01},
booktitle = {SPIE Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling},
address = {Houston, Texas},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Kamali, Shahrokh; Ungi, Tamas; Lasso, Andras; Yan, Christina; Lougheed, Matthew; Fichtinger, Gabor
Localization of the transverse processes in ultrasound for spinal curvature measurement Conference
SPIE Medical Imaging, vol. 10135, 2017.
@conference{Kamali2017a,
title = {Localization of the transverse processes in ultrasound for spinal curvature measurement},
author = {Shahrokh Kamali and Tamas Ungi and Andras Lasso and Christina Yan and Matthew Lougheed and Gabor Fichtinger},
url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2615387
https://labs.cs.queensu.ca/perklab/wp-content/uploads/sites/3/2024/02/Kamali2017a.pdf},
doi = {10.1117/12.2256007},
year = {2017},
date = {2017-02-01},
urldate = {2017-02-01},
booktitle = {SPIE Medical Imaging},
volume = {10135},
pages = {101350I-101350I-7},
abstract = {<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>},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
<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>