Keyword search (3,619 papers available)


Automatic collateral circulation scoring in ischemic stroke using 4D CT angiography with low-rank and sparse matrix decomposition.

Author(s): Aktar M, Tampieri D, Rivaz H, Kersten-Oertel M, Xiao Y

Automatic collateral circulation scoring in ischemic stroke using 4D CT angiography with low-rank and sparse matrix decomposition.

Int J Comput Assist Radiol Surg. 2020 Jul 14;:

Authors: Aktar M, Tampieri D, Rivaz H, Kersten-Oertel M, Xi...

Article GUID: 32662055
Two-stage ultrasound image segmentation using U-Net and test time augmentation.

Author(s): Amiri M; Brooks R; Behboodi B; Rivaz H;

PURPOSE: Detecting breast lesions using ultrasound imaging is an important application of computer-aided diagnosis systems. Several automatic methods have been proposed for breast lesion detection and segmentation; however, due to the ultrasound artefacts, ...

Article GUID: 32350786
MARIN: an open-source mobile augmented reality interactive neuronavigation system.

Author(s): Léger É; Reyes J; Drouin S; Popa T; Hall JA; Collins DL; Kersten-Oertel M;

PURPOSE: Neuronavigation systems making use of augmented reality (AR) have been the focus of much research in the last couple of decades. In recent years, there has been considerable interest in using mobile devices for AR in the operating room (OR). We pro...

Article GUID: 32323206
Cognitive load associations when utilizing auditory display within image-guided neurosurgery.

Author(s): Plazak J, DiGiovanni DA, Collins DL, Kersten-Oertel M

Int J Comput Assist Radiol Surg. 2019 Apr 17;: Authors: Plazak J, DiGiovanni DA, Collins DL, Kersten-Oertel M

Article GUID: 30997635
Deformable registration of preoperative MR, pre-resection ultrasound, and post-resection ultrasound images of neurosurgery.

Author(s): Rivaz H, Collins DL

Int J Comput Assist Radiol Surg. 2015 Jul;10(7):1017-28 Authors: Rivaz H, Collins DL

Article GUID: 25373447
Nonlinear deformation of tractography in ultrasound-guided low-grade gliomas resection.

Author(s): Xiao Y, Eikenes L, Reinertsen I, Rivaz H

Int J Comput Assist Radiol Surg. 2018 Mar;13(3):457-467 Authors: Xiao Y, Eikenes L, Reinertsen I, Rivaz H

Article GUID: 29299739
Correction to: Nonlinear deformation of tractography in ultrasound-guided low-grade gliomas resection.

Author(s): Xiao Y, Eikenes L, Reinertsen I, Rivaz H

Int J Comput Assist Radiol Surg. 2018 03;13(3):469 Authors: Xiao Y, Eikenes L, Reinertsen I, Rivaz H

Article GUID: 29392538
ARENA: Inter-modality affine registration using evolutionary strategy.

Author(s): Masoumi N, Xiao Y, Rivaz H

Int J Comput Assist Radiol Surg. 2019 Mar;14(3):441-450 Authors: Masoumi N, Xiao Y, Rivaz H

Article GUID: 30535826
Title:Two-stage ultrasound image segmentation using U-Net and test time augmentation.
Authors:Amiri M,  Brooks R,  Behboodi B,  Rivaz H, 
Link:https://www.ncbi.nlm.nih.gov/pubmed/32350786
DOI:10.1007/s11548-020-02158-3
Category:Int J Comput Assist Radiol Surg
PMID:32350786
Dept Affiliation: IMAGING
1 Concordia University, 1493 Saint-Catherine St W, Montreal, Quebec, Canada. amirim@encs.concordia.ca.
2 Concordia University, 1493 Saint-Catherine St W, Montreal, Quebec, Canada.
3 Nuance Communications, 1500 Boulevard Robert-Bourassa, Montreal, Quebec, H3A 3S7, Canada.

Description:

PURPOSE: Detecting breast lesions using ultrasound imaging is an important application of computer-aided diagnosis systems. Several automatic methods have been proposed for breast lesion detection and segmentation; however, due to the ultrasound artefacts, and to the complexity of lesion shapes and locations, lesion or tumor segmentation from ultrasound breast images is still an open problem. In this paper, we propose using a lesion detection stage prior to the segmentation stage in order to improve the accuracy of the segmentation.

METHODS: We used a breast ultrasound imaging dataset which contained 163 images of the breast with either benign lesions or malignant tumors. First, we used a U-Net to detect the lesions and then used another U-Net to segment the detected region. We could show when the lesion is precisely detected, the segmentation performance substantially improves; however, if the detection stage is not precise enough, the segmentation stage also fails. Therefore, we developed a test-time augmentation technique to assess the detection stage performance.

RESULTS: By using the proposed two-stage approach, we could improve the average Dice score by 1.8% overall. The improvement was substantially more for images wherein the original Dice score was less than 70%, where average Dice score was improved by 14.5%.

CONCLUSIONS: The proposed two-stage technique shows promising results for segmentation of breast US images and has a much smaller chance of failure.

PMID: 32350786 [PubMed - indexed for MEDLINE]