6533b85cfe1ef96bd12bd513
RESEARCH PRODUCT
Joint Probability of Shape and Image Similarities to Retrieve 2D TRUS-MR Slice Correspondence for Prostate Biopsy
Désiré SidibéJhimli MitraJosep CometSoumya GhoseFabrice MeriaudeauArnau OliverXavier LladoRobert MartíJoan C. Vilanovasubject
MaleProstate biopsyBiopsy[INFO.INFO-IM] Computer Science [cs]/Medical Imaging030230 surgeryNormalized mutual information030218 nuclear medicine & medical imagingImage (mathematics)03 medical and health sciences0302 clinical medicineJoint probability distribution[INFO.INFO-IM]Computer Science [cs]/Medical ImagingMedicineHumansComputer visionMR ProstateProbabilitymedicine.diagnostic_test[ INFO.INFO-IM ] Computer Science [cs]/Medical Imagingbusiness.industryUltrasoundProstatic NeoplasmsMagnetic resonance imagingImage segmentationMagnetic Resonance ImagingArtificial intelligencebusinessdescription
International audience; This paper presents a novel method to identify the 2D axial Magnetic Resonance (MR) slice from a pre-acquired MR prostate volume that closely corresponds to the 2D axial Transrectal Ultrasound (TRUS) slice obtained during prostate biopsy. The method combines both shape and image intensity information. The segmented prostate contours in both the imaging modalities are described by shape-context representations and matched using the Chi-square distance. Normalized mutual information and correlation coefficient between the TRUS and MR slices are computed to find image similarities. Finally, the joint probability values comprising shape and image similarities are used in a rule-based framework to provide the MR slice that closely resembles the TRUS slice acquired during the biopsy procedure. The method is evaluated for 20 patient datasets, of which 18 results match at least one of the two clinical expert choices.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2012-08-28 |