Medical ultrasound image similarity measurement by human visual system (HVS) modelling

D  de Cunha; L  Eadie; B  Adams; D  Hawkes

Medical ultrasound image similarity measurement by human visual system (HVS) modelling

D de Cunha, L Eadie, B Adams, D Hawkes

Applied Health Sciences

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

We applied a four stage model of human vision to the problem of similarity measurement of medical (liver) ultrasound images. The results showed that when comparing a given image to a set that contained images with similar features, the model was able to correctly identify the most similar image in the set. Additionally, the shape of the similarity function closely followed a subjective measure of visual similarity for images around the best match. Removing some computational steps to reduce processing time enabled the comparison method to run in near real-time (< 5 seconds), but with some acceptable loss of accuracy. These results could not be achieved using conventional similarity measurements based on image grey level statistics.

Original language	English
Title of host publication	BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS
Editors	HH Bulthoff, SW Lee, TA Poggio, C Wallraven
Place of Publication	BERLIN
Publisher	SPRINGER-VERLAG BERLIN
Pages	340-347
Number of pages	8
ISBN (Print)	3-540-00174-3
Publication status	Published - 2002
Event	2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002) - TUBINGEN Duration: 22 Nov 2002 → 24 Nov 2002

Conference

Conference	2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002)
City	TUBINGEN
Period	22/11/02 → 24/11/02

Cite this

Medical ultrasound image similarity measurement by human visual system (HVS) modelling. / de Cunha, D ; Eadie, L ; Adams, B et al.
BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS. ed. / HH Bulthoff; SW Lee; TA Poggio; C Wallraven. BERLIN: SPRINGER-VERLAG BERLIN, 2002. p. 340-347.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

de Cunha, D, Eadie, L, Adams, B & Hawkes, D 2002, Medical ultrasound image similarity measurement by human visual system (HVS) modelling. in HH Bulthoff, SW Lee, TA Poggio & C Wallraven (eds), BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS. SPRINGER-VERLAG BERLIN, BERLIN, pp. 340-347, 2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002), TUBINGEN, 22/11/02.

@inproceedings{aad27f1b459c4809a6cee3227fe38906,

title = "Medical ultrasound image similarity measurement by human visual system (HVS) modelling",

abstract = "We applied a four stage model of human vision to the problem of similarity measurement of medical (liver) ultrasound images. The results showed that when comparing a given image to a set that contained images with similar features, the model was able to correctly identify the most similar image in the set. Additionally, the shape of the similarity function closely followed a subjective measure of visual similarity for images around the best match. Removing some computational steps to reduce processing time enabled the comparison method to run in near real-time (< 5 seconds), but with some acceptable loss of accuracy. These results could not be achieved using conventional similarity measurements based on image grey level statistics.",

author = "{de Cunha}, D and L Eadie and B Adams and D Hawkes",

year = "2002",

language = "English",

isbn = "3-540-00174-3",

pages = "340--347",

editor = "HH Bulthoff and SW Lee and TA Poggio and C Wallraven",

booktitle = "BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS",

publisher = "SPRINGER-VERLAG BERLIN",

note = "2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002) ; Conference date: 22-11-2002 Through 24-11-2002",

}

TY - GEN

T1 - Medical ultrasound image similarity measurement by human visual system (HVS) modelling

AU - de Cunha, D

AU - Eadie, L

AU - Adams, B

AU - Hawkes, D

PY - 2002

Y1 - 2002

N2 - We applied a four stage model of human vision to the problem of similarity measurement of medical (liver) ultrasound images. The results showed that when comparing a given image to a set that contained images with similar features, the model was able to correctly identify the most similar image in the set. Additionally, the shape of the similarity function closely followed a subjective measure of visual similarity for images around the best match. Removing some computational steps to reduce processing time enabled the comparison method to run in near real-time (< 5 seconds), but with some acceptable loss of accuracy. These results could not be achieved using conventional similarity measurements based on image grey level statistics.

AB - We applied a four stage model of human vision to the problem of similarity measurement of medical (liver) ultrasound images. The results showed that when comparing a given image to a set that contained images with similar features, the model was able to correctly identify the most similar image in the set. Additionally, the shape of the similarity function closely followed a subjective measure of visual similarity for images around the best match. Removing some computational steps to reduce processing time enabled the comparison method to run in near real-time (< 5 seconds), but with some acceptable loss of accuracy. These results could not be achieved using conventional similarity measurements based on image grey level statistics.

M3 - Published conference contribution

SN - 3-540-00174-3

SP - 340

EP - 347

BT - BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS

A2 - Bulthoff, HH

A2 - Lee, SW

A2 - Poggio, TA

A2 - Wallraven, C

PB - SPRINGER-VERLAG BERLIN

CY - BERLIN

T2 - 2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002)

Y2 - 22 November 2002 through 24 November 2002

ER -

Medical ultrasound image similarity measurement by human visual system (HVS) modelling

Abstract

Conference

Fingerprint

Cite this