Advanced

A Novel Automated Platform for Quantifying the Extent of Skeletal Tumour Involvement in Prostate Cancer Patients Using the Bone Scan Index.

Ulmert, David LU ; Kaboteh, Reza; Fox, Josef J; Savage, Caroline; Evans, Michael J; Lilja, Hans LU ; Abrahamsson, Per-Anders LU ; Björk, Thomas LU ; Gerdtsson, Axel LU and Bjartell, Anders LU , et al. (2012) In European Urology 62(1). p.78-84
Abstract
BACKGROUND:

There is little consensus on a standard approach to analysing bone scan images. The Bone Scan Index (BSI) is predictive of survival in patients with progressive prostate cancer (PCa), but the popularity of this metric is hampered by the tedium of the manual calculation.

OBJECTIVE:

Develop a fully automated method of quantifying the BSI and determining the clinical value of automated BSI measurements beyond conventional clinical and pathologic features.



DESIGN, SETTING, AND PARTICIPANTS:

We conditioned a computer-assisted diagnosis system identifying metastatic lesions on a bone scan to automatically compute BSI measurements. A training group of 795 bone scans was used... (More)
BACKGROUND:

There is little consensus on a standard approach to analysing bone scan images. The Bone Scan Index (BSI) is predictive of survival in patients with progressive prostate cancer (PCa), but the popularity of this metric is hampered by the tedium of the manual calculation.

OBJECTIVE:

Develop a fully automated method of quantifying the BSI and determining the clinical value of automated BSI measurements beyond conventional clinical and pathologic features.



DESIGN, SETTING, AND PARTICIPANTS:

We conditioned a computer-assisted diagnosis system identifying metastatic lesions on a bone scan to automatically compute BSI measurements. A training group of 795 bone scans was used in the conditioning process. Independent validation of the method used bone scans obtained ≤3 mo from diagnosis of 384 PCa cases in two large population-based cohorts. An experienced analyser (blinded to case identity, prior BSI, and outcome) scored the BSI measurements twice. We measured prediction of outcome using pretreatment Gleason score, clinical stage, and prostate-specific antigen with models that also incorporated either manual or automated BSI measurements. MEASUREMENTS: The agreement between methods was evaluated using Pearson's correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index).



RESULTS AND LIMITATIONS:

Manual and automated BSI measurements were strongly correlated (ρ=0.80), correlated more closely (ρ=0.93) when excluding cases with BSI scores ≥10 (1.8%), and were independently associated with PCa death (p<0.0001 for each) when added to the prediction model. Predictive accuracy of the base model (C-index: 0.768; 95% confidence interval [CI], 0.702-0.837) increased to 0.794 (95% CI, 0.727-0.860) by adding manual BSI scoring, and increased to 0.825 (95% CI, 0.754-0.881) by adding automated BSI scoring to the base model. CONCLUSIONS: Automated BSI scoring, with its 100% reproducibility, reduces turnaround time, eliminates operator-dependent subjectivity, and provides important clinical information comparable to that of manual BSI scoring. (Less)
Please use this url to cite or link to this publication:
author
, et al. (More)
(Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
European Urology
volume
62
issue
1
pages
78 - 84
publisher
Elsevier
external identifiers
  • wos:000304487900027
  • pmid:22306323
  • scopus:84861602779
ISSN
1873-7560
DOI
10.1016/j.eururo.2012.01.037
language
English
LU publication?
yes
id
146df779-d772-4d69-b55a-b5fbcbf28f54 (old id 2367248)
alternative location
http://www.ncbi.nlm.nih.gov/pubmed/22306323?dopt=Abstract
date added to LUP
2012-03-02 09:31:23
date last changed
2017-11-05 04:47:54
@article{146df779-d772-4d69-b55a-b5fbcbf28f54,
  abstract     = {BACKGROUND: <br/><br>
There is little consensus on a standard approach to analysing bone scan images. The Bone Scan Index (BSI) is predictive of survival in patients with progressive prostate cancer (PCa), but the popularity of this metric is hampered by the tedium of the manual calculation. <br/><br>
OBJECTIVE: <br/><br>
Develop a fully automated method of quantifying the BSI and determining the clinical value of automated BSI measurements beyond conventional clinical and pathologic features. <br/><br>
<br/><br>
DESIGN, SETTING, AND PARTICIPANTS: <br/><br>
We conditioned a computer-assisted diagnosis system identifying metastatic lesions on a bone scan to automatically compute BSI measurements. A training group of 795 bone scans was used in the conditioning process. Independent validation of the method used bone scans obtained ≤3 mo from diagnosis of 384 PCa cases in two large population-based cohorts. An experienced analyser (blinded to case identity, prior BSI, and outcome) scored the BSI measurements twice. We measured prediction of outcome using pretreatment Gleason score, clinical stage, and prostate-specific antigen with models that also incorporated either manual or automated BSI measurements. MEASUREMENTS: The agreement between methods was evaluated using Pearson's correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index). <br/><br>
<br/><br>
RESULTS AND LIMITATIONS: <br/><br>
Manual and automated BSI measurements were strongly correlated (ρ=0.80), correlated more closely (ρ=0.93) when excluding cases with BSI scores ≥10 (1.8%), and were independently associated with PCa death (p&lt;0.0001 for each) when added to the prediction model. Predictive accuracy of the base model (C-index: 0.768; 95% confidence interval [CI], 0.702-0.837) increased to 0.794 (95% CI, 0.727-0.860) by adding manual BSI scoring, and increased to 0.825 (95% CI, 0.754-0.881) by adding automated BSI scoring to the base model. CONCLUSIONS: Automated BSI scoring, with its 100% reproducibility, reduces turnaround time, eliminates operator-dependent subjectivity, and provides important clinical information comparable to that of manual BSI scoring.},
  author       = {Ulmert, David and Kaboteh, Reza and Fox, Josef J and Savage, Caroline and Evans, Michael J and Lilja, Hans and Abrahamsson, Per-Anders and Björk, Thomas and Gerdtsson, Axel and Bjartell, Anders and Gjertsson, Peter and Höglund, Peter and Lomsky, Milan and Ohlsson, Mattias and Richter, Jens and Sadik, May and Morris, Michael J and Scher, Howard I and Sjöstrand, Karl and Yu, Alice and Suurküla, Madis and Edenbrandt, Lars and Larson, Steven M},
  issn         = {1873-7560},
  language     = {eng},
  number       = {1},
  pages        = {78--84},
  publisher    = {Elsevier},
  series       = {European Urology},
  title        = {A Novel Automated Platform for Quantifying the Extent of Skeletal Tumour Involvement in Prostate Cancer Patients Using the Bone Scan Index.},
  url          = {http://dx.doi.org/10.1016/j.eururo.2012.01.037},
  volume       = {62},
  year         = {2012},
}