TY - JOUR

T1 - A Novel Automated Platform for Quantifying the Extent of Skeletal Tumour Involvement in Prostate Cancer Patients Using the Bone Scan Index

A1 - Ulmert,David

A1 - Kaboteh,Reza

A1 - Fox,Josef J.

A1 - Savage,Caroline

A1 - Evans,Michael J.

A1 - Lilja,Hans

A1 - Abrahamsson,Per-Anders

A1 - Björk,Thomas

A1 - Gerdtsson,Axel

A1 - Bjartell,Anders

A1 - Gjertsson,Peter

A1 - Höglund,Peter

A1 - Lomsky,Milan

A1 - Ohlsson,Mattias

A1 - Richter,Jens

A1 - Sadik,May

A1 - Morris,Michael J.

A1 - Scher,Howard I.

A1 - Sjöstrand,Karl

A1 - Yu,Alice

A1 - Suurküla,Madis

A1 - Edenbrandt,Lars

A1 - Larson,Steven M.

AU - Ulmert,David

AU - Kaboteh,Reza

AU - Fox,Josef J.

AU - Savage,Caroline

AU - Evans,Michael J.

AU - Lilja,Hans

AU - Abrahamsson,Per-Anders

AU - Björk,Thomas

AU - Gerdtsson,Axel

AU - Bjartell,Anders

AU - Gjertsson,Peter

AU - Höglund,Peter

AU - Lomsky,Milan

AU - Ohlsson,Mattias

AU - Richter,Jens

AU - Sadik,May

AU - Morris,Michael J.

AU - Scher,Howard I.

AU - Sjöstrand,Karl

AU - Yu,Alice

AU - Suurküla,Madis

AU - Edenbrandt,Lars

AU - Larson,Steven M.

PB - Elsevier BV

PY - 2012

Y1 - 2012

N2 - Background<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/>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 participantsWe 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. MeasurementsThe agreement between methods was evaluated using Pearson's correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index).<br/> <br/>Results and limitations<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. ConclusionsAutomated 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.<br/><br/>We developed and evaluated the first unbiased, fully automated software system to systematically calculate skeletal tumour burden in patients with metastatic cancer in the bone, simplifying a valuable but cumbersome technology with shortcomings that had prevented its widespread clinical use.

AB - Background<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/>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 participantsWe 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. MeasurementsThe agreement between methods was evaluated using Pearson's correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index).<br/> <br/>Results and limitations<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. ConclusionsAutomated 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.<br/><br/>We developed and evaluated the first unbiased, fully automated software system to systematically calculate skeletal tumour burden in patients with metastatic cancer in the bone, simplifying a valuable but cumbersome technology with shortcomings that had prevented its widespread clinical use.

KW - Bone Scan Index

KW - Image analysis

KW - Radionuclide imaging

KW - Bone metastases

KW - Computer assisted diagnosis

KW - Automated detection

KW - Automated quantification

KW - Risk prediction

U2 - 10.1016/j.eururo.2012.01.037

DO - 10.1016/j.eururo.2012.01.037

JO - European Urology

JF - European Urology

SN - 0302-2838

IS - 1

VL - 62

SP - 78

EP - 84

ER -