A novel automated platform for quantifying the extent of skeletal tumour involvement in prostate cancer patients using the Bone Scan Index

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 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.

Fig. 1. Consolidated Standards of Reporting Trials diagram: participant flow of the study

MPP = Malmö Preventive Medicine Project; MCDS = Malmö Diet and Cancer Study; PCa = prostate cancer; BSI = Bone Scan Index.

Fig. 2. Atlas based on 10 normal bone scans (a) with 12 skeletal regions (b) used for automated segmentation of the patient skeleton

Fig. 3. Patients from the evaluation group with automated Bone Scan Index (BSI) measurements of (a, top left) 1.1, (b, top right) 4.4, and (c, bottom) 12.8. The corresponding manual BSI measures were 1.2/1.0, 5.2/3.7, and 40.6/28.2, respectively

Fig. 4. Bland-Altman plot of manual and automated Bone Scan Index (BSI) readings. Two hundred thirty-four men had a negative (zero) score on manual and automated BSI (n = 384)

Fig. 5. Bland-Altman plot of two manual Bone Scan Index (BSI) readings. Fifty-one men had a negative (zero) score on manual and automated BSI (n = 133)

Fig. 6. Kaplan-Meier curve for death from prostate cancer among 384 men, stratified by automated Bone Scan Index (BSI) categories