Expert System for Bone Scan Interpretation Improves Progression Assessment in Bone Metastatic Prostate Cancer
Introduction The bone scan index (BSI) was introduced as a quantitative tool for tumor involvement in bone of patients with metastatic prostate cancer (mPCa). The computer-aided diagnosis device for BSI analysis EXINIbone BSI seems to represent technical progress for the quantitative assessment of b...
Gespeichert in:
Veröffentlicht in: | Advances in therapy 2017-04, Vol.34 (4), p.986-994 |
---|---|
Hauptverfasser: | , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Introduction
The bone scan index (BSI) was introduced as a quantitative tool for tumor involvement in bone of patients with metastatic prostate cancer (mPCa). The computer-aided diagnosis device for BSI analysis EXINIbone
BSI
seems to represent technical progress for the quantitative assessment of bone involvement. But it is not yet clear if the automated BSI (aBSI) could contribute to improved evaluation of progression in patients under antiandrogens or chemotherapy in contrast to the visual interpretation and/or conventional biomarkers such as the prostate-specific antigen (PSA).
Methods
In 49 mPCa patients, bone scans were performed initially and during different therapy courses. Scans were evaluated visually and by the artificial-neural-network-based expert system EXINIbone
BSI
. Progression of metastatic bone involvement was defined according to the Prostate Cancer Clinical Trials Working Group 2 (PCWG2) criteria in the visual interpretation. The computer-assisted interpretation was based on different cutoff values in relative changes of the aBSI. Additionally, assessments according to bone scanning were compared to changes in the PSA value as a potential surrogate for treatment response.
Results
Using a sensitive cutoff value (5% or 10%) for the relative aBSI increase led to significantly increased progression determination compared to the visual interpretation of bone scans (49% and 43% vs. 27%,
p
|
---|---|
ISSN: | 0741-238X 1865-8652 |
DOI: | 10.1007/s12325-017-0505-z |