Automated Detection of Metastatic Bone Disease on Bone Scintigraphy Scans

Metastatic Bone Tumor Clinical Trial

Official title:

In Silico Clinical Trial Comparing the Reading Accuracy of Doctors and a Deep Learning Algorithm for Detection of Metastatic Bone Disease on Bone Scintigraphy Scans.

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT05110430
• Other study ID #: MBDDL
• Status: Completed
• Start date: March 10, 2021
• Est. completion date: December 31, 2021

Study information

• Verified date: March 2023
• Source: Maastricht University
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Bone scintigraphy scans are two dimensional medical images that are used heavily in nuclear medicine. The scans detect changes in bone metabolism with high sensitivity, yet it lacks the specificity to underlying causes. Therefore, further imaging would be required to confirm the underlying cause. The aim of this study is to investigate whether deep learning can improve clinical decision based on bone scintigraphy scans.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 2365
• Est. completion date: December 31, 2021
• Est. primary completion date: December 30, 2021
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• Patients who underwent a bone scintigraphy scan that is available with the radiologic report between 2010-2018

Exclusion Criteria:

• The lack of a bone scan, or corresponding radiologic report

Related Conditions & MeSH terms

• Bone Diseases
• Metastatic Bone Tumor

Intervention

Other:
• Deep learning based detection of metastatic bone disease on bone scintigraphy scans.
The aim is to investigate whether deep learning algorithms can detect bone metastasis with high accuracy and specificity.

Locations

Country	Name	City	State
Netherlands	Maastricht University	Maastricht	Limburg

Sponsors (5)

Lead Sponsor	Collaborator
Maastricht University	Aalborg University Hospital, Centre Hospitalier Universitaire de Liege, University Hospital, Aachen, University of Namur

Country where clinical trial is conducted

Netherlands, 

References & Publications (1)

Ibrahim A, Vaidyanathan A, Primakov S, Belmans F, Bottari F, Refaee T, Lovinfosse P, Jadoul A, Derwael C, Hertel F, Woodruff HC, Zacho HD, Walsh S, Vos W, Occhipinti M, Hanin FX, Lambin P, Mottaghy FM, Hustinx R. Deep learning based identification of bone — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	The classification performance of DL algorithm compared to the ground truth	Reporting the performance measures (Area under the curve, accuracy, specificity..etc)	June 2021
Secondary	Comparing the classification performance of the DL algorithm to that of physicians	Correctness of the diagnosis of Dr versus AI (dichotomous variable: correct versus not correct) on a subset of the validation data, using a McNemar statistical test	June 2021