We've updated our Privacy Policy to make it clearer how we use your personal data.
We use cookies to provide you with a better experience, read our Cookie Policy
EP23282
Abstract: Aims:
Sacroiliitis is difficult to diagnose and harder still to quantify or monitor response. Dynamika is a stand-alone, cloud-based software using complex algorithms to allow real-time, user-defined analysis of regions of interest (ROI)in 3D and allows quantification of signal intensity (and/or contrast enhancement) within these ROIs on scans. The ROI evaluation technique in simplest guise was used to evaluate isotope imaging as proof of principle but we aim to show similar/better success with this software on STIR MR images.
Content:
50 MRI and 30 bone scans were analysed to evaluate initial validity of Dynamika software, including some follow-up imaging - giving insight into how disease monitoring could be undertaken. This analysis was benchmarked against scintigraphy standard peak-trough algorithm analysis.
Impact:
Potential to diagnose and grade disease and also monitor response with MRI, as well as show its superiority compared with bone scanning - though show utility of the software with bone scans also.
Outcomes:
Positive Negative Total
Bone scan 5 25 30
MRI scan (visual) 13 37 50
MRI (+Dynamika) 21 29 50
Clinical picture 19 31 50
Quantitative assessment:
“Positivity” of result: visual v ‘score’
Score rating Mild/ Moderate/ Severe
MRI result 11 mild; 1 moderate; 1 severe
MRI Dynamika outcome 7 mild; 7 moderate, 7 severe
Dynamika clinical correlation 2 false positive, no false negative:
100% sens; 94% spec; NPV 100%
Patients can be quantitatively graded into mild, moderate or severe sacroiliitis with greatest reliability using MRI +Dynamika.
Discussion:
Needs validating in bigger studies but initial results of Dynamika software are promising and simple to reproduce in evaluating sacroiliitis, with some correlation between results and the clinical scenario in a way not applicable to bone scintigraphy without the penalty of ionising radiation or contract administration.Summary: Computer Aided-Detection of sacroiliitis on MRI with Dynamika, a stand-alone, web-based ssoftware algorithm - how it compares with human perceptionReferences: 1. Bozkurt MF and Kiratli P. Quantitative sacroiliac scintigraphy for pediatric patients: comparison of two methods. Ann Nucl Med. 2014 Apr;28(3):227-31;
2. Tiwari BP and Basu S. Estimation of sacroiliac joint index in normal subjects of various age groups... Nucl Med Rev Cent East Eur. 2013;16(1):26 30;
3. Kubassova O, et al. A computer-aided detection system for rheumatoid arthritis MRI data interpretation and quantification of synovial activity. Eur J Radiol. 2010 Jun;74(3):e67-72;
4. Althoff CE et al. Magnetic resonance imaging of active sacroiliitis: do we really need gadolinium? Eur J Radiol. 2009 Aug;71(2):232-6
Sacroiliitis is difficult to diagnose and harder still to quantify or monitor response. Dynamika is a stand-alone, cloud-based software using complex algorithms to allow real-time, user-defined analysis of regions of interest (ROI)in 3D and allows quantification of signal intensity (and/or contrast enhancement) within these ROIs on scans. The ROI evaluation technique in simplest guise was used to evaluate isotope imaging as proof of principle but we aim to show similar/better success with this software on STIR MR images.
Content:
50 MRI and 30 bone scans were analysed to evaluate initial validity of Dynamika software, including some follow-up imaging - giving insight into how disease monitoring could be undertaken. This analysis was benchmarked against scintigraphy standard peak-trough algorithm analysis.
Impact:
Potential to diagnose and grade disease and also monitor response with MRI, as well as show its superiority compared with bone scanning - though show utility of the software with bone scans also.
Outcomes:
Positive Negative Total
Bone scan 5 25 30
MRI scan (visual) 13 37 50
MRI (+Dynamika) 21 29 50
Clinical picture 19 31 50
Quantitative assessment:
“Positivity” of result: visual v ‘score’
Score rating Mild/ Moderate/ Severe
MRI result 11 mild; 1 moderate; 1 severe
MRI Dynamika outcome 7 mild; 7 moderate, 7 severe
Dynamika clinical correlation 2 false positive, no false negative:
100% sens; 94% spec; NPV 100%
Patients can be quantitatively graded into mild, moderate or severe sacroiliitis with greatest reliability using MRI +Dynamika.
Discussion:
Needs validating in bigger studies but initial results of Dynamika software are promising and simple to reproduce in evaluating sacroiliitis, with some correlation between results and the clinical scenario in a way not applicable to bone scintigraphy without the penalty of ionising radiation or contract administration.Summary: Computer Aided-Detection of sacroiliitis on MRI with Dynamika, a stand-alone, web-based ssoftware algorithm - how it compares with human perceptionReferences: 1. Bozkurt MF and Kiratli P. Quantitative sacroiliac scintigraphy for pediatric patients: comparison of two methods. Ann Nucl Med. 2014 Apr;28(3):227-31;
2. Tiwari BP and Basu S. Estimation of sacroiliac joint index in normal subjects of various age groups... Nucl Med Rev Cent East Eur. 2013;16(1):26 30;
3. Kubassova O, et al. A computer-aided detection system for rheumatoid arthritis MRI data interpretation and quantification of synovial activity. Eur J Radiol. 2010 Jun;74(3):e67-72;
4. Althoff CE et al. Magnetic resonance imaging of active sacroiliitis: do we really need gadolinium? Eur J Radiol. 2009 Aug;71(2):232-6
Ask the author a question about this poster.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Related Posters
Machine Learning Approach to Geometry Prediction in Cold Spray Additive Manufacturing
Daiki Ikeuchi
Plant Extract
Tylor Keller
3D Printing Materials
Tylor Keller
Development of a valid consent policy for Radiological Imaging procedures in Irish (HSE) Hospitals
gerard brassil
MICRONUCLEI AS BIOMARKERS OF GENETIC DAMAGE IN ORAL SQUAMOUS CELL CARCINOMA
Nancy A. Shaaban 1 BDS, Hanaa S. Raslan 2 PhD, Omneya M. Ramadan 3 PhD, Ahmed S. Habib 4 PhD, Eiman I. Zaki 5 PhD