Trial Outcomes & Findings for Comparative Study of Conventional MR Images With Synthetically Reconstructed MR Images of the Brain (NCT NCT05425927)

NCT ID: NCT05425927

Last Updated: 2025-04-23

Results Overview

Sensitivity of pathological findings (true number of participants with pathological findings over assessed number of participants with pathological findings by reader) for synthetic and conventional MR images on the full analysis set. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Recruitment status

COMPLETED

Study phase

NA

Target enrollment

189 participants

Primary outcome timeframe

Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Results posted on

2025-04-23

Participant Flow

Participant milestones

Participant milestones
Measure
Neurological MRI
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Overall Study
STARTED
189
Overall Study
COMPLETED
189
Overall Study
NOT COMPLETED
0

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

Race and Ethnicity were not collected from any participant.

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure
Neurological MRI Synthetic
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Age, Continuous
35.4 years
STANDARD_DEVIATION 23.1 • n=189 Participants
Age, Customized
Pediatric (<18 years)
63 Participants
n=189 Participants
Age, Customized
Adults (>= 18)
126 Participants
n=189 Participants
Sex: Female, Male
Female
107 Participants
n=189 Participants
Sex: Female, Male
Male
82 Participants
n=189 Participants
Region of Enrollment
United States
189 participants
n=189 Participants
Pathological finding
Congential malformations
13 Participants
n=189 Participants
Pathological finding
Infectious/inflammatory/demyelinating
20 Participants
n=189 Participants
Pathological finding
Intracranial neoplasms
27 Participants
n=189 Participants
Pathological finding
Toxic and metabolic conditions
0 Participants
n=189 Participants
Pathological finding
Traumatic lesions
4 Participants
n=189 Participants
Pathological finding
Vascular disorders of the brain
26 Participants
n=189 Participants
Pathological finding
Neuro degenerative disorders and hydrocephalus
13 Participants
n=189 Participants
Pathological finding
Normal/no findings
86 Participants
n=189 Participants
Anaesthesia used
Yes
5 Participants
n=189 Participants
Anaesthesia used
No
184 Participants
n=189 Participants

PRIMARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Sensitivity of pathological findings (true number of participants with pathological findings over assessed number of participants with pathological findings by reader) for synthetic and conventional MR images on the full analysis set. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Sensitivity of Pathological Findings (Full Analysis Set)
Synthetic
0.66 Proportion of participants
Interval 0.59 to 0.74
Sensitivity of Pathological Findings (Full Analysis Set)
Conventional
0.68 Proportion of participants
Interval 0.6 to 0.75

PRIMARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Specificity of pathological findings (true number of participants with normal/no finding over assessed number of participants with normal/no finding by reader) for synthetic and conventional MR images on the full analysis set. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Specificity of Pathological Findings (Full Analysis Set)
Synthetic
0.85 Proportion of participants
Interval 0.81 to 0.9
Specificity of Pathological Findings (Full Analysis Set)
Conventional
0.85 Proportion of participants
Interval 0.8 to 0.9

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Diagnostic accuracy of radiological findings (radiological finding class) for synthetic and conventional MR images on the full analysis set. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Classification of Pathological Findings
Synthetic
0.60 Proportion of participants
Interval 0.55 to 0.65
Classification of Pathological Findings
Conventional
0.60 Proportion of participants
Interval 0.55 to 0.65

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Adult subpopulation 18-99 years

Sensitivity of pathological findings (true number of participants with pathological findings over assessed number of participants with pathological findings) for synthetic and conventional MR images in adult population (18-99 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=126 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Sensitivity (Adult Population)
Synthetic
0.68 Proportion of participants
Interval 0.58 to 0.78
Sensitivity (Adult Population)
Conventional
0.70 Proportion of participants
Interval 0.61 to 0.79

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Adult subpopulation 18-99 years

Specificity of pathological findings (true number of participants with normal/no finding over assessed number of participants with normal/no finding) for synthetic and conventional MR images on the in adult population (18-99 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=126 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Selectivity (Adult Population)
Synthetic
0.84 Proportion of participants
Interval 0.78 to 0.9
Selectivity (Adult Population)
Conventional
0.84 Proportion of participants
Interval 0.78 to 0.91

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Adult subpopulation 18-99 years

Diagnostic accuracy of radiological findings (radiological finding class) for synthetic and conventional MR images in adult population (18-99 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=126 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Classification of Pathological Findings (Adult Population)
Synthetic
0.61 Proportion of participants
Interval 0.55 to 0.68
Classification of Pathological Findings (Adult Population)
Conventional
0.61 Proportion of participants
Interval 0.54 to 0.67

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Pediatric subpopulation 0-17 years

Sensitivity of pathological findings (true number of participants with pathological findings over assessed number of participants with pathological findings) for synthetic and conventional MR images in pediatric population (0-17 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=63 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Sensitivity (Pediatric Population)
Synthetic
0.64 Proportion of participants
Interval 0.52 to 0.76
Sensitivity (Pediatric Population)
Conventional
0.64 Proportion of participants
Interval 0.52 to 0.76

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Pediatric subpopulation 0-17 years

Specificity of pathological findings (true number of participants with normal/no finding over assessed number of participants with normal/no finding) for synthetic and conventional MR images on the in pediatric population (0-17 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=63 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Selectivity (Pediatric Population)
Synthetic
0.90 Proportion of participants
Interval 0.83 to 0.97
Selectivity (Pediatric Population)
Conventional
0.87 Proportion of participants
Interval 0.8 to 0.95

SECONDARY outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Population: Pediatric subpopulation 0-17 years

Diagnostic accuracy of radiological findings (radiological finding class) for synthetic and conventional MR images in pediatric population (0-17 years). Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The ground truth is the site-determined diagnosis.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=63 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Classification of Pathological Findings (Pediatric Population)
Synthetic
0.57 Proportion of participants
Interval 0.48 to 0.67
Classification of Pathological Findings (Pediatric Population)
Conventional
0.58 Proportion of participants
Interval 0.49 to 0.68

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Legibility of anatomical structures, per structure, on the full analysis set for T1w images. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The result for each anatomical structure per image type, independent of reading period, is summarized in corresponding row below.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=945 Number of observations
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Legibility T1w (Full Analysis Set)
Central sulcus : Synthetic
940 Number of observations
Legibility T1w (Full Analysis Set)
Cerebral peduncle : Synthetic
944 Number of observations
Legibility T1w (Full Analysis Set)
Cervicomedullary junction : Synthetic
944 Number of observations
Legibility T1w (Full Analysis Set)
Head of caudate nucleus : Synthetic
942 Number of observations
Legibility T1w (Full Analysis Set)
Middle cerebellar peducle : Synthetic
944 Number of observations
Legibility T1w (Full Analysis Set)
Posterior limb of internal capsule : Synthetic
942 Number of observations
Legibility T1w (Full Analysis Set)
Central sulcus : Conventional
938 Number of observations
Legibility T1w (Full Analysis Set)
Cerebral peduncle : Conventional
940 Number of observations
Legibility T1w (Full Analysis Set)
Cervicomedullary junction : Conventional
944 Number of observations
Legibility T1w (Full Analysis Set)
Head of caudate nucleus : Conventional
936 Number of observations
Legibility T1w (Full Analysis Set)
Middle cerebellar peducle : Conventional
943 Number of observations
Legibility T1w (Full Analysis Set)
Posterior limb of internal capsule : Conventional
933 Number of observations

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Legibility of anatomical structures, per structure, on the full analysis set for T2w images. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The result for each anatomical structure per image type, independent of reading period, is summarized in corresponding row below.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=945 Number of observations
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Legibility T2w (Full Analysis Set)
Central sulcus : Synthetic
939 Number of observations
Legibility T2w (Full Analysis Set)
Cerebral peduncle : Synthetic
942 Number of observations
Legibility T2w (Full Analysis Set)
Cervicomedullary junction : Synthetic
943 Number of observations
Legibility T2w (Full Analysis Set)
Head of caudate nucleus : Synthetic
934 Number of observations
Legibility T2w (Full Analysis Set)
Middle cerebellar peducle : Synthetic
944 Number of observations
Legibility T2w (Full Analysis Set)
Posterior limb of internal capsule : Synthetic
937 Number of observations
Legibility T2w (Full Analysis Set)
Central sulcus : Conventional
941 Number of observations
Legibility T2w (Full Analysis Set)
Cerebral peduncle : Conventional
942 Number of observations
Legibility T2w (Full Analysis Set)
Cervicomedullary junction : Conventional
927 Number of observations
Legibility T2w (Full Analysis Set)
Head of caudate nucleus : Conventional
923 Number of observations
Legibility T2w (Full Analysis Set)
Middle cerebellar peducle : Conventional
942 Number of observations
Legibility T2w (Full Analysis Set)
Posterior limb of internal capsule : Conventional
921 Number of observations

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Presence and type of artifacts determined for synthetic T1w images, on the full analysis set determined by all readers. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The result for each artifact per image type, independent of reading period, is summarized in corresponding row below.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=945 Number of observations
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Artifacts T1w(Full Analysis Set)
No artifacts : Synthetic
851 Number of observations
Artifacts T1w(Full Analysis Set)
Motion artifacts : Synthetic
29 Number of observations
Artifacts T1w(Full Analysis Set)
In-folding or wrap around artifacts : Synthetic
1 Number of observations
Artifacts T1w(Full Analysis Set)
Flow or phase-encoding artifacts : Synthetic
4 Number of observations
Artifacts T1w(Full Analysis Set)
Magic angle effect artifacts : Synthetic
1 Number of observations
Artifacts T1w(Full Analysis Set)
Water-fat shift/ chemical shift artifacts : Synthetic
0 Number of observations
Artifacts T1w(Full Analysis Set)
Magnetic susceptibility artifact : Synthetic
55 Number of observations
Artifacts T1w(Full Analysis Set)
Low resolution : Synthetic
7 Number of observations
Artifacts T1w(Full Analysis Set)
Low signal to noise : Synthetic
4 Number of observations
Artifacts T1w(Full Analysis Set)
Low tissue contrast : Synthetic
5 Number of observations
Artifacts T1w(Full Analysis Set)
No artifacts : Conventional
820 Number of observations
Artifacts T1w(Full Analysis Set)
Motion artifacts : Conventional
40 Number of observations
Artifacts T1w(Full Analysis Set)
In-folding or wrap around artifacts : Conventional
0 Number of observations
Artifacts T1w(Full Analysis Set)
Flow or phase-encoding artifacts : Conventional
10 Number of observations
Artifacts T1w(Full Analysis Set)
Magic angle effect artifacts : Conventional
0 Number of observations
Artifacts T1w(Full Analysis Set)
Water-fat shift/ chemical shift artifacts : Conventional
0 Number of observations
Artifacts T1w(Full Analysis Set)
Magnetic susceptibility artifact : Conventional
56 Number of observations
Artifacts T1w(Full Analysis Set)
Low resolution : Conventional
17 Number of observations
Artifacts T1w(Full Analysis Set)
Low signal to noise : Conventional
22 Number of observations
Artifacts T1w(Full Analysis Set)
Low tissue contrast : Conventional
21 Number of observations

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Presence and type of artifacts determined for synthetic T2w images, on the full analysis set determined by all readers. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The result for each artifact per image type, independent of reading period, is summarized in corresponding row below.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=945 Number of observations
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Artifacts T2w(Full Analysis Set)
Magic angle effect artifacts : Conventional
0 Number of observations
Artifacts T2w(Full Analysis Set)
No artifacts : Synthetic
655 Number of observations
Artifacts T2w(Full Analysis Set)
T2 weighted : Motion artifacts : Synthetic
33 Number of observations
Artifacts T2w(Full Analysis Set)
In-folding or wrap around artifacts : Synthetic
1 Number of observations
Artifacts T2w(Full Analysis Set)
Flow or phase-encoding artifacts : Synthetic
10 Number of observations
Artifacts T2w(Full Analysis Set)
Magic angle effect artifacts : Synthetic
0 Number of observations
Artifacts T2w(Full Analysis Set)
Water-fat shift/ chemical shift artifacts : Synthetic
0 Number of observations
Artifacts T2w(Full Analysis Set)
Magnetic susceptibility artifact : Synthetic
51 Number of observations
Artifacts T2w(Full Analysis Set)
Low resolution : Synthetic
106 Number of observations
Artifacts T2w(Full Analysis Set)
Low signal to noise : Synthetic
30 Number of observations
Artifacts T2w(Full Analysis Set)
Low tissue contrast : Synthetic
164 Number of observations
Artifacts T2w(Full Analysis Set)
No artifacts : Conventional
600 Number of observations
Artifacts T2w(Full Analysis Set)
Motion artifacts : Conventional
40 Number of observations
Artifacts T2w(Full Analysis Set)
In-folding or wrap around artifacts : Conventional
4 Number of observations
Artifacts T2w(Full Analysis Set)
Flow or phase-encoding artifacts : Conventional
207 Number of observations
Artifacts T2w(Full Analysis Set)
Water-fat shift/ chemical shift artifacts : Conventional
0 Number of observations
Artifacts T2w(Full Analysis Set)
Magnetic susceptibility artifact : Conventional
57 Number of observations
Artifacts T2w(Full Analysis Set)
Low resolution : Conventional
66 Number of observations
Artifacts T2w(Full Analysis Set)
Low signal to noise : Conventional
64 Number of observations
Artifacts T2w(Full Analysis Set)
Low tissue contrast : Conventional
56 Number of observations

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Inter-rater agreement between all reader's assessment of pathological finding, as well as radiological finding classes, on the full analysis set. Each image was evaluated only once per reader and the agreement is independent of reading session. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The agreement was assessed separately per image type over both reading periods using overall agreement, Fleiss' kappa coefficient, and Gwet's AC1 coefficient. The first reading begun after all image processing was complete.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Overall agreement (Synthetic)
0.82 Proportion of participants
Interval 0.79 to 0.86
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Fleiss' kappa coefficient (Synthetic)
0.64 Proportion of participants
Interval 0.57 to 0.71
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Gwet's AC1 coefficient (Synthetic)
0.65 Proportion of participants
Interval 0.58 to 0.72
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Overall agreement (Synthetic)
0.67 Proportion of participants
Interval 0.62 to 0.71
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Fleiss' kappa coefficient (Synthetic)
0.48 Proportion of participants
Interval 0.42 to 0.53
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Gwet's AC1 coefficient (Synthetic)
0.63 Proportion of participants
Interval 0.58 to 0.68
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Overall agreement (Conventional)
0.82 Proportion of participants
Interval 0.78 to 0.85
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Fleiss' kappa coefficient (Conventional)
0.63 Proportion of participants
Interval 0.55 to 0.7
Inter-rater Agreement (Full Analysis Set)
Pathological finding: Gwet's AC1 coefficient (Conventional)
0.64 Proportion of participants
Interval 0.57 to 0.71
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Overall agreement (Conventional)
0.67 Proportion of participants
Interval 0.62 to 0.71
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Fleiss' kappa coefficient (Conventional)
0.48 Proportion of participants
Interval 0.43 to 0.54
Inter-rater Agreement (Full Analysis Set)
Radiological finding class: Gwet's AC1 coefficient (Conventional)
0.63 Proportion of participants
Interval 0.58 to 0.68

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Inter-method agreement between the different reader's assessment of pathological finding, as well as radiological finding classes, on the full analysis set. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The agreement was evaluated for all images, independent of reading period and image type, using overall agreement, Fleiss' kappa coefficient, and Gwet's AC1 coefficient. The first reading begun after all image processing was complete.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Inter-method Agreement (Full Analysis Set)
Pathological finding: Overall agreement
0.86 Proportion of participants
Interval 0.83 to 0.88
Inter-method Agreement (Full Analysis Set)
Pathological finding: Fleiss' kappa coefficient
0.71 Proportion of participants
Interval 0.65 to 0.76
Inter-method Agreement (Full Analysis Set)
Pathological finding: Gwet's AC1 coefficient
0.72 Proportion of participants
Interval 0.67 to 0.77
Inter-method Agreement (Full Analysis Set)
Radiological finding class: Overall agreement
0.75 Proportion of participants
Interval 0.72 to 0.78
Inter-method Agreement (Full Analysis Set)
Radiological finding class: Fleiss' kappa coefficient
0.61 Proportion of participants
Interval 0.56 to 0.66
Inter-method Agreement (Full Analysis Set)
Radiological finding class: Gwet's AC1 coefficient
0.73 Proportion of participants
Interval 0.69 to 0.76

OTHER_PRE_SPECIFIED outcome

Timeframe: Conventional images and necessary MRI information acquired from participant on exam day (1 day). Synthetic images generated before first reading. Analysis by readers in two readings, first reading: week 0-2, second reading: week 7-8

Image quality score (1 (Unacceptable) - 5 (Excellent)) per contrast weighting (T1w, T2w) per both image types (conventional and synthetic) where 3,4,5 are deemed acceptable for diagnostic use and 1,2 unacceptable for diagnostic use. Each image was evaluated only once per reader. The images were split between two readings, with a wash-out period of 4 weeks in between. Both readings contained both types of images, synthetic and conventional. The first reading begun after all image processing was complete. The result presented, independent of reading period, is the averaged score per contrast weight and image type with the standard deviation.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Image Quality Score (Full Analysis Set)
T1w : Synthetic
4.6 score on a scale
Standard Deviation 0.6
Image Quality Score (Full Analysis Set)
T1w : Conventional
4.5 score on a scale
Standard Deviation 0.7
Image Quality Score (Full Analysis Set)
T2w : Synthetic
4.4 score on a scale
Standard Deviation 0.7
Image Quality Score (Full Analysis Set)
T2w : Conventional
4.2 score on a scale
Standard Deviation 0.8

OTHER_PRE_SPECIFIED outcome

Timeframe: Exam day (1 day), Generation of Synthetic Images (up to 7 weeks)

Incidence of Adverse Events (AE), Adverse Device Effects (ADE), Serious Adverse Events (SAE), Serious Adverse Device Effects (SADE), Unanticipated Adverse Device Effect (UADE), Unanticipated Serious Adverse Device Effect (USADE) and Device Deficiencies (DD). The measurement was assessed in two periods: during exam day after signing consent form (all incidents applicable) and when generating the synthetic images (only device deficiencies) after all exams were performed.

Outcome measures

Outcome measures
Measure
Neurologic Synthetic and Conventional MRI
n=189 Participants
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Safety (Full Analysis Set)
Adverse Events (AE)
0 events
Safety (Full Analysis Set)
Adverse Device Effects (ADE)
0 events
Safety (Full Analysis Set)
Serious Adverse Events (SAE)
0 events
Safety (Full Analysis Set)
Unanticipated Adverse Device Effect (UADE)
0 events
Safety (Full Analysis Set)
Unanticipated Serious Adverse Device Effect (USADE)
0 events
Safety (Full Analysis Set)
Device Deficiencies (DD)
1 events

Adverse Events

Neurologic Synthetic and Conventional MRI

Serious events: 0 serious events
Other events: 1 other events
Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Other adverse events
Measure
Neurologic Synthetic and Conventional MRI
n=189 participants at risk
MR images of the brain acquired for post-processing with software (SyMRI 15, 3D). Comparison is done between the conventional MR images and the post-processed synthetic MR images SyMRI 15 (3D): Neurological MRI image collection. All participants with complete set of scans that was part of the image review study.
Product Issues
Device Deficiencies
0.53%
1/189 • Number of events 1 • Exam day (1 day), Generation of Synthetic Images (up to 7 weeks)

Additional Information

Erik Lange

SyntheticMR

Phone: +46(0)70-331 56 78

Results disclosure agreements

  • Principal investigator is a sponsor employee
  • Publication restrictions are in place