Upload
ayita
View
37
Download
0
Tags:
Embed Size (px)
DESCRIPTION
XII PMT meeting – September 26, 2012. Agenda : New benchmark ICC and Dice’s Training set for Naïve Beta testers proposals Congress presentations. Benchmark Images. ADNI scans: 2 x 5 Scheltens’s atrophy score x 2 sides x 2 magnet strengths (1.5-3T) Total per rater: 40 hippos. - PowerPoint PPT Presentation
Citation preview
Agenda:
- New benchmark ICC and Dice’s
- Training set for Naïve
- Beta testers proposals
- Congress presentations
XII PMT meeting – September 26, 2012
Benchmark Images
ADNI scans: 2 x 5 Scheltens’s atrophy score x 2 sides
x 2 magnet strengths (1.5-3T)Total per rater: 40 hippos
5 Master Tracers’ segmentations:
Corrections after check for overlapping discrepanciesImproved Harmonized Protocol (HP) in many points
HP re-sent to panelists
Benchmark Images
Overlapping agreement Volume ICCs
1.5T images: 0.73
3T images: 0.75
Maximum level for
human tracers???
Left Hippocampus Right Hippocampus
Intra-rater 1.5T vs 3T (n=10)
MB 0.981 (0.928-0.995) 0.986 (0.776-0.997)
RG 0.968 (0.879-0.992) 0.974 (0.902-0.994)
GP 0.943 (0.335-0.989) 0.968 (0.541-0.994)
LA 0.966 (0.819-0.992) 0.971 (0.818-0.993)
DW 0.981 (0.930-0.995) 0.986 (0.944-0.997)
Inter-rater (n=10)
1.5T 0.957 (0.881-0.988) 0.971 (0.916-0.992)
Inter-rater (n=10)
3T 0.943 (0.791-0.986) 0.962 (0.863-0.990)
Training set for Naïve Tracers
- Liana Apostolova (7T)
-Brescia - Normative Archive (1.5 and 3T; 12 images (different severity) per magnet field strength?)
? TIMING for Certif. Platform ?
Will need to recap with available tracers in the 20 centres
Publication Policy
STANDARD FORM for submission:
TITLE of PROPOSAL:PI / CENTRE:AIM of the PROJECT:METHODS of the PROJECT:WHAT IS ASKED to the SC of the HARMONIZED HIPPOCAMPAL PROTOCOL WHAT IS OFFERED to the HARMONIZED HIPPOCAMPAL PROTOCOL PROJECT/COMMUNITY:
Masami Nishikawa (comparison of VSRAD performance; segmentation of human phantoms x HP)
Lei Wang (library of atlases; validation vs other algorithm/s x HP?)
Ronald Pierson (train ANN of Brain Image Analysis, LLC validation vs other algorithm/s x HP?)
Beta tester submissions
Lei Wang: use of “local” labels
“construction of a library of atlases for the purposes of mapping MR scans such as the ADNI data set”
Asks: use of label already segmented based on local protocol
Asks: to be informed as to when harmonized labels are available
Offers: solving the conversion of MultiTracer files into more common format
Beta tester submissions
Masami Nishikawa
Project aim: to validate the new version of VSRAD (Voxel-based Specific Regional analysis system for Alzheimer’s Disease), comparing it versus the Harmonized Protocol as the gold standard method to manually measure hippocampal volume.
Asks: Harmonized Protocol
Offers: Hippocampal segmentations on 3 healthy volunteers scanned twice by the 7 different machines will contribute for the validation of the Harmonized Protocol.
Beta tester submissions
Ronald Pierson
Project aim: Compare the results of the current hippocampal segmentation with other hippocampal definitions using BRAINS (Brain Research: Analysis of Images, Networks, and Systems)
Asks: Harmonized Protocol
Asks: ADNI IDs of benchmark subjects
Offers: not clear
Beta tester submissions
- CTAD (October, 29-31 2012)Definition of the Harmonized Protocol for Hippocampal Segmentation
- DGPPN Symposium 2012 Berlin (Andreas Fellgiebel)Segmentation of the hippocampus: Towards a joint EADC-ADNI harmonized protocol
- AAN 2013 EADC-ADNI Benchmark Images of Harmonized Hippocampal Segmentation
Congress Presentations
Papers describing the project
Survey of protocols (preliminary phase; published, JAD 2011)Operationalization (preliminary phase; I revision, Alzheimer’s & Dementia, MS n. ADJ-D-12-00094)
Axes check short report (Brescia Team, in progress)Delphi consensus (Brescia Team, in progress)Master tracers’ practice and reliability (Brescia Team, in progr)
Development of certification platform (Duchesne and coll)Validation data (Brescia Team – companion paper 1)Protocol definition (Brescia Team – companion paper 2)Validation vs pathology (TBD)
DO
NE
IN P
RO
GR
ES
S P
LA
NN
ED
VALIDATION VS CURRENT PROTOCOLSASSESSMENT OF SOURCES OF
VARIANCE TRAINING SET DEVELOPMENT
VALIDATION VS PATHOLOGY
GOLD STANDARD
Harmonized ProtocolADNI scans: 2 x 5 Scheltens’s
atrophy score x 2 sides x 2 magnet strengths (1.5-3T)
Total per rater: 40 hippos
Harmonized ProtocolADNI scans: 2 sides x 5 Scheltens’s atrophy scores
x 3 time points (bl-1y-2y) x 3 scanners (+ retracing @ bl)
x 2 magnet strengths (1.5-3T)Total per rater: 240 hippos
Assessment of variance due to rater and center
Local ProtocolADNI scans: 2 x 5 Scheltens’s atrophy scores
x 2 sides x 2 magnet strengths (1.5-3T)
Harmonized ProtocolADNI scans: 2 x 5 Scheltens’s atrophy score x
2 sides x 2 magnet strength (1.5-3T)Total per rater: 40 hippos Harmonized Protocol:
Pathological datasets: Mayo Clinic and NYU
Total: about 40 hippos
TrainingADNI scans: 10 at 1.5T x 2 sides x 7
SUs x 2 tracing roundsTotal per rater: 40 hippos
20 naïve tracers 5 master tracers 1 tracer
REFERENCE PROBABILISTIC MASKS
with 95% C.I.
QUALIFICATION QUALIFICATION
Best 5 naïve tracers
Assessment of variance due to side, trace-retrace, atrophy, time, scanner, rater
TRAINING SET
Assessment of agreement with volume on pathology or ex vivo
MRI and correlation with neuronal density
GANTT
CSF exclusion (n. labels)
using the same CSF label containing two (or more) separate CSF area on the same slice, for each hippocampus
using a single CSF label to exclude a large CSF pool