Go to: content | top | bottom | search
You are hereUNIL > Laboratoire de recherche en neuroimagerie > Research topics > Early detection of neurodegeneration

Classifying Images and Detecting Neurodegeneration in Pre-Clinical Phases

Principal Investigator: Richard Frackowiak



We are exploring ways of translating imaging science to patient diagnosis and in particular to the detection of pre-clinical atrophy signatures of various neurodegenerative disorders. We use image classification methods largely based on machine learning and graphical approaches and attempt to validate results with pathologically verified material. We have succeeded in showing proof of principle using support vector machines and now want to explore the methods so that we can optimise sensitivity and maximise the chances of detecting early change when functional compensation successfully postpones cognitive change. Our collaboration with mathematicians in the group is critical to the development of the analytical techniques. We have international collaborations with John Ashburner at the FIL in London, Stefan Kloppel in Freiburg-im-Giesau and physics collaborations in both the UK and Germany. We work on the ADNI data set and also collect scans from colleagues world wide who have pathologically verified data to validate the methods developed. The possibility of grading disease by extent of atrophy and measuring cognitive reserve by correlation with behavioural tests are major aims. The notion that early treatment with degeneration decelerating agents may postpone disease manifestations effectively is our guiding principle. Finally we want to associate anatomical change profiles with genetic biomarkers of the same neurodegenerative disorders


Research topics

• Effects of pooling scans from different sources and at different magnetic strengths

• Correlations between signature patterns of anatomical change and cognitive or behavioural profiles

• Generalisation of the techniques by a combination of mass data farming (e.g., all structural scans from a defined geographical area in the over 50s) and data trawling looking for patterns of atrophy using image classification to do epidemiology, create atrophy degree dependant cohorts for therapeutic trials etc…

• Searching for reliable quantitative disease biomarkers in neurodegeneration.




Key publications

1. Good CD, Johnsrude IS, Ashburner J, Henson RNA, Friston KJ, Frackowiak RSJ. (2001) A voxel-based morphometric study of ageing in 465 normal adult human brains. NeuroImage 14, 21-36.
2. Thieben MJ, Duggins AJ, Good CD, Gomes L, Mahant N, Richards F, McCusker E, Frackowiak RSJ. (2002) The distribution of structural neuropathology in pre-clinical Huntington’s disease. Brain 125, 1815-1828.
3. Morcom AM, Good CD, Frackowiak RSJ, Rugg MD. (2003) Age effects on the neural correlates of successful memory encoding Brain 126, 213-229.
4. Mechelli A, Friston KJ, Frackowiak RSJ, Price CJ. (2005) Structural covariance in the human cortex J. Neurosci. 25, 8303-8310.
5. Pariente J, Cole S, Henson R, Clare L, Kennedy A, Rossor M, Cipolotti L, Puel M, Demonet JF, Chollet F, Frackowiak RSJ. (2005) Alzheimer's patients engage an alternative network during a memory task. Ann. Neurol. 58, 870-879.
6. Rowe JB, Siebner H, Filipovic SR, Cordivari C, Gerschlager W, Rothwell J, Frackowiak RSJ. (2006) Aging is associated with contrasting changes in local and distant cortical connectivity in the human motor system. Neuroimage 32, 747-60.
7. Good CD, Frackowiak RSJ, Dolan RJ. (2006) Genetic association and brain morphology studies and the chromosome 8p22 pericentriolar material 1 (PCM1) gene in susceptibility to schizophrenia. Arch. Gen. Psychiatry 63, 844-54.
8. Stonnington CM, Tan G, Klöppel S, Chu C, Draganski B, Jack CR Jr, Chen K, Ashburner J, Frackowiak RSJ. (2008) Interpreting scan data acquired from multiple scanners: A study with Alzheimer's disease. Neuroimage 39, 1180-1185.
9. Klöppel S, Draganski B, Golding CV, Chu C, Nagy Z, Cook PA, Hicks SL, Kennard C, Alexander DC, Parker GJ, Tabrizi SJ, Frackowiak RSJ. (2008) White matter connections reflect changes in voluntary-guided saccades in pre-symptomatic Huntington's disease. Brain. 131, 196-204.
10. Kloppel S, Stonnington CM, Chu C, Draganski B, Scahill RI, Rohrer JD, Fox NC, Jack CR, Ashburner J, Frackowiak RSJ. (2008) Automatic classification of MR scans in Alzheimers disease. Brain 131, 681-689
11. Klöppel S, Stonnington CM, Barnes J, Chen F, Chu C, Good CD, Mader I, Mitchell LA, Patel AC, Roberts CC, Fox NC, Jack Jr CR, Ashburner J, Frackowiak RSJ. (2008) Accuracy of dementia diagnosis - A direct comparison between radiologists and a computerized method. Brain 131, 2969-2974.
12. Klöppel S, Chu C, Tan GC, Draganski B, Johnson H, Paulsen JS, Kienzle W, Tabrizi SJ, Ashburner J, Frackowiak RSJ; PREDICT-HD Investigators of the Huntington Study Group. (2009) Automatic detection of preclinical neurodegeneration: presymptomatic Huntington disease. Neurology 72, 426-31.
13. Klöppel S, Draganski B, Siebner HR, Tabrizi SJ, Weiller C, Frackowiak RSJ. (2009) Functional compensation of motor function in pre-symptomatic Huntington's disease. Brain 132, 1624- 32.
14. Stonnington CM, Chu C, Klöppel S, Jack Jr CR, Ashburner J, Frackowiak RSJ. (2010) Predicting clinical scores from magnetic resonance scans in Alzheimer's disease. NeuroImage 51: 1405-1413.
15. Tan GCY, Doke TF, Ashburner J, Wood NW, Frackowiak RSJ. (2010) Normal variation in fronto-occipital circuitry and cerebellar structure with an autism-associated polymorphism of CNTNAP2. NeuroImage 53, 1030–1042.



- Fonds National Suisse project grant - Synchronization Failure in Alzheimer’s Disease: Linking Brain Imaging and the Clinical Picture – 3 years CHF280K

- FNS Re’quip grant - Multimodal approach for in vivo exploration of functional and anatomical connectivity in the human brain – EEG equipment – CHF66K





CHUV - Rue du Bugnon 46 - CH-1011 Lausanne  -  Tel. +41 21 314 95 93  -  Fax +41 21 314 12 56
Swiss University