PMID- 17877822
OWN - NLM
STAT- MEDLINE
DCOM- 20071119
LR  - 20220129
IS  - 1472-6947 (Electronic)
IS  - 1472-6947 (Linking)
VI  - 7
DP  - 2007 Sep 18
TI  - Generating prior probabilities for classifiers of brain tumours using belief 
      networks.
PG  - 27
AB  - BACKGROUND: Numerous methods for classifying brain tumours based on magnetic 
      resonance spectra and imaging have been presented in the last 15 years. 
      Generally, these methods use supervised machine learning to develop a classifier 
      from a database of cases for which the diagnosis is already known. However, 
      little has been published on developing classifiers based on mixed modalities, 
      e.g. combining imaging information with spectroscopy. In this work a method of 
      generating probabilities of tumour class from anatomical location is presented. 
      METHODS: The method of "belief networks" is introduced as a means of generating 
      probabilities that a tumour is any given type. The belief networks are 
      constructed using a database of paediatric tumour cases consisting of data 
      collected over five decades; the problems associated with using this data are 
      discussed. To verify the usefulness of the networks, an application of the method 
      is presented in which prior probabilities were generated and combined with a 
      classification of tumours based solely on MRS data. RESULTS: Belief networks were 
      constructed from a database of over 1300 cases. These can be used to generate a 
      probability that a tumour is any given type. Networks are presented for 
      astrocytoma grades I and II, astrocytoma grades III and IV, ependymoma, 
      pineoblastoma, primitive neuroectodermal tumour (PNET), germinoma, 
      medulloblastoma, craniopharyngioma and a group representing rare tumours, 
      "other". Using the network to generate prior probabilities for classification 
      improves the accuracy when compared with generating prior probabilities based on 
      class prevalence. CONCLUSION: Bayesian belief networks are a simple way of using 
      discrete clinical information to generate probabilities usable in classification. 
      The belief network method can be robust to incomplete datasets. Inclusion of a 
      priori knowledge is an effective way of improving classification of brain tumours 
      by non-invasive methods.
FAU - Reynolds, Greg M
AU  - Reynolds GM
AD  - Department of Electrical, Electronic and Computer Engineering, University of 
      Birmingham, Birmingham, UK. gmr001@bham.ac.uk
FAU - Peet, Andrew C
AU  - Peet AC
FAU - Arvanitis, Theodoros N
AU  - Arvanitis TN
LA  - eng
GR  - G0601327/MRC_/Medical Research Council/United Kingdom
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20070918
PL  - England
TA  - BMC Med Inform Decis Mak
JT  - BMC medical informatics and decision making
JID - 101088682
SB  - IM
MH  - *Bayes Theorem
MH  - Brain Neoplasms/*classification/diagnosis
MH  - Child
MH  - Databases, Factual
MH  - *Decision Support Techniques
MH  - *Diagnosis, Computer-Assisted
MH  - Diagnosis, Differential
MH  - Germinoma/*classification/diagnosis
MH  - Humans
MH  - Magnetic Resonance Spectroscopy
MH  - Neoplasm Staging
MH  - Neuroectodermal Tumors/*classification/diagnosis
MH  - Probability
PMC - PMC2040142
EDAT- 2007/09/20 09:00
MHDA- 2007/12/06 09:00
PMCR- 2007/09/18
CRDT- 2007/09/20 09:00
PHST- 2007/05/12 00:00 [received]
PHST- 2007/09/18 00:00 [accepted]
PHST- 2007/09/20 09:00 [pubmed]
PHST- 2007/12/06 09:00 [medline]
PHST- 2007/09/20 09:00 [entrez]
PHST- 2007/09/18 00:00 [pmc-release]
AID - 1472-6947-7-27 [pii]
AID - 10.1186/1472-6947-7-27 [doi]
PST - epublish
SO  - BMC Med Inform Decis Mak. 2007 Sep 18;7:27. doi: 10.1186/1472-6947-7-27.