Rozpoznávání pacientů s první epizodou schizofrenie s využitím obrazů mozku z MRI
SCHWARZ, Daniel, Tomáš KAŠPÁREK and Eva JANOUŠOVÁ. Rozpoznávání pacientů s první epizodou schizofrenie s využitím obrazů mozku z MRI (Recognition of the First-Episode Schizophrenia Patients with the Use of MRI Brain Images). Clinician and Technology (Lékař a technika). Praha: Czech Medical Association J.E.Purkyne, 2011, vol. 41, No 1, p. 27-34. ISSN 0301-5491. |
Other formats:
BibTeX
LaTeX
RIS
|
Basic information | |
---|---|
Original name | Rozpoznávání pacientů s první epizodou schizofrenie s využitím obrazů mozku z MRI |
Name (in English) | Recognition of the First-Episode Schizophrenia Patients with the Use of MRI Brain Images |
Authors | SCHWARZ, Daniel, Tomáš KAŠPÁREK and Eva JANOUŠOVÁ. |
Edition | Clinician and Technology (Lékař a technika), Praha, Czech Medical Association J.E.Purkyne, 2011, 0301-5491. |
Other information | |
---|---|
Original language | Czech |
Type of outcome | Article in a journal |
Field of Study | 30000 3. Medical and Health Sciences |
Country of publisher | Czech Republic |
Confidentiality degree | is not subject to a state or trade secret |
Organization unit | Institute of Biostatistics and Analyses |
Keywords (in Czech) | registrace obrazů, rozpoznávání vzorů, výpočetní neuroanatomie, schizofrenie |
Keywords in English | image registration, pattern recognition, computational neuroanatomy, schizophrenia |
Tags | International impact, Reviewed |
Changed by | Changed by: doc. Ing. Daniel Schwarz, Ph.D., učo 195581. Changed: 20/2/2012 16:42. |
Abstract |
---|
Schizofrenie je závažná, invalidizující psychická porucha. Studium morfologických změn v mozku pacientů s první epizodou schizofrenie je výhodné z hlediska omezení vlivu mnoha nežádoucích faktorů, jako je dlouhodobá medikace nebo možná progrese morfologických změn. Abnormity zachycené na počátku nemoci mohou spíše ukazovat na její primární patologii. V článku je prezentována kombinace pružné registrace strukturálních MRI obrazů mozku s klasifikačními algoritmy z oblasti rozpoznávání vzorů, která umožňuje realizovat postup pro rozlišení pacientů s první epizodou schizofrenie od zdravých dobrovolníků. Je zde navržen originální postup výběru příznaků z 3-D MRI obrazových dat pro klasifikaci a na dostupných datech 173 subjektů je porovnávána sensitivita, specificita, celková správnost a přesnost klasifikace algoritmů k-NN a SVM. Dosažená kvalita klasifikace je srovnatelná s recentně publikovanými výsledky obdobně zaměřených prací. |
Abstract (in English) |
---|
Schizophrenia is one of psychiatric disorders which lead often to violation of the social and economic competencies of the patients. The possibility to uncover potentially high-risk patients may enable searching for preventive and therapeutic strategies, which would be able to eliminate or minimize the adverse effects of the disease. Deformation-based morphometry (DBM) has been used to uncover structural inter-group differences in MRI-based neuropsychiatric studies recently. We use 3-D deformation fields resulting from cross-subject registrations to construct classifiers which are able to recognize first-episode schizophrenia patients from healthy controls. The k-Nearest Neighbors (k-NN) and the Support Vector Machines (SVM) classification methods are compared in terms of their sensitivity, specificity, overall accuracy and precision. High-resolution T1-weighted MRI brain images of 173 male subjects were obtained with a Siemens 1.5 T system. The group contained 49 patients with first-episode schizophrenia (FES), and 124 healthy controls (NC). The brain template from Simulated Brain Database was used as the reference anatomy in the high-dimensional nonlinear registration technique based on the maximization of normalized mutual information. The resulting spatial deformations were converted into scalar fields by calculating Jacobian determinants, which characterize local volume shrinkages or enlargements in each voxel. The scalar fields were then analyzed voxel-by-voxel using t-tests with the age of the subjects as a covariate. Significant local volume changes were found with a threshold set to p-value<0.05 corrected by false discovery rate method. The k-NN as well as the SVM classifiers used the significant volume changes as the features in the following classification. Multiple leave-one-out cross-validation was used to evaluate the accuracy of the classification. Due to unequal numbers of subjects in each class, 10 randomly selected subsets of healthy controls were used for evaluation to avoid preference of the NC class. Both classifiers were trained with the same 97 (49+49-1) vectors of 70 845 features. The k-NN classifier gave the best results with k=11 and the cosine metric, median sensitivity was 70%, median specificity was 73% and median accuracy was 72%. The linear SVM classifier gave median sensitivity 80%, median specificity 78% and median accuracy 79%. The accuracy of the algortihm is comparable to state-of-the-art methods for MRI-based schizophrenia classification. |
Links | |
---|---|
NS10347, research and development project | Name: Moderní metody rozpoznávání pro analýzu obrazových dat v neuropsychiatrickém výzkumu |
Investor: Ministry of Health of the CR | |
NS9893, research and development project | Name: Predikce průběhu iniciálních fází schizofrenie pomocí morfologie mozku |
Investor: Ministry of Health of the CR |
PrintDisplayed: 30/8/2024 04:49