Skip to main content

Anatomical connectivity changes in bipolar disorder and schizophrenia investigated using whole-brain tract-based spatial statistics and machine learning approaches

Abstract

Schizophrenia and bipolar disorder have similar clinical features. Their differential diagnosis is crucial because each has different prognostic and therapeutic characteristics. Earlier studies have used numerous methods, including magnetic resonance investigation, in an effort to differentiate these two disorders. Research has consistently shown that there is reduced white matter density in the fronto-temporal and fronto-thalamic pathways in both patients with bipolar disorder and schizophrenia; however, the sensitivity of the methods used is limited. Tract-based spatial statistics is a method of whole-brain analysis that relies on voxel-based comparison, and uses nonlinear image transformation and permutation tests with correction for multiple comparisons. The primary aim of the present study was to investigate anatomical connectivity changes in patients with bipolar disorder and schizophrenia using tract-based spatial statistics, to classify the patients according to white matter integrity patterns using machine learning, and to identify features that represent the key differences between the disorders. Whole-brain images of 41 bipolar disorder patients, 39 schizophrenia patients, and 23 controls were acquired using a 1.5 T magnetic resonance investigation scanner. As compared to the controls, the schizophrenia and bipolar disorder patients had reduced fractional anisotropy in similar white matter tracts. In addition, the imaging method employed differentiated the schizophrenia and bipolar disorder patients with 81.25% accuracy. Although the bipolar disorder and schizophrenia patients exhibited similar anatomical connectivity changes, as compared to the controls, the connectivity reductions in the right hemisphere in the bipolar disorder patients differentiated them from the schizophrenia patients. The present findings improve our understanding of the etiology and pathogenesis of bipolar disorder and schizophrenia, and can potentially be used as a biomarker for the diagnosis and treatment of both disorders.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

References

  1. American Psychiatric Association (2013) Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Publications, Washington

    Book  Google Scholar 

  2. Walker J, Curtis V, Murray RM (2002) Schizophrenia and bipolar disorder: similarities in pathogenic mechanisms but differences in neurodevelopment. Int Clin Psychopharmacol 17:S11–S19

    Google Scholar 

  3. Hill SK, Reilly JL, Harris MS, Rosen C, Marvin RW, DeLeon O, Sweeney JAA (2009) A comparison of neuropsychological dysfunction in first-episode psychosis patients with unipolar depression, bipolar disorder, and schizophrenia. Schizophr Res 113(2):167–175

    Article  Google Scholar 

  4. Berrettini WH (2000) Are schizophrenic and bipolar disorders related? A review of family and molecular studies. Biol Psychiatry 48(6):531–538

    Article  Google Scholar 

  5. Abi-Dargham A, Rodenhiser J, Printz D, Zea-Ponce Y, Gil R, Kegeles LS et al (2000) Increased baseline occupancy of D2 receptors by dopamine in schizophrenia. Proc Natl Acad Sci 97(14):8104–8109

    Article  Google Scholar 

  6. Jacobs D, Silverstone T (1986) Dextroamphetamine-induced arousal in human subjects as a model for mania. Psychiatr Med 16(02):323–329

    Google Scholar 

  7. Koreen AR, Siris SG, Chakos M, Alvir J (1993) Depression in first-episode schizophrenia. Am J Psychiatry 150(11):1643

    Article  Google Scholar 

  8. Pearlson GD, Ford JM (2014) Distinguishing between schizophrenia and other psychotic disorders. Schizophr Bull 40:501–503

    Article  Google Scholar 

  9. Vederine FE, Wessa M, Leboyer M, Houenou J (2011) A meta-analysis of whole-brain diffusion tensor imaging studies in bipolar disorder. Prog Neuropsychopharmacol Biol Psychiatry 35(8):1820–1826

    Article  Google Scholar 

  10. Lin F, Weng S, Xie B, Wu G, Lei H (2011) Abnormal frontal cortex white matter connections in bipolar disorder: a DTI tractography study. J Affect Disord 131(1):299–306

    Article  Google Scholar 

  11. Barnea-Goraly N, Chang KD, Karchemskiy A, Howe ME, Reiss AL (2009) Limbic and corpus callosum aberrations in adolescents with bipolar disorder: a tract-based spatial statistics analysis. Biol Psychiatry 66(3):238–244

    Article  Google Scholar 

  12. Versace A, Almeida JR, Hassel S, Walsh ND, Novelli M, Klein CR et al (2008) Elevated left and reduced right orbitomedial prefrontal fractional anisotropy in adults with bipolar disorder revealed by tract-based spatial statistics. Arch Gen Psychiatry 65(9):1041–1052

    Article  Google Scholar 

  13. Koch K, Wagner G, Dahnke R, Schachtzabel C, Schultz C, Roebel M et al (2010) Disrupted white matter integrity of corticopontine-cerebellar circuitry in schizophrenia. Eur Arch Psychiatry Clin Neurosci 260(5):419–426

    Article  Google Scholar 

  14. Lee SH, Kubicki M, Asami T, Seidman LJ, Goldstein JM, Mesholam-Gately RI et al (2013) Extensive white matter abnormalities in patients with first-episode schizophrenia: a diffusion tensor imaging (DTI) stud. Schizophr Res 143(2):231–238

    Article  Google Scholar 

  15. Liu X, Lai Y, Wang X, Hao C, Chen L, Zhou Z et al (2013) Reduced white matter integrity and cognitive deficit in never-medicated chronic schizophrenia: a diffusion tensor study using TBSS. Behav Brain Res 252:157–163

    Article  Google Scholar 

  16. Seal ML, Yücel M, Fornito A, Wood SJ, Harrison BJ, Walterfang M et al (2008) Abnormal white matter microstructure in schizophrenia: a voxelwise analysis of axial and radial diffusivity. Schizophr Res 101(1):106–110

    Article  Google Scholar 

  17. McIntosh AM, Maniega SM, Lymer GKS, McKirdy J, Hall J, Sussmann JE et al (2008) White matter tractography in bipolar disorder and schizophrenia. Biol Psychiatry 64(12):1088–1092

    Article  Google Scholar 

  18. Lu LH, Zhou XJ, Keedy SK, Reilly JL, Sweeney JA (2011) White matter microstructure in untreated first episode bipolar disorder with psychosis: comparison with schizophrenia. Bipolar Disord 13(7–8):604–613

    Article  Google Scholar 

  19. Jones DK, Symms MR, Cercignani M, Howard RJ (2005) The effect of filter size on VBM analyses of DT-MRI data. Neuroimage 26(2):546–554

    Article  Google Scholar 

  20. Simon TJ, Ding L, Bish JP, McDonald-McGinn DM, Zackai EH, Gee J (2005) Volumetric, connective, and morphologic changes in the brains of children with chromosome 22q11. 2 deletion syndrome: an integrative stud. Neuroimage 25(1):169–180

    Article  Google Scholar 

  21. Smith SM, Jenkinson M, Johansen-Berg H, Rueckert D, Nichols TE, Mackay CE et al (2006) Tract-based spatial statistics: voxelwise analysis of multi-subject diffusion data. Neuroimage 31(4):1487–1505

    Article  Google Scholar 

  22. Smith SM, Jenkinson M, Woolrich MW, Beckmann CF, Behrens TE, Johansen-Berg H et al (2004) Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23:S208–S219

    Article  Google Scholar 

  23. Smith SM (2002) Fast robust automated brain extraction. Hum Brain Mapp 17(3):143–155

    Article  Google Scholar 

  24. Mori S, Wakana S, Nagae-Poetscher LM, Van Zijl PCM (2006) MRI atlas of human white matter. Am J Neuroradiol 27(6):1384

    Google Scholar 

  25. Philippi CL, Mehta S, Grabowski T, Adolphs R, Rudrauf D (2009) Damage to association fiber tracts impairs recognition of the facial expression of emotion. J Neurosci 29(48):15089–15099

    Article  Google Scholar 

  26. Catani M, De Schotten MT (2008) A diffusion tensor imaging tractography atlas for virtual in vivo dissections. Cortex 44(8):1105–1132

    Article  Google Scholar 

  27. Martino J, Brogna C, Robles SG, Vergani F, Duffau H (2010) Anatomic dissection of the inferior fronto-occipital fasciculus revisited in the lights of brain stimulation data. Cortex 46(5):691–699

    Article  Google Scholar 

  28. Bruno S, Cercignani M, Ron MA (2008) White matter abnormalities in bipolar disorder: a voxel-based diffusion tensor imaging study. Bipolar Disord 10(4):460–468

    Article  Google Scholar 

  29. Garibotto V, Scifo P, Gorini A, Alonso CR, Brambati S, Bellodi L, Perani D (2010) Disorganization of anatomical connectivity in obsessive compulsive disorder: a multi-parameter diffusion tensor imaging study in a subpopulation of patients. Neurobiol Disord 37(2):468–476

    Article  Google Scholar 

  30. Jacobson S, Kelleher I, Harley M, Murtagh A, Clarke M, Blanchard M et al (2010) Structural and functional brain correlates of subclinical psychotic symptoms in 11–13 year old schoolchildren. Neuroimage 49(2):1875–1885

    Article  Google Scholar 

  31. Adler CM, Holland SK, Schmithorst V, Wilke M, Weiss KL, Pan H, Strakowski SM (2004) Abnormal frontal white matter tracts in bipolar disorder: a diffusion tensor imaging study. Bipolar Disord 6(3):197–203

    Article  Google Scholar 

  32. Catani M, Jones DK, Donato R, Ffytche DH (2003) Occipito-temporal connections in the human brain. Brain 126(9):2093–2107

    Article  Google Scholar 

  33. Shinoura N, Suzuki Y, Tsukada M, Katsuki S, Yamada R, Tabei Y et al (2007) Impairment of inferior longitudinal fasciculus plays a role in visual memory disturbance. Neurocase 13(2):127–130

    Article  Google Scholar 

  34. Townsend J, Altshuler LL (2012) Emotion processing and regulation in bipolar disorder: a review. Bipolar Disord 14(4):326–339

    Article  Google Scholar 

  35. Carlson PJ, Singh JB, Zarate CA, Drevets WC, Manji HK (2006) Neural circuitry and neuroplasticity in mood disorders: insights for novel therapeutic targets. NeuroRx 3(1):22–41

    Article  Google Scholar 

  36. Frey BN, Andreazza AC, Nery FG, Martins MR, Quevedo J, Soares JC, Kapczinski F (2007) The role of hippocampus in the pathophysiology of bipolar disorder. Behav Pharmacol 18(5–6):419–430

    Article  Google Scholar 

  37. Strasser HC, Lilyestrom J, Ashby ER, Honeycutt NA, Schretlen DJ, Pulver A et al (2005) Hippocampal and ventricular volumes in psychotic and nonpsychotic bipolar patients compared with schizophrenia patients and community control subjects: a pilot study. Biol Psychiatry 57(6):633–639

    Article  Google Scholar 

  38. De Schotten MT, Dell’Acqua F, Forkel SJ, Simmons A, Vergani F, Murphy DG, Catani M (2011) A lateralized brain network for visuospatial attention. Nat Neurosci 14(10):1245–1246

    Article  Google Scholar 

  39. Magioncalda P, Martino M, Conio B, Piaggio N, Teodorescu R, Escelsior A et al (2016) Patterns of microstructural white matter abnormalities and their impact on cognitive dysfunction in the various phases of type I bipolar disorder. J Affect Disord 193:39–50

    Article  Google Scholar 

  40. Strakowski SM, DelBello MP, Adler CM (2005) The functional neuroanatomy of bipolar disorder: a review of neuroimaging findings. Mol Psychiatry 10(1):105

    Article  Google Scholar 

  41. Forstner AJ, Hecker J, Hofmann A, Maaser A, Reinbold CS, Mühleisen TW et al (2017) Identification of shared risk loci and pathways for bipolar disorder and schizophrenia. PLoS ONE 12(2):e0171595

    Article  Google Scholar 

  42. Oouchi H, Yamada K, Sakai K, Kizu O, Kubota T, Ito H, Nishimura T (2007) Diffusion anisotropy measurement of brain white matter is affected by voxel size: underestimation occurs in areas with crossing fibers. Am J Neuroradiol 28(6):1102–1106

    Article  Google Scholar 

  43. Zhang J, Chen RH, Wang MJ, Tian WX, Su GH, Qiu SZ (2017) Prediction of LBB leakage for various conditions by genetic neural network and genetic algorithms. Nucl Eng Des 325:33–43

    Article  Google Scholar 

  44. Sergeeva M, Delahaye D, Mancel C, Vidosavljevic A (2017) Dynamic airspace configuration by genetic algorithm. J Traffic Transp Eng (English edition) 4(3):300–314

    Article  Google Scholar 

  45. Chowdhury B, Garai G (2017) A review on multiple sequence alignment from the perspective of genetic algorithm. Genomics 109(5–6):419–431

    Article  Google Scholar 

  46. Jafari-Marandi R, Smith BK (2017) Fluid genetic algorithm (FGA). J Comput Des Eng 4(2):158–167

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Baris Metin.

Ethics declarations

Conflict of interest

The authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix 1: Artificial neural network—supervised learning

An artificial neural network (ANN) could be described as a machine learning approach that mimics a biological nervous system, and is a powerful modeling tool for approximating nonlinear relationships and finding patterns within a dataset. An ANN is a structure used for processing information and approximating functions based on a number of inputs. With adaptive ability to be used as an arbitrary function approximation mechanism, ANNs “learn” from the observed data. Following the training process, an ANN model predicts response for any given input. That is, an ANN can be used to infer a function based on the collected input/output data. The main features of an ANN are learning adaptation, generalization, massive parallelism, robustness, and abstraction. The structure of a basic ANN can be theoretically modeled, as depicted in Fig. 4, where X{xi, i = 1, 2, …, n} is the input matrix to the neuron and Y denotes the output of the model.

Fig. 4
figure 4

Basic structure of an ANN

Inputs are connected to each neuron via a mathematical process. Each input is multiplied by a weight (wi) associated with each neuron, and a constant bias (b) is added to that scalar value. The process is repeated for each input for all neurons, and finally, their sum goes through a transfer function (f) that is expressed as given in Eq. 1 [8].

$$Y = f\left( {\mathop \sum \limits_{i = 1}^{n} w_{i} x_{i} + b} \right)$$
(1)

There is a wide variety of transfer functions and selection of the proper transfer function is crucial. As there is a nonlinear relationship between the input and output, nonlinear transfer functions are widely adopted for medical image processing. With selection of proper activation functions and connection of neurons, various neural networks can be constructed and trained to generate specified outputs. ANN learning paradigms for medical image processing generally include supervised learning and unsupervised learning. For supervised learning, a network is trained with preset input and output data. During the training process, a set of inputs is used to generate associated output values until the ANN output converges to the reference target with a predefined error value that is ideally zero. Accordingly, the aim of the training process is to minimize the network’s overall output error for all training cases by iteratively adjusting the neuron connection weights and bias values using a specific training algorithm.

Training process

BP neural network is a typical multilayer feed-forward network trained according to backpropagation algorithm. BP neural network uses parallel distributed processing approach to handle both qualitative and quantitative knowledge. It has strong robustness, fault tolerance, and adaptability and can fully approximate any complex nonlinear relationship. Because of these advantages, BP neural network is more appropriate for processing EEG data which are possible noisy, unstable, and nonlinear. In this study, for modeling process, feed-forward neural network trained by a backpropagation algorithm is used. The network is based on the supervised procedure, i.e., the network constructs a model based on examples of data with known outputs. The architecture of the network is a layered feed-forward neural network, in which the nonlinear elements (neurons) are arranged in successive layers, and the information flows from input layer to output layer, through the hidden layer(s). Sigmoid transfer function used in each neuron because of its nonlinear behavior. In order to minimize the error between the model output and a reference value, MSE (mean square error) is used as the cost function, given in Eq. 2. The cost function is minimized by GA.

$$J\left( w \right) = \frac{1}{N}\mathop \sum \limits_{k = 1}^{N} \left( {y_{k} - z_{k} } \right)^{2}$$
(2)

The sigmoid function was used in the present study as the activation function, and TrainBR (Bayesian regularization backpropagation) was used as the training algorithm. TrainBR is a function that updates the weight and bias values according to the Levenberg–Marquardt optimization method, and minimizes a combination of squared errors and weights in order to determine the correct combinations, so that the generated model can generalize well. For the validation process, fourfold cross-validation with shuffled sampling was employed. The ANN structure was set as a multilayer perceptron (MLP)—a powerful function approximator for prediction and classification using a supervised learning algorithm. The architecture of an MLP neural network is constructed with two layers. A basic two-layer ANN contains an input layer connected to input variables and an output layer that generates the corresponding output. Although an MLP is a satisfactory approximator for linear problems, hidden layers for analyzing nonlinearity and complexity problems are added.

Appendix 2: Genetic neural network

A genetic algorithm (GA) is a very powerful meta-heuristic and evolutionary algorithm that has been used with other evolutionary algorithms for multiple problems across disciplines. Despite the advent of newly adapted meta-heuristic methods, GA remains a popular choice for solving many challenging optimization problems for exact methods that are computationally too expensive. Moreover, due to its intrinsic structure, which is similar to the use of a set (a population) of solutions to be optimized in parallel, GA is considered a natural method for solving problems with multi-objective characteristics.

GA is a stochastic approach inspired by actual genetic processes and follows the “survival of the fittest” mechanism. GA is widely used for optimizing large, complex, and multi-dimensional problems, and generating optimal solutions. The optimization process begins with a set of possible solutions obtained from the whole search space consisting of all features. Each solution is encoded by a set of string expressions (referred to as chromosomes). The set of chromosomes are considered the population. Via the optimization process shown in Fig. 5, the performance of each string is associated with an objective function that evaluates the fitness of a string for the next generation. As such, the objective function is referred to as the fitness function. Considering the fitness values of the strings, the fittest strings are selected and genetic operators, such as crossover and mutation, are applied to generate subsequent generations. This process of selection, crossover, and mutation is iteratively repeated until a maximum number of generations are performed. Therefore, with an adaptive structure GA is able to converge to the best solution (chromosome) that is either the global or the almost global optimal solution. The design process of GA is based primarily on four parameters (population size, crossover rate, mutation rate, and elitist selection), whereas the objective function is defined according the problem. Here, the objective function is taken into consideration apart from the aforementioned four features and only modification to the objective function is sufficient for changing the GA for new problems [43,44,45,46].

Fig. 5
figure 5

Flowchart of an ANN-GA architecture

Fitness function of the wrapper approach

A fitness function is used to put forth the degree of goodness of selected subset. For a classification problem, if two subsets with different number of features present quite similar performance, the subset with less number of features comes into prominence. Therefore, the evaluation of fitness function regards two concerns: the classification accuracy and the number of features in the subset. In order to satisfy these concerns, the fitness function is designed in terms of both accuracy and number of features as:

$$f\left( {x_{j} } \right) = m*J\left( {X_{j} } \right) + n*\left( {1/\left| {X_{j} } \right|} \right)$$
(3)

where Xj is the subset constituted by jth chromosome, J(Xj) is the classification accuracy using Xj, |Xj| is the number of features of Xj, and m ∈ [0, 1] and n ∈ [0, 1] are the two coefficients used assign relative importance to classification accuracy and number of the selected subset parameters.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sutcubasi, B., Metin, S.Z., Erguzel, T.T. et al. Anatomical connectivity changes in bipolar disorder and schizophrenia investigated using whole-brain tract-based spatial statistics and machine learning approaches. Neural Comput & Applic 31, 4983–4992 (2019). https://doi.org/10.1007/s00521-018-03992-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-018-03992-y

Keywords

  • Bipolar disorder
  • Schizophrenia
  • Tract-based spatial statistics
  • Machine learning