Discriminative Analysis of Migraine without Aura: Using Functional and Structural MRI with a Multi-Feature Classification Approach

Zhang, Qiongmin; Wu, Qisong; Zhang, Junran; He, Ling; Huang, Jiangtao; Zhang, Jiang; Huang, Hua; Gong, Qiyong

doi:10.1371/journal.pone.0163875

Cited by 44 publications

(41 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In meta-analyses, the prefrontal cortex was identified as being the most crucial brain area associated with structural change in migraine [ 32 , 33 ]. A discriminative analysis of migraine without aura (vs. controls) also identified, using a machine learning classifier, the superior frontal gyrus as one of the most discriminative GM features [ 34 ]. The present finding of a lower prefrontal GM volume in patients with migraine has three clinical implications.…”

Section: Discussionmentioning

confidence: 99%

Comparison of gray matter volume between migraine and “strict-criteria” tension-type headache

Chen

Chou²,

Lee

et al. 2018

J Headache Pain

View full text Add to dashboard Cite

BackgroundDespite evidently distinct symptoms, tension-type headache (TTH) and migraine are highly comorbid and exhibit many similarities in clinical practice. The purpose of this study was to investigate whether both types of headaches are similar in brain morphology.MethodsConsecutive patients with TTH and age- and sex-matched patients with migraine and healthy controls were enrolled for brain magnetic resonance imaging examination. Patients with TTH were excluded if they reported any headache features or associated symptoms of migraine. Changes in gray matter (GM) volume associated with headache diagnosis (TTH vs. migraine) and frequency (episodic vs. chronic) were examined using voxel-based morphometry. The correlation with headache profile and the discriminative ability between TTH and migraine were also investigated for these GM changes.ResultsIn comparison with controls (n = 43), the patients with TTH (25 episodic and 24 chronic) exhibited a GM volume increase in the anterior cingulate cortex, supramarginal gyrus, temporal pole, lateral occipital cortex, and caudate. The patients with migraine (31 episodic and 25 chronic) conversely exhibited a GM volume decrease in the orbitofrontal cortex. These GM changes did not correlate with any headache profile. A voxel-wise 2 × 2 factorial analysis further revealed the substantial effects of headache types and frequency in the comparison of GM volume between TTH and migraine. Specifically, the migraine group (vs. TTH) had a GM decrease in the superior and middle frontal gyri, cerebellum, dorsal striatum, and precuneus. The chronic group (vs. episodic group) otherwise demonstrated a GM decrease in the bilateral insula and anterior cingulate cortex. In receiver operating characteristic analysis, the GM volumes of the left superior frontal gyrus and right cerebellum V combined had good discriminative ability for distinguishing TTH and migraine (area under the curve = 0.806).ConclusionsTTH and migraine are separate headache disorders with different characteristics in relation to GM changes. The major morphological difference between the two types of headaches is the relative GM decrease of the prefrontal and cerebellar regions in migraine, which may reflect a higher allostatic load associated with this disabling headache.Electronic supplementary materialThe online version of this article (10.1186/s10194-018-0834-6) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of gray matter volume between migraine and “strict-criteria” tension-type headache

Chen

Chou²,

Lee

et al. 2018

J Headache Pain

View full text Add to dashboard Cite

show abstract

“…Upon comparing the results obtained using the two different CNNS, we found that the Inception module-based CNN shows a better performance than the AlexNet-based CNN. Compared with the support vector machine classifier that we previously analyzed (a final classification accuracy of 83.67%) [ 20 ], our approach provides preliminary support for deep learning methods combined with the fMRI features as a method for improving the discriminative power for migraine. In fact, we obtained an accuracy as high as 99.25% when using the RFCS feature in deep learning-based frameworks.…”

Section: Discussionmentioning

confidence: 99%

“…The first model we used was the CNN network based on AlexNet [ 21 ], and the second model was the CNN with Google’s Inception module. As a lot of information can be lost when decomposing 4D rs-fMRI data into 2D data, many fMRI studies use feature mapping instead of raw data as the original input [ 17 , 20 ]. Thus, after preprocessing, we extracted three indices—ALFF, ReHo and RFCS—as inputs to improve the classification results for migraine patients.…”

Section: Introductionmentioning

confidence: 99%

Multimodal MRI-based classification of migraine: using deep learning convolutional neural network

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundRecently, deep learning technologies have rapidly expanded into medical image analysis, including both disease detection and classification. As far as we know, migraine is a disabling and common neurological disorder, typically characterized by unilateral, throbbing and pulsating headaches. Unfortunately, a large number of migraineurs do not receive the accurate diagnosis when using traditional diagnostic criteria based on the guidelines of the International Headache Society. As such, there is substantial interest in developing automated methods to assist in the diagnosis of migraine.MethodsTo the best of our knowledge, no studies have evaluated the potential of deep learning technologies in assisting with the classification of migraine patients. Here, we used deep learning methods in combination with three functional measures (the amplitude of low-frequency fluctuations, regional homogeneity and regional functional correlation strength) based on rs-fMRI data to distinguish not only between migraineurs and healthy controls, but also between the two subtypes of migraine. We employed 21 migraine patients without aura, 15 migraineurs with aura, and 28 healthy controls.ResultsCompared with the traditional support vector machine classifier, which has an accuracy of 83.67%, our Inception module-based convolutional neural network approach showed a significant improvement in classification output (over 86.18%). Our data also indicate that the Inception module-based CNN performs better than the AlexNet-based CNN (Inception module-based CNN reached an accuracy of 99.25%). Finally, we also found that regional functional correlation strength (RFCS) could be regarded as the optimum input out of the three indices (ALFF, ReHo, RFCS).ConclusionsOverall, our study shows that combining the three functional measures of rs-fMRI with deep learning classification is a powerful method to distinguish between migraineurs and healthy individuals. Our data also highlight that deep learning-based frameworks could be used to develop more complicated models or systems to aid in clinical decision making in the future.Electronic supplementary materialThe online version of this article (10.1186/s12938-018-0587-0) contains supplementary material, which is available to authorized users.

show abstract

“…Similar changes in the reward circuitry had been observed before in episodic migraine patients, during the course of spontaneous migraine headache attacks ( DaSilva et al, 2014 ). However, in that case, instead of the NAc, the μ-opioid activation, represented by a decreased availability of μ-opioid receptors was found in the mPFC ( Figure 3 ), suggesting the possible contribution of this area to the migraine pathophysiology ( Zhang et al, 2016 ). The results of the two aforementioned studies also denote that specific regions within the reward system could be active by different chronic pain syndromes, though many other limbic regions that not the PFC (e.g., insula and amygdala) have been related to migraine ( Stankewitz and May, 2011 ).…”

Section: Plastic Changes In the Reward System Related To Chronic Painmentioning

confidence: 92%

Reward Circuitry Plasticity in Pain Perception and Modulation

2017

View full text Add to dashboard Cite

Although pain is a widely known phenomenon and an important clinical symptom that occurs in numerous diseases, its mechanisms are still barely understood. Owing to the scarce information concerning its pathophysiology, particularly what is involved in the transition from an acute state to a chronic condition, pain treatment is frequently unsatisfactory, therefore contributing to the amplification of the chronic pain burden. In fact, pain is an extremely complex experience that demands the recruitment of an intricate set of central nervous system components. This includes cortical and subcortical areas involved in interpretation of the general characteristics of noxious stimuli. It also comprises neural circuits that process the motivational-affective dimension of pain. Hence, the reward circuitry represents a vital element for pain experience and modulation. This review article focuses on the interpretation of the extensive data available connecting the major components of the reward circuitry to pain suffering, including the nucleus accumbens, ventral tegmental area, and the medial prefrontal cortex; with especial attention dedicated to the evaluation of neuroplastic changes affecting these structures found in chronic pain syndromes, such as migraine, trigeminal neuropathic pain, chronic back pain, and fibromyalgia.

show abstract

Discriminative Analysis of Migraine without Aura: Using Functional and Structural MRI with a Multi-Feature Classification Approach

Cited by 44 publications

References 52 publications

Comparison of gray matter volume between migraine and “strict-criteria” tension-type headache

Comparison of gray matter volume between migraine and “strict-criteria” tension-type headache

Multimodal MRI-based classification of migraine: using deep learning convolutional neural network

Reward Circuitry Plasticity in Pain Perception and Modulation

Contact Info

Product

Resources

About