Chained regularization for identifying brain patterns specific to HIV infection.
Chained regularization for identifying brain patterns specific to HIV infection.
复制标题
DOI：
10.1016/j.neuroimage.2018.08.022
复制
发表时间：
2018-12
期刊：
影响因子：
5.7
通讯作者：
Pohl KM
中科院分区：
文献类型：
--
作者：
Adeli E;Kwon D;Zhao Q;Pfefferbaum A;Zahr NM;Sullivan EV;Pohl KM
尽管联合抗逆转录病毒疗法（cART）在降低HIV病毒载量和改善免疫功能方面有效，但人类免疫缺陷病毒（HIV）感染继续具有重大不利的公共卫生和临床后果。随着成功治疗的艾滋病毒感染者年龄的增长，他们的认知能力下降速度比正常衰老更快。这一现象强调了改善长期护理的重要性，这需要更好地了解艾滋病毒对大脑的影响。在本文中，受HIV感染影响的患者和大脑区域的自动识别被建模为分类问题，其解决方案在我们提出的链式正则化框架内分两步确定。第一步侧重于选择HIV模式（即，用于区分HIV感染受试者和健康对照的脑区域测量的最具信息量的星座）。第二步通过约束相对于所选测量值的参数化和欧几里得正则化（Euclidean regularization）（Euclidean 2-norm）来提高分类精度。当应用于65名对照和65名HIV感染者的皮质和皮质下结构磁共振图像（MRI）测量时，这种方法在区分两个队列方面比更常见的模型更准确。最后，确定的HIV模式的大脑区域与使用传统组分析模型的HIV文献一致。
Human Immunodeficiency Virus (HIV) infection continues to have major adverse public health and clinical consequences despite the effectiveness of combination Antiretroviral Therapy (cART) in reducing HIV viral load and improving immune function. As successfully treated individuals with HIV infection age, their cognition declines faster than reported for normal aging. This phenomenon underlines the importance of improving long-term care, which requires better understanding of the impact of HIV on the brain. In this paper, automated identification of patients and brain regions affected by HIV infection are modeled as a classification problem, whose solution is determined in two steps within our proposed Chained-Regularization framework. The first step focuses on selecting the HIV pattern (i.e., the most informative constellation of brain region measurements for distinguishing HIV infected subjects from healthy controls) by constraining the search for the optimal parameter setting of the classifier via group sparsity (ℓ2,1-norm). The second step improves classification accuracy by constraining the parameterization with respect to the selected measurements and the Euclidean regularization (ℓ2-norm). When applied to the cortical and subcortical structural Magnetic Resonance Images (MRI) measurements of 65 controls and 65 HIV infected individuals, this approach is more accurate in distinguishing the two cohorts than more common models. Finally, the brain regions of the identified HIV pattern concur with the HIV literature that uses traditional group analysis models.
登录
查看更多内容
影响因子：
4.4
作者：
Correa, Diogo Goulart;Zimmermann, Nicolle;Gasparetto, Emerson Leandro
通讯作者：
Gasparetto, Emerson Leandro
影响因子：
3.3
作者：
Arlot, Sylvain;Celisse, Alain
通讯作者：
Celisse, Alain
影响因子：
9.9
作者：
Castelo, J. M. B.;Sherman, S. J.;Stern, C. E.
通讯作者：
Stern, C. E.
影响因子：
10.9
作者：
Avants, B. B.;Epstein, C. L.;Gee, J. C.
通讯作者：
Gee, J. C.
影响因子：
56.3
作者：
Clifford, David B.;Ances, Beau M.
通讯作者：
Ances, Beau M.