Machine learning classification of schizophrenia patients and healthy controls using diverse neuroanatomical markers and Ensemble methods.

Schizophrenia is a major psychiatric disorder that imposes enormous clinical burden on patients and their caregivers. Determining classification biomarkers can complement clinical measures and improve understanding of the neural basis underlying schizophrenia. Using neuroanatomical features, several machine learning based investigations have attempted to classify schizophrenia from healthy controls but the range of neuroanatomical measures employed have been limited in range to date. In this study, we sought to classify schizophrenia and healthy control cohorts using a diverse set of neuroanatomical measures (cortical and subcortical volumes, cortical areas and thickness, cortical mean curvature) and adopted Ensemble methods for better performance. Additionally, we correlated such neuroanatomical features with Quality of Life (QoL) assessment scores within the schizophrenia cohort. With Ensemble methods and diverse neuroanatomical measures, we achieved classification accuracies ranging from 83 to 87%, sensitivities and specificities varying between 90-98% and 65-70% respectively. In addition to lower QoL scores within schizophrenia cohort, significant correlations were found between specific neuroanatomical measures and psychological health, social relationship subscale domains of QoL. Our results suggest the utility of inclusion of subcortical and cortical measures and Ensemble methods to achieve better classification performance and their potential impact of parsing out neurobiological correlates of quality of life in schizophrenia.

Deformable Registration-Based Super-resolution for Isotropic Reconstruction of 4-D MRI Volumes.

Multi-plane super-resolution (SR) has been widely employed for resolution improvement of MR images. However, this has mostly been limited to MRI acquisitions with rigid motion. In cases of non-rigid motion, volumes are usually pre-registered using deformable registration methods before SR reconstruction. The pre-registered images are then used as input for the SR reconstruction. Since deformable registration involves smoothening of the inputs, using pre-registered inputs could lead to loss in information in SR reconstructions. Additionally, any registration errors present in pre-registered inputs could propagate throughout SR reconstructions leading to error accumulation. To address these limitations, in this study, we propose a deformable registration-based super-resolution reconstruction (DIRSR) reconstruction, which handles deformable registration as part of super-resolution. This approach has been demonstrated using 12 synthetic 4-D MRI lung datasets created using single plane (coronal) datasets of six patients and multi-plane (coronal and axial) 4-D lung MRI dataset of one patient. From our evaluation, DIRSR reconstructions are sharper and well aligned compared to reconstructions using SR of pre-registered inputs and rigid-registration SR. MSE, SNR and SSIM evaluations also indicate better reconstruction quality from DIRSR compared to reconstructions from SR of pre-registered inputs (p-value less than 0.0001). In conclusion, we found superior isotropic reconstructions of 4-D MR datasets from DIRSR reconstructions, which could benefit volumetric MR analyses.

A preclinical evaluation of an autologous living hyaline-like cartilaginous graft for articular cartilage repair: a pilot study.

In this pilot study, an autologous synthetic scaffold-free construct with hyaline quality, termed living hyaline cartilaginous graft (LhCG), was applied for treating cartilage lesions. Implantation of autologous LhCG was done at load-bearing regions of the knees in skeletally mature mini-pigs for 6 months. Over the course of this study, significant radiographical improvement in LhCG treated sites was observed via magnetic resonance imaging. Furthermore, macroscopic repair was effected by LhCG at endpoint. Microscopic inspection revealed that LhCG engraftment restored cartilage thickness, promoted integration with surrounding native cartilage, produced abundant cartilage-specific matrix molecules, and re-established an intact superficial tangential zone. Importantly, the repair efficacy of LhCG was quantitatively shown to be comparable to native, unaffected cartilage in terms of biochemical composition and biomechanical properties. There were no complications related to the donor site of cartilage biopsy. Collectively, these results imply that LhCG engraftment may be a viable approach for articular cartilage repair.

Diffusion weighted magnetic resonance imaging and its recent trend-a survey.

Since its inception in 1985, diffusion weighted magnetic resonance imaging has been evolving and is becoming instrumental in diagnosis and investigation of tissue functions in various organs including brain, cartilage, and liver. Even though brain related pathology and/or investigation remains as the main application, diffusion weighted magnetic resonance imaging (DWI) is becoming a standard in oncology and in several other applications. This review article provides a brief introduction of diffusion weighted magnetic resonance imaging, challenges involved and recent advancements.