Biology subjects

Yeh, F.-C.

Publications and source records attributed to Yeh, F.-C..

7 recordsLinked to original sources

bioRxiv2018

Small Data Challenge: Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size

Deep neural networks have gained immense popularity in the Big Data problem; however, the availability of training samples can be relatively limited in certain application domains, particularly medical imaging, and consequently leading to overfitting problems. This \"Small Data\" challenge may need a mindset that is entirely different from the existing Big Data paradigm. Here, under the small data setting, we examined whether the network structure has a substantial influence on the performance and whether the optimal structure is predominantly determined by sample size or data nature. To this end, we listed all possible combinations of layers given an upper bound of the VC-dimension to study how structural hyperparameters affected the performance. Our results showed that structural optimization improved accuracy by 27.99%, 16.44%, and 13.11% over random selection for a sample size of 100, 500, and 1,000 in the MNIST dataset, respectively, suggesting that the importance of the network structure increases as the sample size becomes smaller. Furthermore, the optimal network structure was mostly determined by the data nature (photographic, calligraphic, or medical images), and less affected by the sample size, suggesting that the optimal network structure is data-driven, not sample size driven. After network structure optimization, the conventional convolutional neural network could achieve 91.13% in accuracy with only 500 samples, 93.66% in accuracy with only 1000 samples for the MNIST dataset and 94.10% in accuracy with only 3300 samples for the Mitosis (microscopic) dataset. These results indicate the primary importance of the network structure and the nature of the data in facing the Small Data challenge.

bioengineering↗

bioRxiv2018

Improved Accuracy of Diffusion MRI Tractography Using Topology-Informed Pruning (TIP)

Diffusion MRI fiber tracking provides a non-invasive method for mapping the trajectories of human brain connections, but its false connection problem has been a major challenge. This study introduces topology-informed pruning (TIP), a method that automatically identifies singular tracts and eliminates them to improve the tracking accuracy. The accuracy of the tractography with and without TIP was evaluated by a team of 6 neuroanatomists in a blinded setting to examine whether TIP could improve the accuracy. The results showed that TIP improved the tracking accuracy by 11.93% in the single-shell scheme and by 3.47% in the grid scheme. The improvement is significantly different from a random pruning (p-value < 0.001). The diagnostic agreement between TIP and neuroanatomists was comparable to the agreement between neuroanatomists. The proposed TIP algorithm can be used to automatically clean up noisy fibers in deterministic tractography, with a potential to confirm the existence of a fiber connection in basic neuroanatomical studies or clinical neurosurgical planning.

neuroscience↗

bioRxiv2018

Lead-DBS v2: Toward a comprehensive pipeline for deep brain stimulation imaging

Deep brain stimulation (DBS) is a highly efficacious treatment option for movement disorders and a growing number of other indications are investigated in clinical trials. To ensure optimal treatment outcome, exact electrode placement is required. Moreover, to analyze the relationship between electrode location and clinical results, a precise reconstruction of electrode placement is required, posing specific challenges to the field of neuroimaging. Since 2014 the open source toolbox Lead-DBS is available, which aims at facilitating this process. The tool has since become a popular platform for DBS imaging. With support of a broad community of researchers worldwide, methods have been continuously updated and complemented by new tools for tasks such as multispectral nonlinear registration, structural / functional connectivity analyses, brain shift correction, reconstruction of microelectrode recordings and orientation detection of segmented DBS leads. The rapid development and emergence of these methods in DBS data analysis require us to revisit and revise the pipelines introduced in the original methods publication. Here we demonstrate the updated DBS and connectome pipelines of Lead-DBS using a single patient example with state-of-the-art high-field imaging as well as a retrospective cohort of patients scanned in a typical clinical setting at 1.5T. Imaging data of the 3T example patient is co-registered using five algorithms and nonlinearly warped into template space using ten approaches for comparative purposes. After reconstruction of DBS electrodes (which is possible using three methods and a specific refinement tool), the volume of tissue activated is calculated for two DBS settings using four distinct models and various parameters. Finally, four whole-brain tractography algorithms are applied to the patients preoperative diffusion MRI data and structural as well as functional connectivity between the stimulation volume and other brain areas are estimated using a total of eight approaches and datasets. In addition, we demonstrate impact of selected preprocessing strategies on the retrospective sample of 51 PD patients. We compare the amount of variance in clinical improvement that can be explained by the computer model depending on the method of choice.\n\nThis work represents a multi-institutional collaborative effort to develop a comprehensive, open source pipeline for DBS imaging and connectomics, which has already empowered several studies, and may facilitate a variety of future studies in the field.

neuroscience↗

bioRxiv2018

A Quantitative Tractography Study into the Connectivity, Segmentation and Laterality of the Human Inferior Longitudinal Fasciculus

The human inferior longitudinal fasciculus (ILF) is a ventral, temporo-occipital association tract. Though described in early neuroanatomical works, its existence was later questioned. Application of in vivo tractography to the neuroanatomical study of the ILF has generally confirmed its existence, however consensus is lacking regarding its subdivision, laterality and connectivity. Further, there is a paucity of detailed neuroanatomic data pertaining to the exact anatomy of the ILF. Generalized Q-Sampling imaging (GQI) is a non-tensor tractographic modality permitting high resolution imaging of white-matter structures. As it is a non-tensor modality, it permits visualization of crossing fibers and accurate delineation of close-proximity fiber-systems. We applied deterministic GQI tractography to data from 30 healthy subjects and a large-volume diffusion atlas, to delineate ILF anatomy. Post-mortem white matter dissection was also carried out in a cadaveric specimen for further validation. The ILF was found in all 60 hemispheres. At its occipital extremity, it demonstrated a trifurcated termination pattern which was used to separate the ILF into 3 distinct sub-fascicles: Dorsolateral, ventrolateral and ventromedial. These divisions were consistent across the subject set and within the atlas. We applied quantitative techniques to study connectivity strength of the ILF at its anterior and posterior extremities. Overall, the 3 sub-fascicles, and the whole ILF, demonstrated strong leftward-lateralized connectivity patterns. Leftward-lateralization was also found for ILF volumes across the subject set. Due to connective and volumetric leftward-dominance and ventral location, we postulate the ILFs role in the semantic system. Further, our results are in agreement with functional and lesion-based postulations pertaining to the ILFs role in facial recognition.

neuroscience↗

bioRxiv2017

A Population-Based Atlas Of The Macroscale Structural Connectome In The Human Brain

A comprehensive map of the structural connectome in the human brain has been a coveted resource for understanding macroscopic brain networks. Here we report an expert-vetted, population-averaged atlas of the structural connectome derived from diffusion MRI data (N=842). This was achieved by creating a high-resolution template of diffusion patterns averaged across individual subjects and using tractography to generate 550,000 trajectories of representative white matter fascicles annotated by 80 anatomical labels. The trajectories were subsequently clustered and labeled by a team of experienced neuroanatomists in order to conform to prior neuroanatomical knowledge. A multi-level network topology was then described using whole-brain connectograms, with subdivisions of the association pathways showing small-worldness in intra-hemisphere connections, projection pathways showing hub structures at thalamus, putamen, and brainstem, and commissural pathways showing bridges connecting cerebral hemispheres to provide global efficiency. This atlas of the structural connectome provides representative organization of human brain white matter, complementary to traditional histologically-derived and voxel-based white matter atlases, allowing for better modeling and simulation of brain connectivity for future connectome studies.

neuroscience↗

bioRxiv2017

Local Connectome Phenotypes Predict Social, Health, and Cognitive Factors

The unique architecture of the human connectome is defined initially by genetics and subsequently sculpted over time with experience. Thus, similarities in predisposition and experience that lead to similarities in social, biological, and cognitive attributes should also be reflected in the local architecture of white matter fascicles. Here we employ a method known as local connectome fingerprinting that uses diffusion MRI to measure the fiber-wise characteristics of macroscopic white matter pathways throughout the brain. This fingerprinting approach was applied to a large sample (N=841) of subjects from the Human Connectome Project, revealing a reliable degree of between-subject correlation in the local connectome fingerprints, with a relatively complex, low-dimensional substructure. Using a cross-validated, high-dimensional regression analysis approach, we derived local connectome phenotype (LCP) maps that could reliably predict a subset of subject attributes measured, including demographic, health and cognitive measures. These LCP maps were highly specific to the attribute being predicted but also sensitive to correlations between attributes. Collectively, these results indicate that the local architecture of white matter fascicles reflects a meaningful portion of the variability shared between subjects along several dimensions.\n\nAuthor SummaryThe local connectome is the pattern of fiber systems (i.e., number of fibers, orientation, and size) within a voxel and reflects the proximal characteristics of white matter fascicles distributed throughout the brain. Here we show how variability in the local connectome is correlated in a principled way across individuals. This inter-subject correlation is reliable enough that unique phenotype maps can be learned to predict between-subject variability in a range of social, health, and cognitive attributes. This work shows, for the first time, how shared variability across individuals is reflected in the local connectome.

neuroscience↗

bioRxiv2016

Tractography-based connectomes are dominated by false-positive connections

Fiber tractography based on non-invasive diffusion imaging is at the heart of connectivity studies of the human brain. To date, the approach has not been systematically validated in ground truth studies. Based on a simulated human brain dataset with ground truth white matter tracts, we organized an open international tractography challenge, which resulted in 96 distinct submissions from 20 research groups. While most state-of-the-art algorithms reconstructed 90% of ground truth bundles to at least some extent, on average they produced four times more invalid than valid bundles. About half of the invalid bundles occurred systematically in the majority of submissions. Our results demonstrate fundamental ambiguities inherent to tract reconstruction methods based on diffusion orientation information, with critical consequences for the approach of diffusion tractography in particular and human connectivity studies in general.

neuroscience↗