Matching Items (14)
Filtering by
- All Subjects: Bioinformatics
- Creators: Li, Baoxin
- Creators: Wilson Sayres, Melissa
Description
Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud.
ContributorsIslam, Gazi (Author) / Li, Baoxin (Thesis advisor) / Liang, Jianming (Thesis advisor) / Dinu, Valentin (Committee member) / Greenes, Robert (Committee member) / Smith, Marshall (Committee member) / Kahol, Kanav (Committee member) / Patel, Vimla L. (Committee member) / Arizona State University (Publisher)
Created2013
Description
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2014
Description
In many classication problems data samples cannot be collected easily, example in drug trials, biological experiments and study on cancer patients. In many situations the data set size is small and there are many outliers. When classifying such data, example cancer vs normal patients the consequences of mis-classication are probably more important than any other data type, because the data point could be a cancer patient or the classication decision could help determine what gene might be over expressed and perhaps a cause of cancer. These mis-classications are typically higher in the presence of outlier data points. The aim of this thesis is to develop a maximum margin classier that is suited to address the lack of robustness of discriminant based classiers (like the Support Vector Machine (SVM)) to noise and outliers. The underlying notion is to adopt and develop a natural loss function that is more robust to outliers and more representative of the true loss function of the data. It is demonstrated experimentally that SVM's are indeed susceptible to outliers and that the new classier developed, here coined as Robust-SVM (RSVM), is superior to all studied classier on the synthetic datasets. It is superior to the SVM in both the synthetic and experimental data from biomedical studies and is competent to a classier derived on similar lines when real life data examples are considered.
ContributorsGupta, Sidharth (Author) / Kim, Seungchan (Thesis advisor) / Welfert, Bruno (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2011
Description
Mammary gland development in humans during puberty involves the enlargement of breast tissue, but this is not true in non-human primates. To identify potential causes of this difference, I examined variation in substitution rates across genes related to mammary development. Genes undergoing purifying selection show slower-than-average substitution rates, while genes undergoing positive selection show faster rates. These may be related to the difference between humans and other primates. Three genes were found to be accelerated were FOXF1, IGFBP5, and ATP2B2, but only the latter one was found in humans and it seems unlikely that it would be related to the differences between mammary gland development at puberty between humans and non-human primates.
ContributorsArroyo, Diana (Author) / Cartwright, Reed (Thesis director) / Wilson Sayres, Melissa (Committee member) / Schwartz, Rachel (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
This creative thesis project aimed to create career development resources that School of Life Sciences majors could use to enhance their college experience, expand the breadth of relevant career options for School of Life Sciences majors, and confront and divert career problems through the implementation of these career development resources. Students encounter career problems when their intention and action diverge. These career problems may cause a student to stop their pursuit of a given career, change majors, or even stop schooling completely. It is the objective of this project to help resolve these career problems by introducing a career development resource flyer that educates the student about a given career, provides coursework to guide a student towards this career path, familiarize students with extracurricular efforts necessary for this position, propose valuable resources that the student can utilize to learn more about the career, and offer a question and answer portion for further career and professional understanding. In order to create these career development resource flyers a variety of professionals, both with and without relationships with Arizona State University were contacted and interviewed. The answers gathered from these interviews were then utilized to create the career flyers. The project was successful in creating five distinct career development resource flyers, as well as a blank template with instructions to be used in the future by the School of Life Sciences. The career development resource flyers will be utilized by the School of Life Sciences advising staff for future exploratory majors, but is not limited to just these students. Aspirations are set to create an expansive reservoir of these resources for future generations of students to access in hopes that they will be better suited to find a career path that they are passionate about and be better prepared to attain.
ContributorsGallegos, Darius Sloan (Author) / Wilson Sayres, Melissa (Thesis director) / Downing, Virginia (Committee member) / DeNardo, Dale (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
With the rising data output and falling costs of Next Generation Sequencing technologies, research into data compression is crucial to maintaining storage efficiency and costs. High throughput sequencers such as the HiSeqX Ten can produce up to 1.8 terabases of data per run, and such large storage demands are even more important to consider for institutions that rely on their own servers rather than large data centers (cloud storage)1. Compression algorithms aim to reduce the amount of space taken up by large genomic datasets by encoding the most frequently occurring symbols with the shortest bit codewords and by changing the order of the data to make it easier to encode. Depending on the probability distribution of the symbols in the dataset or the structure of the data, choosing the wrong algorithm could result in a compressed file larger than the original or a poorly compressed file that results in a waste of time and space2. To test efficiency among compression algorithms for each file type, 37 open-source compression algorithms were used to compress six types of genomic datasets (FASTA, VCF, BCF, GFF, GTF, and SAM) and evaluated on compression speed, decompression speed, compression ratio, and file size using the benchmark test lzbench. Compressors that outpreformed the popular bioinformatics compressor Gzip (zlib -6) were evaluated against one another by ratio and speed for each file type and across the geometric means of all file types. Compressors that exhibited fast compression and decompression speeds were also evaluated by transmission time through variable speed internet pipes in scenarios where the file was compressed only once or compressed multiple times.
ContributorsHowell, Abigail (Author) / Cartwright, Reed (Thesis director) / Wilson Sayres, Melissa (Committee member) / Taylor, Jay (Committee member) / Barrett, The Honors College (Contributor)
Created2017-05
Description
This project was designed to develop resources to highlight diverse career options for students achieving a degree within the School of Life Sciences. Many students have a very narrow view of what careers their degree prepares them for. In addition, if they have a career in mind, they have difficulty selecting an appropriate degree that will prepare them for their intended career. The goal of this project was to provide a broader view of career options, as well as illustrate the requirements each student would need to meet in order to pursue these careers. This was done by interviewing five career professionals and developing a major map that corresponds to the specific requirements of that career.
ContributorsBaber, Ariel Kate Elven (Author) / Wilson Sayres, Melissa (Thesis director) / DeNardo, Dale (Committee member) / Downing, Virginia (Committee member) / School of Life Sciences (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Lactase persistence is the ability of adults to digest lactose in milk (Segurel & Bon, 2017). Mammals are generally distinguished by their mammary glands which gives females the ability to produce milk and feed their newborn children. The new born therefore requires the ability to breakdown the lactose in the milk to ensure its proper digestion (Segurel & Bon, 2017). Generally, humans lose the expression of lactase after weaning, which prevents them being able to breakdown lactose from dairy (Flatz, 1987).
My research is focused on the people of Turkana, a human pastoral population inhabiting Northwest Kenya. The people of Turkana are Nilotic people that are native to the Turkana district. There are currently no conclusive studies done on evidence for genetic lactase persistence in Turkana. Therefore, my research will be on the evolution of lactase persistence in the people of Turkana. The goal of this project is to investigate the evolutionary history of two genes with known involvement in lactase persistence, LCT and MCM6, in the Turkana. Variants in these genes have previously been identified to result in the ability to digest lactose post-weaning age. Furthermore, an additional study found that a closely related population to the Turkana, the Massai, showed stronger signals of recent selection for lactase persistence than Europeans in these genes. My goal is to characterize known variants associated with lactase persistence by calculating their allele frequencies in the Turkana and conduct selection scans to determine if LCT/MCM6 show signatures of positive selection. In doing this, we conducted a pilot study consisting of 10 female Turkana individuals and 10 females from four different populations from the 1000 genomes project namely: the Yoruba in Ibadan, Nigeria (YRI); Luhya in Webuye, Kenya; Utah Residents with Northern and Western European Ancestry (CEU); and the Southern Han Chinese. The allele frequency calculation suggested that the CEU (Utah Residents with Northern and Western European Ancestry) population had a higher lactase persistence associated allele frequency than all the other populations analyzed here, including the Turkana population. Our Tajima’s D calculations and analysis suggested that both the Turkana population and the four haplotype map populations shows signatures of positive selection in the same region. The iHS selection scans we conducted to detect signatures of positive selection on all five populations showed that the Southern Han Chinese (CHS), the LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations had stronger signatures of positive selection than the Turkana population. The LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations showed the strongest signatures of positive selection in this region. This project serves as a first step in the investigation of lactase persistence in the Turkana population and its evolution over time.
My research is focused on the people of Turkana, a human pastoral population inhabiting Northwest Kenya. The people of Turkana are Nilotic people that are native to the Turkana district. There are currently no conclusive studies done on evidence for genetic lactase persistence in Turkana. Therefore, my research will be on the evolution of lactase persistence in the people of Turkana. The goal of this project is to investigate the evolutionary history of two genes with known involvement in lactase persistence, LCT and MCM6, in the Turkana. Variants in these genes have previously been identified to result in the ability to digest lactose post-weaning age. Furthermore, an additional study found that a closely related population to the Turkana, the Massai, showed stronger signals of recent selection for lactase persistence than Europeans in these genes. My goal is to characterize known variants associated with lactase persistence by calculating their allele frequencies in the Turkana and conduct selection scans to determine if LCT/MCM6 show signatures of positive selection. In doing this, we conducted a pilot study consisting of 10 female Turkana individuals and 10 females from four different populations from the 1000 genomes project namely: the Yoruba in Ibadan, Nigeria (YRI); Luhya in Webuye, Kenya; Utah Residents with Northern and Western European Ancestry (CEU); and the Southern Han Chinese. The allele frequency calculation suggested that the CEU (Utah Residents with Northern and Western European Ancestry) population had a higher lactase persistence associated allele frequency than all the other populations analyzed here, including the Turkana population. Our Tajima’s D calculations and analysis suggested that both the Turkana population and the four haplotype map populations shows signatures of positive selection in the same region. The iHS selection scans we conducted to detect signatures of positive selection on all five populations showed that the Southern Han Chinese (CHS), the LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations had stronger signatures of positive selection than the Turkana population. The LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations showed the strongest signatures of positive selection in this region. This project serves as a first step in the investigation of lactase persistence in the Turkana population and its evolution over time.
ContributorsJobe, Ndey Bassin (Author) / Wilson Sayres, Melissa (Thesis director) / Paaijmans, Krijn (Committee member) / Taravella, Angela (Committee member) / School of Earth and Space Exploration (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Unlike the autosomes, recombination on the sex chromosomes is limited to the pseudoautosomal regions (PARs) at each end of the chromosome. PAR1 spans approximately 2.7 Mb from the tip of the proximal arm of each sex chromosome, and a pseudoautosomal boundary between the PAR1 and non-PAR region is thought to have evolved from a Y-specific inversion that suppressed recombination across the boundary. In addition to the two PARs, there is also a human-specific X-transposed region (XTR) that was duplicated from the X to the Y chromosome. Genetic diversity is expected to be higher in recombining than nonrecombining regions, particularly because recombination reduces the effects of linked selection, allowing neutral variation to accumulate. We previously showed that diversity decreases linearly across the previously defined pseudoautosomal boundary (rather than drop suddenly at the boundary), suggesting that the pseudoautosomal boundary may not be as strict as previously thought. In this study, we analyzed data from 1271 genetic females to explore the extent to which the pseudoautosomal boundary varies among human populations (broadly, African, European, South Asian, East Asian, and the Americas). We found that, in all populations, genetic diversity was significantly higher in the PAR1 and XTR than in the non-PAR regions, and that diversity decreased linearly from the PAR1 to finally reach a non-PAR value well past the pseudoautosomal boundary in all populations. However, we also found that the location at which diversity changes from reflecting the higher PAR1 diversity to the lower nonPAR diversity varied by as much as 500 kb among populations. The lack of genetic evidence for a strict pseudoautosomal boundary and the variability in patterns of diversity across the pseudoautosomal boundary are consistent with two potential explanations: (1) the boundary itself may vary across populations, or (2) that population-specific demographic histories have shaped diversity across the pseudoautosomal boundary.
ContributorsCotter, Daniel Juetten (Author) / Wilson Sayres, Melissa (Thesis director) / Stone, Anne (Committee member) / Webster, Timothy (Committee member) / School of Life Sciences (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three enddiastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system significantly outperforms the state-of-the-art methods. The superior performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.
ContributorsShin, Jaeyul (Author) / Liang, Jianming (Thesis advisor) / Maciejewski, Ross (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2016