195 research outputs found
Lung cancer malignancy predication with recurrent neural networks
No full textLung cancer has the highest mortality rate among all cancer types in the United States, comprising almost 25% of all cancer deaths. Existing work in computer-aided diagnosis (CAD) has applied convolutional neural networks (CNNs) to detect and classify nodules in CT scans, with the goal of assisting radiologists diagnose lung cancer. In the past decade, new screening pro- tocols have been enacted that advise high-risk patients to get annual CT screenings to monitor any suspicious lesions found in the lungs. This change increases the availability of CT scans and the number of scans per patient for computational models to learn from. In this thesis, we present bounding box annotations for a subset of patients from the National Lung Screening Trial (NLST) over three years time and provide baseline results on the benchmark task of malignancy prediction using this time-series data. We analyze the use of longitudinal models to capture the progression of nodule malignancy and see that recurrent neural networks (RNNs) outperform standard CNNs by 4.58% in accuracy, 5.03% in precision for a fixed sensitivity of 95.06%, and 6.61% in area under the curve (AUC).Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-08-01The student, Mary Dasso, accepted the attached license on 2021-07-21 at 11:52.The student, Mary Dasso, submitted this Thesis for approval on 2021-07-21 at 11:57.This Thesis was approved for publication on 2021-07-21 at 14:25.DSpace SAF Submission Ingestion Package generated from Vireo submission #17051 on 2022-01-12 at 12:55:35Made available in DSpace on 2022-01-12T22:35:21Z (GMT). No. of bitstreams: 2
DASSO-THESIS-2021.pdf: 2134304 bytes, checksum: 8ab24b85418e13f2ca95ee3523487f57 (MD5)
LICENSE.txt: 4207 bytes, checksum: a390b4b7688a732b73d2f44432f45077 (MD5)
Previous issue date: 2021-07-21Embargo set by: Seth Robbins for item 121150
Lift date: 2024-01-12T22:35:30Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemAuthor requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemU of I Onl
Síndrome burnout y su incidencia en el clima institucional de los docentes de la institución educativa N° 40324 José Miguel Morales Dasso, distrito de Orcopampa, provincia de Castilla, Arequipa, 2018
No full textEl presente trabajo de investigación tiene como objetivo, determinar la correlación entre el síndrome Burnout y el clima institucional de los docentes de la institución educativa N° 40324 José Miguel Morales Dasso, distrito de Orcopampa, provincia de Castilla, Arequipa, 2018. De esta manera, mediante la metodología científica, nivel de investigación relacional, diseño de investigación correlacional - causal, haciendo uso de los instrumentos escala de Likert “Maslach” para la variable síndrome burnout y “Clima Institucional” para la variable del mismo nombre, usando como proceso de recolección de datos la encuesta, estos se aplicaron a una muestra conformada por treinta y uno docentes de la institución educativa N° 40324 José Miguel Morales Dasso. Una vez aplicados los instrumentos se evidencia, para la variable síndrome burnout, lo siguiente, en la dimensión cansancio emocional, el 3,23% de docentes se encuentra en el nivel alto, el 12,90% en el nivel medio y el 83,87% en el nivel bajo; en la dimensión despersonalización, el 9,68% se encuentra en el nivel medio y el 90,32% en el nivel bajo y en la dimensión realización profesional, el 12,90% se encuentra en el nivel medio y el 87,10% en el nivel bajo; y para la variable clima institucional el 70,97% considera que hay un alto nivel de clima institucional, el 22,58% un nivel medio y el 6,45% considera que hay un nivel bajo. Finalmente, mediante la prueba de coeficiente de correlación de Spearman con un nivel bajo o ligero, de esta misma, se asume que existe correlación entre el síndrome Burnout y el clima institucional.Tesi
The Ran GTPase: Theme and Variations
No full textAbstractThe small GTPase Ran has roles in multiple cellular processes, including nuclear transport, mitotic spindle assembly, the regulation of cell cycle progression and nuclear assembly. The past year has seen a remarkable unification of these different roles with respect to the effectors and mechanisms through which they function. Our emergent understanding of Ran suggests that it plays a central role in spatial and temporal organization of the vertebrate cell
Shedding Light on Mysterious Microtubules
No full textWe have known for decades that vertebrate kinetochores can nucleate microtubules. However, the role of such microtubules was unclear. Kitamura et al. investigated this issue by following a marked budding yeast centromere after its conditional reactivation to examine microtubule capture at unattached kinetochores. They found not only that yeast kinetochores can nucleate microtubules, but also that such microtubules facilitate attachment by decreasing the time required for spindle-pole-associated microtubules to make contact with unattached kinetochores. Historically, the fact that microtubules nucleated at kinetochores are opposite in polarity to those in mature spindle fibers was used to argue that they were not physiologically relevant for spindle assembly. Kitamura et al. have now shown that they, in fact, do play a role, and then rapidly depolymerize after spindle fiber attachments form. In sum, this paper provides a function for a previously mysterious microtubule population and outlines a surprising and dynamic mechanism through which kinetochore-originated microtubules assist spindle pole microtubules to efficiently “locate” unattached kinetochores. It also shows how this assistance mechanism is shut off to dim the “locator beacon” after correct attachments have been made.Understanding Kinetochore-Nucleated MicrotubulesTomoyuki Tanaka, with the help of Etsushi Kitamura and Shinya Komoto, explains his group's key findings regarding the roles of kinetochore-generated microtubules in mitosis
Emerging roles of the SUMO pathway in mitosis
No full textAbstract SUMO proteins are small ubiquitin-like modifiers found in all eukaryotes that become covalently conjugated to other cellular proteins. The SUMO conjugation pathway is biochemically similar to ubiquitin conjugation, although the enzymes within the pathway act exclusively on SUMO proteins. This post-translational modification controls many processes. Here, I will focus on evidence that SUMOylation plays a critical role(s) in mitosis: Early studies showed a genetic requirement for SUMO pathway components in the process of cell division, while later findings implicated SUMOylation in the control of mitotic chromosome structure, cell cycle progression, kinetochore function and cytokinesis. Recent insights into the targets of SUMOylation are likely to be extremely helpful in understanding each of these aspects. Finally, growing evidence suggests that SUMOylation is a downstream target of regulation through Ran, a small GTPase with important functions in both interphase nuclear trafficking and mitotic spindle assembly.</p
Catch and release: 14-3-3 controls Ncd in meiotic spindles
No full textDuring Drosophila melanogaster oogenesis, spindle assembly occurs without centrosomes and relies on signals from chromosomes. Beaven et al. (2017. J. Cell. Biol. https://doi.org/10.1083/jcb.201704120) show that 14-3-3 proteins bind and inhibit a key microtubule motor, Ncd, during oogenesis, but Aurora B releases Ncd inhibition near chromosomes, allowing Ncd to work in the right time and place.</jats:p
- …
