Search

Your search keyword '"Arenas, Gabriel"' showing total 34 results
Start Over Author "Arenas, Gabriel"
34 results on '"Arenas, Gabriel"'

1. PRISM Lite: A lightweight model for interactive 3D placenta segmentation in ultrasound

Author

Li, Hao, Oguz, Baris, Arenas, Gabriel, Yao, Xing, Wang, Jiacheng, Pouch, Alison, Byram, Brett, Schwartz, Nadav, and Oguz, Ipek

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Placenta volume measured from 3D ultrasound (3DUS) images is an important tool for tracking the growth trajectory and is associated with pregnancy outcomes. Manual segmentation is the gold standard, but it is time-consuming and subjective. Although fully automated deep learning algorithms perform well, they do not always yield high-quality results for each case. Interactive segmentation models could address this issue. However, there is limited work on interactive segmentation models for the placenta. Despite their segmentation accuracy, these methods may not be feasible for clinical use as they require relatively large computational power which may be especially prohibitive in low-resource environments, or on mobile devices. In this paper, we propose a lightweight interactive segmentation model aiming for clinical use to interactively segment the placenta from 3DUS images in real-time. The proposed model adopts the segmentation from our fully automated model for initialization and is designed in a human-in-the-loop manner to achieve iterative improvements. The Dice score and normalized surface Dice are used as evaluation metrics. The results show that our model can achieve superior performance in segmentation compared to state-of-the-art models while using significantly fewer parameters. Additionally, the proposed model is much faster for inference and robust to poor initial masks. The code is available at https://github.com/MedICL-VU/PRISM-placenta.

Published
2024

2. Interactive Segmentation Model for Placenta Segmentation from 3D Ultrasound images

Author

Li, Hao, Oguz, Baris, Arenas, Gabriel, Yao, Xing, Wang, Jiacheng, Pouch, Alison, Byram, Brett, Schwartz, Nadav, and Oguz, Ipek

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Placenta volume measurement from 3D ultrasound images is critical for predicting pregnancy outcomes, and manual annotation is the gold standard. However, such manual annotation is expensive and time-consuming. Automated segmentation algorithms can often successfully segment the placenta, but these methods may not consistently produce robust segmentations suitable for practical use. Recently, inspired by the Segment Anything Model (SAM), deep learning-based interactive segmentation models have been widely applied in the medical imaging domain. These models produce a segmentation from visual prompts provided to indicate the target region, which may offer a feasible solution for practical use. However, none of these models are specifically designed for interactively segmenting 3D ultrasound images, which remain challenging due to the inherent noise of this modality. In this paper, we evaluate publicly available state-of-the-art 3D interactive segmentation models in contrast to a human-in-the-loop approach for the placenta segmentation task. The Dice score, normalized surface Dice, averaged symmetric surface distance, and 95-percent Hausdorff distance are used as evaluation metrics. We consider a Dice score of 0.95 a successful segmentation. Our results indicate that the human-in-the-loop segmentation model reaches this standard. Moreover, we assess the efficiency of the human-in-the-loop model as a function of the amount of prompts. Our results demonstrate that the human-in-the-loop model is both effective and efficient for interactive placenta segmentation. The code is available at \url{https://github.com/MedICL-VU/PRISM-placenta}.

Published
2024

4. Interactive Segmentation Model for Placenta Segmentation from 3D Ultrasound Images

Author

Li, Hao, Oguz, Baris, Arenas, Gabriel, Yao, Xing, Wang, Jiacheng, Pouch, Alison, Byram, Brett, Schwartz, Nadav, Oguz, Ipek, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Gomez, Alberto, editor, Khanal, Bishesh, editor, King, Andrew, editor, and Namburete, Ana, editor

Published
2025
Full Text
View/download PDF

5. False Negative/Positive Control for SAM on Noisy Medical Images

Author

Yao, Xing, Liu, Han, Hu, Dewei, Lu, Daiwei, Lou, Ange, Li, Hao, Deng, Ruining, Arenas, Gabriel, Oguz, Baris, Schwartz, Nadav, Byram, Brett C, and Oguz, Ipek

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

The Segment Anything Model (SAM) is a recently developed all-range foundation model for image segmentation. It can use sparse manual prompts such as bounding boxes to generate pixel-level segmentation in natural images but struggles in medical images such as low-contrast, noisy ultrasound images. We propose a refined test-phase prompt augmentation technique designed to improve SAM's performance in medical image segmentation. The method couples multi-box prompt augmentation and an aleatoric uncertainty-based false-negative (FN) and false-positive (FP) correction (FNPC) strategy. We evaluate the method on two ultrasound datasets and show improvement in SAM's performance and robustness to inaccurate prompts, without the necessity for further training or tuning. Moreover, we present the Single-Slice-to-Volume (SS2V) method, enabling 3D pixel-level segmentation using only the bounding box annotation from a single 2D slice. Our results allow efficient use of SAM in even noisy, low-contrast medical images. The source code will be released soon.

Published
2023

10. Open-source graphical user interface for the creation of synthetic skeletons for medical image analysis

Author

Herz, Christian, primary, Vergnet, Nicolas, additional, Tian, Sijie, additional, Aly, Abdullah H., additional, Jolley, Matthew A., additional, Tran, Nathanael, additional, Arenas, Gabriel, additional, Lasso, Andras, additional, Schwartz, Nadav, additional, O’Neill, Kathleen E., additional, Yushkevich, Paul A., additional, and Pouch, Alison M., additional

Published
2024
Full Text
View/download PDF

15. Sedación profunda en endoscopia digestiva superior terapéutica en niños

Author

Mosquera, Nazareth, primary, Colina, Nina, additional, Caraballo, L, additional, Marcano, Ana Sofia, additional, Piermattei, Giormar, additional, Rodriguez, Ana, additional, Arenas, Gabriel, additional, Gonzalez, Palmira, additional, Fajardo, Dayana, additional, Duran, Osmary, additional, Barreto, Arianna, additional, Dimas, Isabel, additional, Ruiz, Maygreg, additional, and Rodríguez, Miroslaba, additional

Published
2023
Full Text
View/download PDF

18. Estricturotomía como alternativa terapéutica en niños con estenosis esofágica refractaria

Author

Marcano, Ana, primary, Colina, Nina, additional, Di Giorgio, José, additional, Mosquera, Nazareth, additional, González, Palmira, additional, Piermattei, G, additional, Rodríguez, Ana, additional, Arenas, Gabriel, additional, Fajardo, Dayana, additional, Durán, Osmary, additional, Barreto, Arianna, additional, Dimas, Isabel, additional, Ruiz, Maygreg, additional, and Rodríguez, Miroslava, additional

Published
2023
Full Text
View/download PDF

20. Speaker Identification in Interactions between Mothers and Children with Down Syndrome via Audio Analysis: A Case Study in Mexico.

Author

Flores-Carballo, Carlos R., Molina-Arenas, Gabriel A., Macias, Adrian, Caro, Karina, Beltran, Jessica, and Castro, Luis A.

Subjects
*MOTHER-child relationship, *DOWN syndrome, *SYNDROMES in children, *MACHINE learning, *SPEECH, *AUTOMATIC speech recognition
Abstract

In this work, we aim at identifying the speaker in interactions between mothers and children with Down syndrome (DS) using audio. We collected audio from a session in which children with DS solved puzzles, and their mothers were by their side. We generated a dataset by manually annotating human speech activity and non-speech. We used machine learning to perform four experiments, including individual and generalized models achieving on average F1-scores of 0.74 (five-class model) and 0.84 (two-class) for individual models and 0.69 (five-class) and 0.82 (two-class) for the generalized models. Our results can be helpful to behavioral researchers, therapists, and those interested in better understanding how mother–child interactions unfold in naturalistic settings. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

27. Calidad en las empresas en el sector de bebidas alcohólicas en la región Lima

Author

Breña Barnett, Walter, Espinoza Trinidad, Lilian, Ly Alfaro, Javier, Montoya Bravo Arenas, Gabriel, and Afcha Chávez, Sergio Moisés

Subjects
Investigación cuantitativa, Calidad total, Bebidas alcohólicas--Industria y comercio--Perú--Lima, purl.org/pe-repo/ocde/ford#5.02.04 [https]
Abstract

En la presente investigación se efectúo una comparación entre los niveles de cumplimiento percibidos por los altos funcionarios de las empresas del sector de bebidas alcohólicas en la región Lima del Perú que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto a los nueve factores de éxito de la calidad (TQM por sus siglas en inglés): Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Gestión de la Calidad del Proveedor, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. Para este propósito se aplicó una encuesta basada en el instrumento TQM desarrollado por Benzaquen (2013) que consta de 35 preguntas sobre la implementación de prácticas del TQM, las cuales son agrupadas en cada uno de los nueve factores señalados anteriormente. La naturaleza de la investigación tuvo un enfoque cuantitativo, un alcance descriptivo y explicativo. El diseño de la investigación fue no experimental y transeccional. Los resultados obtenidos confirmaron la hipótesis de investigación planteada, es decir, se encontraron diferencias significativas en el nivel de cumplimiento percibido respecto de los factores de calidad en las empresas del sector de bebidas alcohólicas en la región Lima que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto de los siguientes ocho factores: Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. El único factor en donde no se encontró una diferencia significativa fue el relacionado con la Gestión de la Calidad del Proveedor. In the present investigation, a comparison between compliance levels perceived by senior officials of companies in the sector of alcoholic beverages from Lima Region in Peru with a quality management system (ISO 9001) and those without it have been made. This comparison was made with respect of the nine success factors of quality (TQM for its acronym in English): Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Supplier Quality Management, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Customer Satisfaction. For the purpose a survey based on an instrument developed by Benzaquen (2013) TQM including 35 questions about the implementation of TQM practices grouped in each of the nine factors listed above was applied. The nature of the study had a quantitative approach, a descriptive and explanatory scope. It has a nonexperimental and transactional design research. The results confirmed the hypothesis proposed in the investigation, ie, significant differences in the level of compliance perceived of quality factors in companies of alcoholic beverages sectors from Lima Region with a quality management system (ISO 9001) and those without it, in respect of the following eight factors: Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Satisfaction customer. The only factor where a significant difference wasn’t found was related to the Supplier Quality Management. Tesis

Published
2015

28. Ultrasound Shear Wave Velocity Varies Across Anatomical Region in Ex VivoBovine Ovaries

Author

Gargus, Emma S., Jakubowski, Kristen L., Arenas, Gabriel A., Miller, Scott J., Lee, Sabrina S. M., and Woodruff, Teresa K.

Abstract

The physical properties of the ovarian extracellular matrix (ECM) regulate the function of ovarian cells, specifically the ability of the ovary to maintain a quiescent primordial follicle pool while allowing a subset of follicles to grow and mature in the estrous cycle. Design of a long-term, cycling artificial ovary has been hindered by the limited information regarding the mechanical properties of the ovary. In particular, differences in the mechanical properties of the two ovarian compartments, the cortex and medulla, have never been quantified. Shear wave (SW) ultrasound elastography is an imaging modality that enables assessment of material properties, such as the mechanical properties, based on the velocity of SWs, and visualization of internal anatomy, when coupled with B-mode ultrasound. We used SW ultrasound elastography to assess whole, ex vivobovine ovaries. We demonstrated, for the first time, a difference in mechanical properties, as inferred from SW velocity, between the cortex and medulla, as measured along the length (cortex: 2.57 ± 0.53 m/s, medulla: 2.87 ± 0.77 m/s, p< 0.0001) and width (cortex: 2.99 ± 0.81 m/s, medulla: 3.24 ± 0.97 m/s, p< 0.05) and that the spatial distribution and magnitude of SW velocity vary between these two anatomical planes. This work contributes to a larger body of literature assessing the mechanical properties of the ovary and related cells and specialized ECMs and will enable the rational design of biomimetic tissue engineered models and durable bioprostheses.Impact StatementShear wave (SW) ultrasound elastography can be used to simultaneously assess the material properties and tissue structures when accompanied with B-mode ultrasound. We report a quantitative difference in mechanical properties, as inferred from SW velocity, between the cortex and medulla, with SW velocity being 11.4% and 8.4% higher in the medulla than the cortex when measured along the length and width, respectively. This investigation into the spatial and temporal variation in SW velocity in bovine ovaries will encourage and improve design of more biomimetic scaffolds for ovarian tissue engineering.

Published
2020
Full Text
View/download PDF

32. Calidad en las empresas en el sector de bebidas alcohólicas en la región Lima

Author

Breña Barnett, Walter, Espinoza Trinidad, Lilian, Ly Alfaro, Javier, Montoya Bravo Arenas, Gabriel, Breña Barnett, Walter, Espinoza Trinidad, Lilian, Ly Alfaro, Javier, and Montoya Bravo Arenas, Gabriel

Abstract

En la presente investigación se efectúo una comparación entre los niveles de cumplimiento percibidos por los altos funcionarios de las empresas del sector de bebidas alcohólicas en la región Lima del Perú que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto a los nueve factores de éxito de la calidad (TQM por sus siglas en inglés): Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Gestión de la Calidad del Proveedor, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. Para este propósito se aplicó una encuesta basada en el instrumento TQM desarrollado por Benzaquen (2013) que consta de 35 preguntas sobre la implementación de prácticas del TQM, las cuales son agrupadas en cada uno de los nueve factores señalados anteriormente. La naturaleza de la investigación tuvo un enfoque cuantitativo, un alcance descriptivo y explicativo. El diseño de la investigación fue no experimental y transeccional. Los resultados obtenidos confirmaron la hipótesis de investigación planteada, es decir, se encontraron diferencias significativas en el nivel de cumplimiento percibido respecto de los factores de calidad en las empresas del sector de bebidas alcohólicas en la región Lima que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto de los siguientes ocho factores: Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. El único factor en donde no se encontró una diferencia significativa fue el relacionado con la Gestión de la Calidad del Proveedor., In the present investigation, a comparison between compliance levels perceived by senior officials of companies in the sector of alcoholic beverages from Lima Region in Peru with a quality management system (ISO 9001) and those without it have been made. This comparison was made with respect of the nine success factors of quality (TQM for its acronym in English): Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Supplier Quality Management, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Customer Satisfaction. For the purpose a survey based on an instrument developed by Benzaquen (2013) TQM including 35 questions about the implementation of TQM practices grouped in each of the nine factors listed above was applied. The nature of the study had a quantitative approach, a descriptive and explanatory scope. It has a nonexperimental and transactional design research. The results confirmed the hypothesis proposed in the investigation, ie, significant differences in the level of compliance perceived of quality factors in companies of alcoholic beverages sectors from Lima Region with a quality management system (ISO 9001) and those without it, in respect of the following eight factors: Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Satisfaction customer. The only factor where a significant difference wasn’t found was related to the Supplier Quality Management., Tesis

33. Calidad en las empresas en el sector de bebidas alcohólicas en la región Lima

Author

Breña Barnett, Walter, Espinoza Trinidad, Lilian, Ly Alfaro, Javier, Montoya Bravo Arenas, Gabriel, Breña Barnett, Walter, Espinoza Trinidad, Lilian, Ly Alfaro, Javier, and Montoya Bravo Arenas, Gabriel

Abstract

En la presente investigación se efectúo una comparación entre los niveles de cumplimiento percibidos por los altos funcionarios de las empresas del sector de bebidas alcohólicas en la región Lima del Perú que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto a los nueve factores de éxito de la calidad (TQM por sus siglas en inglés): Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Gestión de la Calidad del Proveedor, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. Para este propósito se aplicó una encuesta basada en el instrumento TQM desarrollado por Benzaquen (2013) que consta de 35 preguntas sobre la implementación de prácticas del TQM, las cuales son agrupadas en cada uno de los nueve factores señalados anteriormente. La naturaleza de la investigación tuvo un enfoque cuantitativo, un alcance descriptivo y explicativo. El diseño de la investigación fue no experimental y transeccional. Los resultados obtenidos confirmaron la hipótesis de investigación planteada, es decir, se encontraron diferencias significativas en el nivel de cumplimiento percibido respecto de los factores de calidad en las empresas del sector de bebidas alcohólicas en la región Lima que poseen un sistema de gestión de la calidad (ISO 9001) y las que no, respecto de los siguientes ocho factores: Alta Gerencia, Planeamiento de la Calidad, Auditoría y Evaluación de la Calidad, Diseño del Producto, Control y Mejoramiento del Proceso, Entrenamiento y Educación, Círculos de Calidad y Enfoque hacia la Satisfacción del Cliente. El único factor en donde no se encontró una diferencia significativa fue el relacionado con la Gestión de la Calidad del Proveedor., In the present investigation, a comparison between compliance levels perceived by senior officials of companies in the sector of alcoholic beverages from Lima Region in Peru with a quality management system (ISO 9001) and those without it have been made. This comparison was made with respect of the nine success factors of quality (TQM for its acronym in English): Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Supplier Quality Management, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Customer Satisfaction. For the purpose a survey based on an instrument developed by Benzaquen (2013) TQM including 35 questions about the implementation of TQM practices grouped in each of the nine factors listed above was applied. The nature of the study had a quantitative approach, a descriptive and explanatory scope. It has a nonexperimental and transactional design research. The results confirmed the hypothesis proposed in the investigation, ie, significant differences in the level of compliance perceived of quality factors in companies of alcoholic beverages sectors from Lima Region with a quality management system (ISO 9001) and those without it, in respect of the following eight factors: Senior Management, Quality Planning, Audit and Quality Assessment, Product Design, Quality Control and Process Improvement, Training and Education, Quality Circles and Approach to Satisfaction customer. The only factor where a significant difference wasn’t found was related to the Supplier Quality Management.

34. FNPC-SAM: Uncertainty-Guided False Negative/Positive Control for SAM on Noisy Medical Images.

Author

Yao X, Liu H, Hu D, Lu D, Lou A, Li H, Deng R, Arenas G, Oguz B, Schwartz N, Byram BC, and Oguz I

Abstract

The Segment Anything Model (SAM) is a recently developed all-range foundation model for image segmentation. It can use sparse manual prompts such as bounding boxes to generate pixel-level segmentation in natural images but struggles in medical images such as low-contrast, noisy ultrasound images. We propose a refined test-phase prompt augmentation technique designed to improve SAM's performance in medical image segmentation. The method couples multi-box prompt augmentation and an aleatoric uncertainty-based false-negative (FN) and false-positive (FP) correction (FNPC) strategy. We evaluate the method on two ultrasound datasets and show improvement in SAM's performance and robustness to inaccurate prompts, without the necessity for further training or tuning. Moreover, we present the Single-Slice-to-Volume (SS2V) method, enabling 3D pixel-level segmentation using only the bounding box annotation from a single 2D slice. Our results allow efficient use of SAM in even noisy, low-contrast medical images. The source code has been released at: https://github.com/MedICL-VU/FNPC-SAM.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results