Saul Langarica
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saul Langarica has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Felipe Núñez
Department of Electrical Engineering, Pontificia Universidad Catlica de Chile, Santiago, Chile
5 shared publications - Synho Do
Department of Radiology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street and 125 Nashua Street, Boston, MA, 02114, USA.
5 shared publications Young-Tak Kim
Lab of Medical Imaging and Computation, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
3 shared publicationsAdham Alkhadrawi
Department of Radiology, Massachusetts General Hospital and Harvard Medical School , 125 Nashua Street, Boston, MA 02114
2 shared publications- Adham M. Alkhadrawi
Department of Molecular Biosciences and Bioengineering, University of Hawaii at Manoa, Honolulu, USA
2 shared publications - Camilo Jaimes
Department of Radiology, Massachusetts General Hospital, Boston, United States
2 shared publications
Latest Publications
- Open Access
- 31 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101098
A Deep Learning Framework for Predicting Teprotumumab Treatment Response in Thyroid Eye Disease
- 31 January 2026
- Published by Elsevier in Ophthalmology Science
- Vol. 6 (4) , 101098
Open AccessA Deep Learning Framework for Predicting Teprotumumab Treatment Response in Thyroid Eye Disease
- Open Access
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Response to ‘Methodological and statistical concerns in MINERVA microbiome–disease knowledge graph’ by Salvatore Chirumbolo
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Open AccessResponse to ‘Methodological and statistical concerns in MINERVA microbiome–disease knowledge graph’ by Salvatore Chirumbolo
- Open Access
- 20 October 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (4) , 1-2
Correction: ARANet: Adaptive Resolution Attention Network for Precise MRI-Based Segmentation and Quantification of Fetal Size and Amniotic Fluid Volume
- 20 October 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (4) , 1-2
Open AccessCorrection: ARANet: Adaptive Resolution Attention Network for Precise MRI-Based Segmentation and Quantification of Fetal Size and Amniotic Fluid Volume
- Open Access
- 31 August 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (5)
MINERVA—microbiome network research and visualization atlas: a scalable knowledge graph for mapping microbiome-disease associations
Bacterial pathogens contribute significantly to the global burden of disease. Understanding their complex interactions with human health is essential for developing new diagnostic, preventative, and therapeutic strategies. While recent breakthroughs have revolutionized our understanding of these relationships, the rapid expansion of microbiome research presents a significant challenge: knowledge remains scattered across scientific literature, hindering comprehensive analysis and clinical translation. To address this, we introduce MINERVA (Microbiome Network Research and Visualization Atlas), an innovative platform that leverages a fine-tuned large language model to systematically map microbe-disease associations across extensive scientific literature. MINERVA constructs a rich, ontology-driven knowledge graph that prioritizes accuracy and transparency, enabling efficient exploration and discovery of previously hidden associations relevant to clinical decision-making. The platform features specialized modules that allow researchers to analyze individual microbes and diseases, visualize complex relationships within the knowledge network, uncover hidden connections through advanced graph algorithms and machine-learning models, and perform personalized and population-level microbiome compositional analysis. These capabilities facilitate the identification of disease risks, comorbidities, and actionable insights, supporting both research and clinical decision-making. By bridging the gap between microbiome research and real-world applications, MINERVA has the potential to transform our understanding of microbe-disease interactions, accelerating discoveries and advancing patient care. The MINERVA platform is available at https://minervabio.org/.
- 31 August 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (5)
Open AccessMINERVA—microbiome network research and visualization atlas: a scalable knowledge graph for mapping microbiome-disease associations
Bacterial pathogens contribute significantly to the global burden of disease. Understanding their complex interactions with human health is essential for developing new diagnostic, preventative, and therapeutic strategies. While recent breakthroughs have revolutionized our understanding of these relationships, the rapid expansion of microbiome research presents a significant challenge: knowledge remains scattered across scientific literature, hindering comprehensive analysis and clinical translation. To address this, we introduce MINERVA (Microbiome Network Research and Visualization Atlas), an innovative platform that leverages a fine-tuned large language model to systematically map microbe-disease associations across extensive scientific literature. MINERVA constructs a rich, ontology-driven knowledge graph that prioritizes accuracy and transparency, enabling efficient exploration and discovery of previously hidden associations relevant to clinical decision-making. The platform features specialized modules that allow researchers to analyze individual microbes and diseases, visualize complex relationships within the knowledge network, uncover hidden connections through advanced graph algorithms and machine-learning models, and perform personalized and population-level microbiome compositional analysis. These capabilities facilitate the identification of disease risks, comorbidities, and actionable insights, supporting both research and clinical decision-making. By bridging the gap between microbiome research and real-world applications, MINERVA has the potential to transform our understanding of microbe-disease interactions, accelerating discoveries and advancing patient care. The MINERVA platform is available at https://minervabio.org/.
- 1 July 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 316 (1) , e241050
AI to Reduce the Interval Cancer Rate of Screening Digital Breast Tomosynthesis
The use of a U.S. Food and Drug Administration–cleared artificial intelligence algorithm for lesion detection and diagnosis at screening digital breast tomosynthesis examinations could reduce interval cancers by nearly one-third.
- 1 July 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 316 (1) , e241050
AI to Reduce the Interval Cancer Rate of Screening Digital Breast Tomosynthesis
The use of a U.S. Food and Drug Administration–cleared artificial intelligence algorithm for lesion detection and diagnosis at screening digital breast tomosynthesis examinations could reduce interval cancers by nearly one-third.
- 25 June 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (2) , 1202-1216
ARANet: Adaptive Resolution Attention Network for Precise MRI-Based Segmentation and Quantification of Fetal Size and Amniotic Fluid Volume
Amniotic fluid volume (AFV) is a critical indicator of fetal health, traditionally assessed using ultrasound-based methods, which are limited by operator dependency and 2D measurements. While MRI offers superior tissue characterization, it remains underutilized for AFV assessment due to labor-intensive manual segmentations. Pulse sequence variations in MRI can significantly influence image contrast through T1 and T2 weighting and potentially cause signal dropout in certain regions, making automated analysis challenging. To address these challenges, we present ARANet (Adaptive Resolution Attention Network), featuring a novel adaptive resolution attention module that uniquely combines adaptive resolution processing with channel-wise attention mechanisms for precise MRI-based segmentation. In extensive evaluations, ARANet demonstrates superior performance with a Dice score of 0.961 at full brightness, maintaining robust performance (0.909) even at 30% brightness, significantly outperforming existing models in challenging low-contrast conditions. We introduce FAFO3D, a new metric integrating amniotic fluid overlap, fetal age, and volume, which achieves 100% accuracy in clinical AFV classification (normal, oligohydramnios, and polyhydramnios) when combined with a support vector classifier. A comprehensive web platform automates the workflow from DICOM processing to analysis, providing detailed reports and 3D visualizations for clinical implementation. This solution offers a novel, accurate, and clinically applicable approach for AFV assessment, though further validation in diverse clinical environments is recommended.
- 25 June 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (2) , 1202-1216
ARANet: Adaptive Resolution Attention Network for Precise MRI-Based Segmentation and Quantification of Fetal Size and Amniotic Fluid Volume
Amniotic fluid volume (AFV) is a critical indicator of fetal health, traditionally assessed using ultrasound-based methods, which are limited by operator dependency and 2D measurements. While MRI offers superior tissue characterization, it remains underutilized for AFV assessment due to labor-intensive manual segmentations. Pulse sequence variations in MRI can significantly influence image contrast through T1 and T2 weighting and potentially cause signal dropout in certain regions, making automated analysis challenging. To address these challenges, we present ARANet (Adaptive Resolution Attention Network), featuring a novel adaptive resolution attention module that uniquely combines adaptive resolution processing with channel-wise attention mechanisms for precise MRI-based segmentation. In extensive evaluations, ARANet demonstrates superior performance with a Dice score of 0.961 at full brightness, maintaining robust performance (0.909) even at 30% brightness, significantly outperforming existing models in challenging low-contrast conditions. We introduce FAFO3D, a new metric integrating amniotic fluid overlap, fetal age, and volume, which achieves 100% accuracy in clinical AFV classification (normal, oligohydramnios, and polyhydramnios) when combined with a support vector classifier. A comprehensive web platform automates the workflow from DICOM processing to analysis, providing detailed reports and 3D visualizations for clinical implementation. This solution offers a novel, accurate, and clinically applicable approach for AFV assessment, though further validation in diverse clinical environments is recommended.
- Open Access
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 5, 467-475
Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management
Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 5, 467-475
Open AccessDeep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management
Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (10) , 5054-5065
A Probabilistic Approach to Blood Glucose Prediction in Type 1 Diabetes Under Meal Uncertainties
Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (10) , 5054-5065
A Probabilistic Approach to Blood Glucose Prediction in Type 1 Diabetes Under Meal Uncertainties
Currently, most reliable and commercialized artificial pancreas systems for type 1 diabetes are hybrid closed-loop systems, which require the user to announce every meal and its size. However, estimating the amount of carbohydrates in a meal and announcing each and every meal is an error-prone process that introduces important uncertainties to the problem, which when not considered, lead to sub-optimal outcomes of the controller. To address this problem, we propose a novel deep-learning-based model for probabilistic glucose prediction, called the Input and State Recurrent Kalman Network (ISRKN), which consists in the incorporation of an input and state Kalman filter in the latent space of a deep neural network so that the posterior distributions can be computed in closed form and the uncertainty can be propagated using the Kalman equations. In addition, the proposed architecture allows explicit estimation of the meal uncertainty distribution, whose parameters are encoded in the filter parameters. Results using the UVA/Padova simulator and data from a clinical trial show that the proposed model outperforms other probabilistic models using several probabilistic metrics across different degrees of distributional shifts.
- Open Access
- 23 March 2023
- Published by Elsevier in Control Engineering Practice
- Vol. 135
A meta-learning approach to personalized blood glucose prediction in type 1 diabetes
- 23 March 2023
- Published by Elsevier in Control Engineering Practice
- Vol. 135
Open AccessA meta-learning approach to personalized blood glucose prediction in type 1 diabetes
- 14 January 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 120
Contrastive blind denoising autoencoder for real time denoising of industrial IoT sensor data
- 14 January 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 120
Contrastive blind denoising autoencoder for real time denoising of industrial IoT sensor data