Laura Daza
A5088988977- Brain Tumor Detection and Classification
- Advanced Neural Network Applications
- Forensic Anthropology and Bioarchaeology Studies
- Artificial Intelligence in Healthcare and Education
- Radiomics and Machine Learning in Medical Imaging
- Adversarial Robustness in Machine Learning
- Computational Drug Discovery Methods
- Retinal Imaging and Analysis
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Medical Image Segmentation Techniques
- Human Pose and Action Recognition
- Biomedical and Engineering Education
- Genetics, Bioinformatics, and Biomedical Research
- Autopsy Techniques and Outcomes
- Bacillus and Francisella bacterial research
- Retinal Diseases and Treatments
- Medical Imaging and Analysis
- Biomedical Text Mining and Ontologies
- Explainable Artificial Intelligence (XAI)
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Health and Medical Research Impacts
- Crystallization and Solubility Studies
- Multimodal Machine Learning Applications
Universidad de Los Andes
2017-2024
FHNW University of Applied Sciences and Arts
2023
Universidad del Rosario
2020
International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far most widely investigated medical processing task, but various segmentation typically been organized in isolation, such that algorithm development was driven by need to tackle single clinical problem. We hypothesized method capable performing well on multiple tasks will generalize previously unseen task and potentially outperform...
Performance of models highly depend not only on the used algorithm but also data set it was applied to. This makes comparison newly developed tools to previously published approaches difficult. Either researchers need implement others' algorithms first, establish an adequate benchmark their data, or a direct new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims address this problem comparability....
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, potential errors hinder translating DL into clinical workflows. Quantifying reliability model predictions form uncertainties could enable review most uncertain regions, thereby building...
Lung cancer is by far the leading cause of death in US. Recent studies have demonstrated effectiveness screening using low dose CT (LDCT) reducing lung related mortality. While nodules are detected with a high rate sensitivity, this exam has specificity and it still difficult to separate benign malignant lesions. The ISBI 2018 Nodule Malignancy Prediction Challenge, developed team from Quantitative Imaging Network National Cancer Institute, was focused on prediction nodule malignancy two...
Drug Discovery is an active research area that demands great investments and generates low returns due to its inherent complexity costs. To identify potential therapeutic candidates more effectively, we propose protein-ligand with adversarial augmentations network (PLA-Net), a deep learning-based approach predict target-ligand interactions. PLA-Net consists of two-module graph convolutional considers ligands' targets' most relevant chemical information, successfully combining them find their...
The discovery and development of novel pharmaceuticals is an area active research mainly due to the large investments required long payback times. As 2016, a drug candidate up $ USD 2.6 billion in investment for only 10% rate approval by FDA. To help decreasing costs associated with process, number silico approaches have been developed relatively low success limited predicting performance. Here, we introduced machine learning-based algorithm as alternative more accurate search new...
In September 2023, the two largest bioimaging networks in Americas, Latin America Bioimaging (LABI) and BioImaging North (BINA), came together during a 1-week meeting Mexico. This provided opportunities for participants to interact closely with decision-makers from imaging core facilities across Americas. The was held hybrid format attended in-person by scientists including Canada, United States, Mexico, Colombia, Peru, Argentina, Chile, Brazil Uruguay. aims of were discuss progress achieved...
Brain lesion segmentation is one of the hardest tasks to be solved in computer vision with an emphasis on medical field. We present a convolutional neural network that produces semantic brain tumors, capable processing volumetric data along information from multiple MRI modalities at same time. This results ability learn small training datasets and highly imbalanced data. Our method based DeepMedic, state art segmentation. develop new architecture more layers, organized three parallel...
International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far most widely investigated medical processing task, but various segmentation typically been organized in isolation, such that algorithm development was driven by need to tackle single clinical problem. We hypothesized method capable performing well on multiple tasks will generalize previously unseen task and potentially outperform...
Bone Age Assessment (BAA) is a task performed by physicians to estimate the skeletal development of pediatric patient. Tipically perform this exam doing manual analysis X-ray image non-dominant hand child, either taking as whole or paying attention certain anatomical Regions Of Interest (ROIs). Over years, several datasets have been proposed in order generate automated methods task. Most notably, 2017 Radiological Society North America (RSNA)1 created Pediatric Challenge, which encouraged...
Abstract The discovery and development of novel pharmaceuticals is an area active research mainly due to the large investments required long payback times. As 2016, a drug candidate up $ USD 2.6 billion in investment for only 10% rate approval by FDA. To help decreasing costs associated with process, number silico approaches have been developed relatively low success limited predicting performance. Here, we introduced machine learning-based algorithm as alternative more accurate search new...
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, potential errors hinder translating DL into clinical workflows. Quantifying reliability model predictions form uncertainties could enable review most uncertain regions, thereby building...
Abstract Drug Discovery is an active research area that demands great investments and generates low returns due to its inherent complexity costs. To identify potential therapeutic candidates more effectively, we propose Protein-Ligand with Adversarial augmentations Network (PLA-Net), a Deep Learning-based approach predict Interactions (PLI). PLA-Net consists of two-module Graph Convolutional considers ligands’ targets’ most relevant chemical information, successfully combining them find...
We implemented Video Swin Transformer as a base architecture for the tasks of Point-of-No-Return temporal localization and Object State Change Classification. Our method achieved competitive performance on both challenges.