A5001187815- Cell Image Analysis Techniques
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Advanced Electron Microscopy Techniques and Applications
- Video Surveillance and Tracking Methods
- Scientific Computing and Data Management
- Video Analysis and Summarization
- AI in cancer detection
- Medical Image Segmentation Techniques
- Molecular Biology Techniques and Applications
- Simulation Techniques and Applications
- Data Management and Algorithms
- Advanced Data Compression Techniques
- Distributed and Parallel Computing Systems
- Medical Imaging Techniques and Applications
- Single-cell and spatial transcriptomics
- Advanced Multi-Objective Optimization Algorithms
- Caching and Content Delivery
- Real-time simulation and control systems
Universidade Federal de Minas Gerais
2023-2024
Universidade de Brasília
2017-2022
We investigate efficient sensitivity analysis (SA) of algorithms that segment and classify image features in a large dataset high-resolution images. Algorithm SA is the process evaluating variations methods parameter values to quantify differences output. A can be very compute demanding because it requires re-processing input several times with different parameters assess In this work, we introduce strategies efficiently speed up via runtime optimizations targeting distributed hybrid systems...
Summary Parameter sensitivity analysis (SA) is an effective tool to gain knowledge about complex applications and assess the variability in their results. However, it expensive process as requires execution of target application multiple times with a large number different input parameter values. In this work, we propose optimizations reduce overall computation cost SA context that segment high‐resolution slide tissue images, ie, images resolutions 100k × pixels. Two cost‐cutting techniques...
Similarity search is utilized in specialized database systems designed to handle multimedia data, often represented by high-dimensional features. In this paper, we focus on accelerating the process with GPUs. This problem has been previously approached Inverted File Asymmetric Distance Computation algorithm (IVFADC) However, most recent for CPU, Multi-Index (IMI), was not considered parallelization because it found too challenging efficient GPU deployment. Thus, propose a novel and version...
<title>Abstract</title> Content-Based Multimedia Retrieval (CBMR) has become very popular in several applications, driven by the growing routine use of multimedia data. Since datasets used real-world applications are large and descriptor’s dimensionality is high, querying an expensive, albeit important functionality. Further, exact search prohibitive most cases, motivating Approximate Nearest Neighbour Search (ANNS) algorithms, trading accuracy for performance. These have been mainly...
<title>Abstract</title> Similarity search is an key operation in Content-based multimedia retrieval(CBMR) applications. Online CBMR applications, which the focus of thiswork, have to large and dynamic datasets that are updated during theexecution while offering low response times. Additionally, these applications aresubmitted workloads vary at runtime. The computing demands thisscenario exceeds processing power a single computer, motivating large-scale machines domain. Thus, this work, we...
Digital pathology imaging enables valuable quantitative characterizations of tissue state at the sub-cellular level. While there is a growing set methods for analysis whole slide images, many them are sensitive to changes in input parameters. Evaluating how results affected by variations parameters important development robust methods. Executing algorithm sensitivity analyses systematically varying an expensive task because single evaluation run with moderate number images may take hours or...
With the increasingly availability of digital microscopy imagery equipments there is a demand for efficient execution whole slide tissue image applications. Through process sensitivity analysis it possible to improve output quality such applications, and thus, desired quality. Due high computational cost analyses recurrent nature executed tasks from methods (i.e., reexecution tasks), opportunity computation reuse arises. By performing we can optimize run time This work focuses then on...
Efficient execution of parameter sensitivity analysis (SA) is critical to allow for its routinely use. The pathology image processing application investigated in this work processes high-resolution whole-slide cancer tissue images from large datasets characterize and classify the disease. However, parameterized changes values may significantly affect results. Thus, understanding impact parameters output using SA important draw reliable scientific conclusions. rather compute intensive, a...