A5079038839- AI in cancer detection
- Digital Imaging for Blood Diseases
- Online Learning and Analytics
- Data Stream Mining Techniques
- Radiomics and Machine Learning in Medical Imaging
- Cervical Cancer and HPV Research
- Gene expression and cancer classification
- Data Mining Algorithms and Applications
- Cultural Heritage Materials Analysis
- Building Energy and Comfort Optimization
- Intelligent Tutoring Systems and Adaptive Learning
- Industrial Vision Systems and Defect Detection
- Digital Imaging in Medicine
- Smart Agriculture and AI
- Remote-Sensing Image Classification
- Machine Learning and Data Classification
- Genomic variations and chromosomal abnormalities
- COVID-19 diagnosis using AI
- Augmented Reality Applications
- Control Systems and Identification
- Head and Neck Cancer Studies
- E-Learning and Knowledge Management
Universidade Federal de Santa Catarina
2018-2022
Algorithms and programming are some of the most challenging topics faced by students during undergraduate programs. Dropout failure rates in courses involving such usually high, which has raised attention towards development strategies to attenuate this situation. Machine learning techniques can help direction providing models able detect at-risk earlier. Therefore, lecturers, tutors or staff pedagogically try mitigate problem. To early predict introductory courses, we present a comparative...
The present work describes the challenges faced during development of a countrywide Learning Analytics study and tool focused on tracking understanding trajectories Uruguayan students their first three years secondary education. Due to large scale project, which covers an entire national educational system, several constraints were its conception development. Examples key were: understand different nuances satisfy ethical legal requirements without narrowing down scope potential novelty...
The present work describes the challenges faced during development of a countrywide Learning Analytics tool focused on tracking trajectories Uruguayan students their first three years secondary education. Due to large-scale project, which covers an entire national educational system, several and constraints (both technical legal) were its conception development. This paper presents design decisions solutions found address or mitigate problems found, with current state project. Early results...
Cervical cancer is the second most common type in women. This a deadly disease that could benefit from early detection methods. Cytology possible, noninvasive, alternative to biopsy for diagnosis of malignant lesions, where information about cells can be obtained. process consists staining slides being able visualize nuclei and then properly diagnosed. In this work, silver-stained slides, method known as Argyrophilic Nucleolar Organizer Regions (AgNOR), employed. shows great potential...
Although oral cancer is considered a global health issue with 350.000 people diagnosed over year it can successfully be treated if at early stages. Papanicolaou an unexpensive and non-invasive method, generally applied to detect cervical cancer, but also useful on cavities. The manual process of analyzing cells abnormalities time-consuming cell analysis subject variations in perceptions from different professionals. This paper compares models for three deep learning approaches: segmentation,...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Soluções modernas para registro de procedimentos médicos representam tecnologia ponta que ainda está surgindo e enfrentando desafios. Este artigo apresenta o Life Surgery Box, um gravador vídeo brasileiro autônomo imagens sincronizadas multimodais. Objetivo: apresentar desenvolvimento prototipagem do equipamento, destinado ao uso tanto em salas cirúrgicas quanto consultórios médicos. Método: envolve a descrição suas arquiteturas hardware software, com foco algoritmo desfoque facial baseado...
Cervical cancer is the second most common type in womenaround world. In some countries, due to non-existent or inadequatescreening, it often detected at late stages, making standardtreatment options absent unaffordable. It a deadlydisease that could benefit from early detection approaches. isusually done by cytological exams which consist of visually inspectingthe nuclei searching for morphological alteration. Since itis humans, naturally, subjectivity introduced. Computationalmethods be...
Abstract Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, that can also be useful cancer on oral cavities. Although considered a global health issue with 350.000 people diagnosed over year it successfully treated if at early stages. The manual process of analyzing cells abnormalities time-consuming subject variations in perceptions from different professionals. To evaluate possible solution the automation this process, paper we employ...
It is possible to observe an enormous increase on the number of researches focused automatically find patterns and factors that affect students behavior performance during their learning process. The fields Learning Analytics Educational Data Mining are in constant growing, developing new innovative tools. Furthermore, methodologies being created follow help professors inside many different types educational settings. At same time, it also see majority existing works still restricted small...
Cervical cancer is the second most common type in women around world. In some countries, due to non-existent or inadequate screening, it often detected at late stages, making standard treatment options absent unaffordable. It a deadly disease that could benefit from early detection approaches. usually done by cytological exams which consist of visually inspecting nuclei searching for morphological alteration. Since humans, naturally, subjectivity introduced. Computational methods be used...
The conventional Papanicolaou sample preparation technique is the worldwide most commonly used method for cell morphology analysis and cancer detection. It generally applied to detect cervical cancer, but it can also be useful in oral cavities. However, manual process of analyzing samples abnormalities a time-consuming task subject variations perception from different professionals. Thus, evaluate possible automation pipelines this process, paper compares composed three deep-learning-based...
Cervical cancer is a public health problem, where the treatment has better chance of success if detected early. The analysis manual process which subject to human error, so this paper provides way analyze argyrophilic nucleolar organizer regions (AgNOR) stained slide using deep learning approaches. Also, compares models for instance and semantic detection Our results show that segmentation U-Net with ResNet-18 or ResNet-34 as backbone have similar results, best model shows an IoU nucleus,...