Titulo Estágio
Text mining techniques applied to biopsy medical reports for esophagus cancer classification
Áreas de especialidade
Engenharia de Software
Sistemas Inteligentes
Local do Estágio
DEI
Enquadramento
Esophageal cancer is the eighth most common cancer and the sixth leading cause of cancer-associated fatalities.
Neoadjuvant therapy has been shown to improve the prognosis of patients in whom a complete or subtotal histopathologic tumor regression is achieved. However, non-responders appear to have poor prognoses, but surgery improves survival in these patients.
Identification of ``responders'' from ``nonresponders'' can help to appropriately select patients for surgery, avoiding the mortality and morbidity of surgery in responders for whom surgery can be safely deferred, while improving local control and survival in non-responders for whom surgery should be considered.
Objetivo
The project has thus the final goal of determining a clear definition of the criteria for non-surgical (conservative) approach for oesophagic early-stage cancers.
Having as basis a set of medical reports, the goal is to use different text mining techniques to mine information on a patient status and history having in consideration that there are several types of reports and multiple reports per patient.
Plano de Trabalhos - Semestre 1
1: Study the state of the art literature on esophagus cancer
2: Study the state of the art literature on text mining techniques
3: Select the most important keywords to describe the cancer stage
4: Creation and validation of the project work plan
Plano de Trabalhos - Semestre 2
1: Implement and test different techniques to extract information from the reports
2: Implement and test different techniques to merge the information per patient
3:Write a scientific article and dissertation
Condições
The work is not financed
Orientador
Pedro Henriques Abreu
pha@dei.uc.pt 📩