Titulo Estágio
Prediction Model for Women Breast Cancer Recurrence
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
University of Coimbra -- Department of Informatics Engineering
Enquadramento
Breast cancer (BC) is the most prevalent cancer in women and although the most recent therapeutic developments; it remains the first cause of death for cancer in female gender worldwide [1]. Nowadays, it is well recognized that BC is not a single disease but it probably consists in a collection of diseases displaying distinct morphological and genomic features, which account for diverse prognostic outcomes [2,3,4]. Like other solid tumors, the disease prognosis is intrinsically related to recurrence (metastic spread), and specific for BC, it is well know that even in non-regional metastasis, the disease prognosis differs concerning the local involved (bone only vs visceral non hepatic vs visceral hepatic). Despite remarkable improvements in BC characterization, we do not achieve yet, an exhaustive comprehension of the underlying carcinogenic process that accurate prediction of its clinical behavior. This fact limits our capacity to define the most personalized therapeutic approach ad initium, which determines undesired overtreatment [5].
[1] Globocan 2012, accessed in www. globocan.iarc.fr, in 05/08/2014;
[2] Beca F, et al. Primary relapse site pattern in women with triple-negative breast cancer. Pathology-research and practice, in press
[3] Sorlie T, et al. Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications. Proc. Natl. Acad. Sci. USA. 98 (2001), 10869-10874.
[4]Perou CM, et al. Molecular portraits of human breast tumours. Nature 406 (2000), 747-752.
[5] Reis-Filho JS. Molecular profiling: moving away from tumor philately. Sci. Transl. Med. 2 (2010), 1482-1485.
Objetivo
1. To evaluate the pattern of metastatic spread in patients with breast cancer;
2. To establish the relation between patterns of metastic spread, patients characteristics and BC subtypes (based in immunochemistry analysis);
3. To construct a model of recurrence of BC in an attempt to define a recurrence pattern based on patients and tumors characteristics.
Patients enrolled
- Age>18 years- old,
- Female gender,
- Histological confirmation of breast carcinoma,
- Determination of nuclear grade, and hormonal receptors, HER 2 and ki67 expression by immunohistochemistry analysis;
- Stage I, II or III.
Plano de Trabalhos - Semestre 1
-Study and analysis the state of the art concerning pattern recognition techniques and data streams;
-Collection of clinical information to construct the database.
Plano de Trabalhos - Semestre 2
-Implementation of different pattern recognition techniques;
-Evaluation of the implemented procedures in the breast cancer data;
-Comparison of obtained results and conclusions;
-Writing the report of the Master Degree Thesis.
Condições
The proposal will not be funded
Orientador
Pedro Abreu
pha@dei.uc.pt 📩