The Prostate Imaging Reporting and Data System (PI-RADS) is a structured reporting scheme for multiparametric prostate magnetic resonance imaging, used to improve early diagnosis and treatment of prostate cancer. The PI-RADS classification is based on a scale of values from 1 to 5, assigned according to the probability that a finding is a malignant tumor (prostate carcinoma). PI-RADS score 3 is recognized as the equivocal likelihood of clinically significant prostate cancer, making its diagnosis very challenging. Prostate biopsy, consisting in the removal of small sections of suspicious tissue, is the gold standard to detect cancers. However, it is an invasive procedure with risks, such as infections.
The aim of the first Machine Learning Mini-Contest (MC1) for the academic year 2021/2022 is to detect prostate cancer in patients with PI-RADS score 3 lesions considering clinical-radiological characteristics and avoiding prostate biopsy. More in detail, the problem to solve can be considered as a binary classification task regarding the distinction between patients with and without prostate cancer.
Contest Rules Each student has to predict if the patient has prostate cancer, realising one or more prediction model using data analysis and Machine Learning techniques. The performance measure to maximise is Accuracy. It is mandatory for the student who will achieve the best performance on the test dataset, to discuss the process steps followed in order to reach the development of the final model. The winning student presentation will be held during the lesson of November the 19th. If the presentation and the proposed solution will be judged positively, the author will be relieved from the final contest. Each participant is free to use external tools (i.e. Weka, Knime, MatLab, etc.).
https://www.kaggle.com/c/unina-machine-learning-2122-minicontest-n1/overview