A radio-pathomics AI-based biomarker to predict pathological response in patients with rectal cancer.
Reference persons SAMANTA ROSATI
External reference persons Valentina Giannini
Research Groups Biolab: Ingegneria Biomedica
Description Rectal cancer is increasingly being recognised as a heterogeneous disease, being challenging to cure and with potential different responses to similar treatments. The standard of care is a multimodal approach incorporating neoadjuvant chemoradiotherapy, followed by total mesorectal excision and adjuvant fluoropyrimidine-based chemotherapy. Only 15–20% of LARC patients achieve a pathological complete response  and benefit from alternative treatment strategies rather than radical surgery, while some patients may not achieve any downstaging of the tumor or even show disease progression. For these nonresponder patients, the side effects of neoadjuvant chemoradiotherapy may outweigh its benefits and different treatment strategies should be considered. the objective of this thesis will be to develop an integrated AI-based multiomics predictive signature for rectal cancer, integrating cross-sectional imaging to additional layers of omics information, i.e., radiomics, pathomics and molecular.
Giovedì 28 settembre 2023 alle ore 10.00 si svolgerà una riunione online di presentazione delle proposte di tesi relative agli argomenti trattati nei corsi di Intelligenza Artificiale in Medicina, Data Science in Medicina e Progettazione di Software Medicali. Il link per partecipare alla riunione è il seguente: https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZThmNTJkMGYtNDRkNC00OTM3LWFjN2ItYmU3Y2ViMThjNTZm%40thread.v2/0?context=%7b%22Tid%22%3a%222a05ac92-2049-4a26-9b34-897763efc8e2%22%2c%22Oid%22%3a%22518f1079-9b02-487d-b6fe-25b3af221b8a%22%7d
Required skills artificial intelligence, machine learning
Deadline 10/10/2023 PROPONI LA TUA CANDIDATURA