Asosiy kontentga oʻtish
Boshqa

A Fully Automatic Multi-Vendor AI-System To Segment And Predict Resistance To Treatment Of Rectal Cancer On MRI

Jovana PanićArianna DefeudisDepartment of Radiology , Candiolo Cancer Institute , FPO-IRCCS , Candiolo , ItalyLorenzo VassalloDepartment of Diagnostic Imaging and Radiotherapy , AOU Città della Salute e della Scienza , Turin , ItalyStefano CirilloDepartment of Radiology , A. O. Ordine Mauriziano (Ospedale Umberto I) , Turin , ItalyMarco GattiUniversity of TurinAntonio EspositoSchool of Medicine , Vita-Salute San Raffaele University , Milan , ItalySerena Dell’AversanaSalvatore SienaNiguarda Cancer Center , Grande Ospedale Metropolitano Niguarda , Milan , ItalyAngelo VanzulliNiguarda Cancer Center , Grande Ospedale Metropolitano Niguarda , Milan , ItalyDaniele ReggeDepartment of Radiology , Candiolo Cancer Institute , FPO-IRCCS , Candiolo , ItalySamanta RosatiDepartment of Electronics and Telecommunications , Polytechnic of Turin , Turin , ItalyGabriella BalestraDepartment of Electronics and Telecommunications , Polytechnic of Turin , Turin , ItalyValentina GianniniUniversity of Turin
2024en
ABI

Annotatsiya

In this study, we developed and validated a fully automatic system based on pretreatment MRI to predict resistance to therapy in rectal cancer patients using a multi-center and multi-vendor database.Tumors were automatically segmented using in-house automatic U-Net segmentations and subsequently classified as responder and non-responder through a Random Forest algorithm that was fed with a subset of features selected by a customized features selection approach.Despite the strong imbalance between the two classes, the performances yielded are promising, with an area under the curve of 0.72 and a balanced accuracy of 66% on the external validation set.Even if further analyses are still required to improve the performance, our results represent a further step towards a more personalized medicine for patients with rectal cancer.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba