b'

\n\t\xc2\xa0

\n\tb'

\nTeam: Technische Universitat Munchen, Computer Aided Medical Procedure (CAMP), Munich, Germany

\n

\n\tAuthors: Bharti Munjal, Amil George, Shadi Albarqouni, Stefanie Demirci, Nassir Navab

\n

\n\tAbstract:

\n

\nThe system uses two GoogleNet models trained on levels 6 and 3 respectively. Then, few geometric features are extracted from the response maps, i.e. Area, Orientation, Major/Minor Axis Length, statistical features (max, min, and mean) and fed to a random forest to predict the probability of a slide having a metastasis.\n\t

\n

\n\tResults:

'\n

\n\tThe following figure shows the receiver operating characteristic (ROC) curve of the method.

\n

\n

\n

\n

\n\t\xc2\xa0

\n

\n\tThe following figure shows the free-response receiver operating characteristic (FROC) curve of the method.

\n
\n

\n\t\xc2\xa0

\n

\n\tThe table below presents the average sensitivity of the developed system at 6 predefined false positive rates: 1/4, 1/2, 1, 2, 4, and 8 FPs per whole slide image.

\n

Error rendering graph from file

'