Abstract #2262
Computer Aided Radiological Diagnostics: Random Forest Classification of Glioma Tumor Progression using Image Texture Parameters derived from ADC-Maps.
Johannes Slotboom 1 , Nuno Pedrosa de Barros 1 , Stefan Bauer 2 , Urspeter Knecht 1 , Nicole Porz 3 , Philippe Schucht 3 , Pica Pica 4 , Andreas Raabe 3 , Roland Wiest 5 , and Beate Sick 6
1
DRNN, Institute of Diagnostic and
Interventional Neuroradiology, University Hospital Bern,
Bern, Switzerland,
2
Institute
of Surgical Technology and Biomechanics, University
Bern, Bern, Switzerland,
3
DKNS-Neurosurgery,
University Hospital Bern, Bern, Switzerland,
4
DOLS-Radiooncology,
University Hospital Bern, Bern, Switzerland,
5
1DRNN,
Institute of Diagnostic and Interventional
Neuroradiology, University Hospital Bern, Bern,
Switzerland,
6
Division
of Biostatistics, ISPM, University Zrich, Zrich,
Switzerland
Despite the huge amount of information provided by an
MR-examination, the initial diagnosis and grading of
frequently extremely heterogeneous brain tumors by
visual inspection remains a difficult task. A diagnostic
text often lists a number of most likely diagnoses, e.g.
anaplastic astrocytoma or glioblastoma multiforme. Here
we discuss a method for computer aided radiologic
diagnostics on how texture parameter analysis in
combination with the advanced statistical classification
random forest algorithm can be used to solve important
differential diagnosis problem for individual
diagnostics.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
