DEEP RANDOM FORESTS FOR SMALL SAMPLE SIZE PREDICTION WITH MEDICAL IMAGING DATA

Katzmann, Alexander; Muehlberg, Alexander; Suehling, Michael; Noerenberg, Dominik; Holch, Julian Walter und Gross, Horst-Michael (2020): DEEP RANDOM FORESTS FOR SMALL SAMPLE SIZE PREDICTION WITH MEDICAL IMAGING DATA. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020): S. 1543-1547

Abstract

Deep neural networks represent the state of the art for computer-aided medical imaging assessment, e.g. lesion detection, organ segmentation and disease classification. While for large datasets their superior performance is a clear argument, medical imaging data is often small and highly heterogeneous. In combination with the typical parameter amount in deep neural networks, this often leads to overfitting and results in a low level of generalization performance. We propose a straight-forward combination of random forests and deep neural networks for superior performance on medical imaging datasets with only small data, and provide an extensive evaluation of survival prediction for metastatic colorectal cancer patients using computed tomography imaging data, with our proposed method clearly outperforming other approaches.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Medizin
• Themengebiete: 600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin und Gesundheit
• ISSN: 1945-7928
• Sprache: Englisch