A tutor system for diagnosing ultrasound images of the prostate
The TuBUs-Pro project aims at tutoring the use of the ANNA-framework to analyze conventional rectal ultrasound images of the prostate. The system provides different training modes with varying difficulty levels, ranging from “mark a suspicious region in a particular ultrasound image” to “find all primary cancers in a complete case”.
The TuBUs-Pro project aims at tutoring the use of the ANNA-framework to analyze conventional rectal ultrasound images of the prostate. The system provides different training modes with varying difficulty levels, ranging from “mark a suspicious region in a particular ultrasound image” to “find all primary cancers in a complete case”. The user is provided with aids (i.e. texture analysis functions) that can be applied to an image and help putting the diagnosis. This way, students get used to pre-analyzed images and to the mental combination of descriptor responses in order to judge a given situation. Although this would be sufficient for a tutoring system TuBUs-Pro can additionally serve as a framework to develop, evaluate, and compare tissue descriptors, since it provides a ground truth i.e. a very large database of manually segmented cases that can be used to judge the performance of newly developed descriptors and descriptor combinations.
Image 1: From an input image several intermediate images are calculated and presented to the user. These intermediates are combined to form the final output image.
Image 2: The TuBUs-Pro GUI showing the evaluation of an exercise, where three out of five regions were marked correctly and two incorrectly. Note that it is extremely difficult to visually detect primary cancer regions i.e. to distinguish them from healthy tissue.