Skip to main content
. Author manuscript; available in PMC: 2018 Mar 27.
Published in final edited form as: Comput Intell Methods Bioinform Biostat. 2017 Oct 17;10477:42–58. doi: 10.1007/978-3-319-67834-4_4

Fig. 2.

Fig. 2

Bladder cancer left, prostate cancer right. Training, validation, testing done on top slides, with additional same-tissue testing on bottom slides. For cross-tissue testing, top slide tested against other top slide. Viewing time heatmap for top left bladder shown in Fig 7. Note how the top bladder has more edges than the more solid bottom bladder, while the prostates have similar tissue texture. We believe this impacts interpatient accuracy, shown in Fig 9.