Data preview

Hello, I'm trying to preview the imaging data along with corresponding lesion annotation. I'm using 3D Slicer tool to preview the data, loading the T2W scan and overlaying the lesion annotation on it. And I got some following previews. Though I don't know much about how caPCas present on MRI, these annotations seems to be misplaced for my eyes. May I ask I'm previewing data correctly, are these previews exactly how the data supposed to look like?

Hi Lingxiao,

Thanks for your query.

We have double-checked this case (patient 10522, study 100532), and indeed, the annotation (made under a radiologist's supervision) seems to be correct. Morphological appearance on T2W, high signal value on DWI, and low signal value on ADC, for the region covered by the annotation (shown in my screenshot below), seems consistent with what you would expect of csPCa. Exact slice that you've shared in your example image is near the base of the prostate gland, where the csPCa lesion seems to be extending into or invading the seminal vesicles.

For more clarity, I would highly recommend scrolling through at least all three axial MRI sequences (i.e. files ending in _t2w.mha, _hbv.mha, _adc.mha ) in parallel, and in 3D, with the annotation overlaid on top. At my end, I use ITK-SNAP v3.80 to do this. I would also recommend reading the following article to get familar with the interpretation of csPCa in MRI (helped me a lot back when I got started):

• B. Israël, M. van der Leest, M. Sedelaar, A.R. Padhani, P. Zámecnik, J.O. Barentsz, "Multiparametric Magnetic Resonance Imaging for the Detection of Clinically Significant Prostate Cancer: What Urologists Need to Know. Part 2: Interpretation", European Urology. DOI: 10.1016/j.eururo.2019.10.024

If you want to dive into even more details, then you can have a look at the PI-RADS v2.1 guidelines.

Hope this helps.

Hello Anindo,

Thank you for your work and informative suggestions, these are very useful and I shall learn a lot.

Hello participants, is there any demo about the competition just to get familiar with such kind of data? Could you share with me if it is possible! Good luck !