Tables 7 and 8 results confusing

[faresbougourzi]

First of all, thank you for your contribution to the field of Cross-Institution Few-Shot Segmentation.

While reading your paper entitled "Prototypical Few-Shot Segmentation for Cross-Institution Male Pelvic Structures with Spatial Registration," I found the evaluation scenario in Tables 6 and 7 somewhat confusing.

Based on the title of Table 7:
"Mean Dice score (%) achieved at different (s_ins, q_ins) combinations by ‘3d_con_align’ when Institution 3 was adopted as the novel institution, where s_ins and q_ins respectively refer to the institution from which the support and query were sampled from. Best performance for each query institution was bolded. p-values were derived from paired t-test performed between the Dice scores where support institution equals query institution and the maximum Dice scores achieved when support institution differs from the query institution."

Here, Institution 3 is the novel institution, so I would expect all query images to be from this institution. However, in the table title and experiment, q_ins changes. Does this mean that s_ins and q_ins refer to the training data?

Best regards,