“…Its positive component is almost 3 times bigger than the next largest one (263,000 positive patches in ours vs. 96,530 in Xiong et al’s dataset [ 15 ]), which is 429 times bigger than the smallest ones (506 in Zaizen et al’s set [ 20 ]). Our negative patches are 7 times more numerous than the second largest one of Pantanowitz et al [ 18 ] (7,000,000 vs. 1,111,918). Further applied augmentation techniques (both as position—rotations, shifts, crops, etc.—and in image properties—brightness, contrast, saturation, etc.)…”