This dataset comprises 40 high-resolution histopathology image tiles obtained from anal canal wall specimens of patients with grade III and IV haemorrhoidal disease. Tissue sections were subjected to an immunohistochemical reaction for the detection of interstitial cells of Cajal (ICC) using an anti-CD117 (c-Kit) antibody. Each image tile, with a resolution of 2048 x 2048 pixels, is provided together with a corresponding segmentation mask that outlines the location and morphology of ICC. Key Specifications: Image Resolution: 2048 x 2048 pixels per tile; Number of Images: 40; Annotations: Segmentation masks. Fišere, I.; Edelmers, E.; Svirskis, Š.; Groma, V. Utilisation of Deep Neural Networks for Estimation of Cajal Cells in the Anal Canal Wall of Patients with Advanced Haemorrhoidal Disease Treated by LigaSure Surgery. Cells 2025, 14, 550. https://doi.org/10.3390/cells14070550