Corrigendum to “Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art” [Comput. Biol. Med. 169 (2024) 107929] (Computers in Biology and Medicine (2024) 169, (S0010482524000131), (10.1016/j.compbiomed.2024.107929))

The authors regret that the SAR-RARP50 dataset is missing from the description of publicly available datasets presented in Chapter 4. To ensure the comprehensiveness of the chapter, one entry each in Tables 1 and 2 and a short paragraph in Chapter 4.10 have to be added. The following entry must be added to Table 1, together with the corresponding reference [1] in the bibliography: [Table presented] The following entry must be added to Table 2: [Table presented] The following paragraph must be added to Chapter 4.10: The dataset for performing the “SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge” [1] in 2022 consists of 50 procedures with a total of 16250 annotated images showing radical prostatectomy performed with the DaVinci Si system. All images were captured at a resolution of 1920 × 1080 pixels, and annotations are available for the recognition of surgical actions as well as for the semantic segmentation of surgical instruments. The frames were labeled at a frequency of 1 FPS, and nine categories were used for semantic segmentation, divided into six non-tool objects and three part-level categories for shaft, wrist, and instrument claspers. The authors would like to apologise for any inconvenience caused.