Computer Vision News - July 2022

40 AI for Medical Imaging Tissue sparing is a common practice during surgeries. This approach aims to remove as little as possible of the surrounding tissue during a procedure. Studies have shown that tissue sparing procedures have fewer complications and faster recovery time. Inurology, tissuesparing isrelevantformany surgical procedures. In prostatectomy , whether partial or radical, it is important to remove cancer cells without leaving any behind. However, intensive tissue resection may damage the neurovascular bundle (NVB), resulting in erectile dysfunction or incontinence. By sparing tissue during prostatectomy, the risk for NVB damage is reduced. Female cystectomy is usually accompanied by removal of surrounding organs . This is performed to reduce risk of malignancy in the future. However, preservation of gynecological organs canassist instructural support of the remaining organs, as well as improve quality of life for the patient. This can be done by careful preoperative planning and accurate execution. Tissue sparing can be achieved using the following techniques: 1. minimal incisions for surgical access 2. extreme precision for tumor removal 3. steady handling of surgical tools . Below we will discuss how implementation of artificial intelligence (AI) and computer vision (CV) can improve these techniques and assist in tissue sparing. (1) When attempting to minimize the entry port in a laparoscopic or open procedure, there are several challenges. The field of view (FOV) and the tool’s operating range will be limited. When the FOV is limited, it is difficult to navigate the surgical scenery and recognize anatomical landmarks. Deep learning networks can be trained to detect specific landmarks and highlight them on the screen, assisting in recognition during the procedure. Additionally, utilizing the pre-opCTorMRI scan, adetailedprocedure plan can be devised by segmenting and modeling the relevant anatomical structures, and the ideal incision position can be determined. This plan can be registered with intra-op imaging to verify incision location. Also, a full surgical plancan be devised using pre-op imaging, and this plan can be introduced into the surgeon’s view using image registration. Developing such modules is done using a combination of classic computer vision algorithms and deep learning. (2) Removing a tumor, radical or partial removal of an organ, requires precise dissection of the tissue. The tumor needs to be removed fully, with minimal damage to surrounding healthy tissue, vasculature, AI ASSISTED TISSUE SPARING IN UROLOGY