SPECIALLY COLLECTED PAPERS
Shimadzu Review 80[1・2] (2023)
Abstract
In surgery, medical incidents occur, such as surgical instruments left inside patients. They have potentially harmful consequences for the patient as they can be life threatening, and usually a further operation is necessary, which is stressful for patients. For hospitals, these incidents can lead to reputational damage and economic losses. To prevent these accidents, surgical instruments are counted before and after surgery and confirmed by X-ray images after surgery. However, incidents still occur due to various factors, such as the miscounting of surgical instruments or missing retained objects on X-ray images. We developed image processing using deep learning to support the confirmation of retained objects, such as surgical instruments, in X-ray images. This image processing emphasizes regions of the input image that have features different from a human being. This supports the prevention of human error in confirming the existence of retained objects in X-ray images after surgery. We expect that this software will contribute to the reduction of medical incidents.
Research & Development Department, Medical Systems Division, Shimadzu Corporation, Kyoto, Japan
*The information contained in Shimadzu Review has not been modified since the original publication date. Please be aware that in some cases, products mentioned within the articles are no longer available.