LAUSR

BACKGROUND Retained surgical items are serious human errors. Surgical sponges account for 70% of retained surgical material. To prevent retained surgical sponges, it is important to establish a system that can identify errors and avoid the occurrence of adverse events. To date, no computer-aided diagnosis (CAD) software specialized for detecting retained surgical sponges has been reported. We developed a software program that enables easy and effective computer-aided diagnosis of retained surgical sponges with high sensitivity and specificity using the technique of deep learning, a subfield of artificial intelligence (AI). STUDY DESIGN In this study, we developed the software by training it through deep learning using a dataset and then validating the software. The dataset consisted of a training set and validation set. We created composite radiographs consisting of normal postoperative radiographs and surgical sponge radiographs for a training set (n=4554) and a validation set (n=470). Phantom radiographs (n=12) were prepared for software validation. Radiographs taken with surgical sponges inserted into cadavers were used for validation purposes (Formalin: Thiel's method= 252:117). Furthermore, postoperative radiographs without retained surgical sponges were used for the validation of software performance to determine false positive rates. Sensitivity, specificity, and false positives per image were calculated. RESULTS In the phantom radiographs, both the sensitivity and specificity in software image interpretation were 100%. The software achieved 97.7％ sensitivity and 83.8％ specificity in the composite radiographs. In the normal postoperative radiographs, the specificity achieved was 86.6%. In reading the cadaveric X-ray radiographs, the software attained both sensitivity and specificity of greater than 90%. CONCLUSION Software with high sensitivity for diagnosis of retained surgical sponges was successfully developed.