Artificial intelligence algorithms enhance urine cytology reporting confidence in postoperative follow-up for upper urinary tract urothelial carcinoma.

Abstract

In Taiwan, the incidence of urothelial carcinoma of the upper urinary tract (UTUC) is high and intravesical recurrence is approximately 22%-47%. Thus, postoperative cystoscopy and urine cytology follow-up, which require experienced cytologists, are needed. The AIxURO system aligns with The Paris System (TPS) guidelines for reporting urinary cytology. This study assessed the benefit of early detection of intravesical recurrence after nephroureterectomy using the AIxURO system. Urine cytology slides (n = 296) from 113 patients with UTUC were retrieved and patient data, pre-operative and postoperative cytology, pathology, and follow-up series for the intravesical recurrence group were collected. Cytology slides were digitized and independently assessed by the AIxURO system, and the results were compared to cytology reports. From January 2022 to August 2023, 113 patients with UTUC underwent nephroureterectomy. Eighty-eight patients (88/113, 77.8%) received 1 or 2 cytology examinations pre-operatively, 44 slides (44/204, 21.5%) were positive and 34 patients (34/113, 30.1%) were diagnosed with UTUC. Postoperative intravesical recurrence was detected in 27 patients (27/113, 23%) at an average of 190.62days. Thirty-four slides (34/56, 60.7%) were negative for UTUC. Eight patients (8/27, 29.6%) met the criteria for early diagnosis of intravesical recurrence. The AIxURO system identified two more patients (10/27, 37.0%) with early intravesical recurrence. The AIxURO system enhanced postoperative urine cytology reporting confidence and could identify some underdiagnosed slides to enhance the early detection of UTUC with intravesical recurrence. AIxURO may be used for post-nephroureterectomy follow-up and reduce the necessity for cystoscopy.