Artificial intelligence: the future of urinary stone management?

Jahrreiss, Victoria; Veser, Julian; Seitz, Christian; Özsoy, Mehmet

doi:10.1097/mou.0000000000000707

Cited by 7 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these preliminary and promising results described above explain why the medical community in urology is convinced of the interest of kidney stone recognition methods based on artificial intelligence [51], [52] and of the importance of incorporating computer-aided diagnosis tools in their workflow [53]. This work is an extension of a preliminary study [16] which still improved the classification results using a RF classifier.…”

Section: B Previous Attempts Of Kidney Stone Classificationmentioning

confidence: 70%

On the In Vivo Recognition of Kidney Stones Using Machine Learning

Lopez-Tiro,

Estrade,

Hubert

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Determining the type of kidney stones allows urologists to prescribe a treatment to avoid the recurrence of renal lithiasis. An automated in-vivo image-based classification method would be an important step towards an immediate identification of the kidney stone type required as a first phase of the diagnosis. In the literature, it was shown on ex-vivo data (i.e., in very controlled scene and image acquisition conditions) that an automated kidney stone classification is indeed feasible. This pilot study compares the kidney stone recognition performances of six shallow machine learning methods and three deep-learning architectures which were tested with in-vivo images of the four most frequent urinary calculus types acquired with an endoscope during standard ureteroscopies. This contribution details the construction of an in-vivo dataset of endoscopic images with four of the most recurrent classes in clinical practice. It also describes the design, implementation, and results of the classifiers (shallow machine learning and deep learning-based methods) of kidney stones. Even if the best results were obtained by the InceptionV3 architecture (weighted accuracy, precision, recall and F1-Score of 97 ± 03%, 97 ± 03%, 98 ± 04%, and 98 ± 03%, respectively), it is also shown that choosing an appropriate colour space and texture features allows a shallow machine learning method to approach closely the performances of the most promising deep-learning methods (the XGBoost classifier led to weighted accuracy, precision, recall and F1-Score values of 96 ± 14%).

show abstract

Section: B Previous Attempts Of Kidney Stone Classificationmentioning

confidence: 70%

On the In Vivo Recognition of Kidney Stones Using Machine Learning

Lopez-Tiro,

Estrade,

Hubert

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The optimization process is intended not only as the reduction in the diameter of our tools but also as adjustments in length and improvement of the maneuverability of the instruments when needed. Additionally, a better patient selection translates into higher success rates and improved safety; to accomplish this task first attempts have been made to combinate artificial intelligence and new technological developments in the field of endourology in adults (32).…”

Section: Discussionmentioning

confidence: 99%

Minimally Invasive Approaches in Pediatric Urolithiasis. The Experience of Two Italian Centers of Pediatric Surgery

et al. 2020

View full text Add to dashboard Cite

Background: Over the last 30 years, the incidence of pediatric urolithiasis (PU) has been increasing and the surgical management has evolved toward a minimally invasive approach (MIA). We reported the experience of two Centers of Pediatric Surgery in the management of PU, focusing on MIA as first choice in treatment. Methods: Data were retrospectively analyzed from October 2009 to October 2019 in children with urolithiasis who were admitted to two referral Italian Centers of Pediatric Surgery. Demographic and clinical data of the patients, features of the urolithiasis, type of surgery were considered. Results: Seventy patients (7.3 ± 5.0 years) with normal renal function were treated for calculi in the pyelocaliceal system (45.7%), ureter (34.3%), bladder (4.3%), urethra (1.4%), and multiple locations (14.3%). Size of calculi was >10 mm in 55.7% of cases (kidney>bladder/urethra>multiple>ureter, p = 0.01). Symptoms were present in 75.7% of patients. Family history was positive in 16.9% of cases. MIA was performed in 59 patients (84.3%): 11.8% shockwave lithotripsy (kidney>ureter>multiple); 32.2% ureteral retrograde surgery (ureteral>other localizations); 30.5% retrograde intrarenal surgery (kidney>other localizations); and 25.4% other procedures including percutaneous nephrolithotomy, cystoscopic bladder stone removal or laser cystolithotripsy (kidney>bladder>multiple). Preoperative stenting was necessary in 52.8% of cases. Four MIA procedures (6.9%, kidney>ureter/multiple) were converted to open surgery. Open surgery was required as first approach in 15.7% of patients (kidney>ureter>multiple) who needed urgent surgery or had associated congenital renal anomalies. In 18/70 of children (25.7%), with prevalence of stones in kidney and multiple location (p < 0.01), a second procedure completed the treatment (88.8% MIA). Intraoperative difficulties were recorded in 8.5% of cases, without difference between location and size of calculi. Late complications (5.7%) were related to displacement and infection of the ureteral stent. Conclusions: MIA resulted to be feasible in more than 75% of primary surgery and in more than 85% of cases requiring a second procedure. Preoperative stent Destro et al. Minimally Invasive Approaches in Pediatric Urolithiasis was mandatory in more than 50% of children. The technological evolution allowed to overcome many of the technical difficulties related to the approach to the papilla and lower calyxes. Open surgery is reserved for selected cases and endoscopic surgery represents the best choice of treatment for PU.

show abstract

“…Artificial intelligence (AI) has been playing an increasingly important role in the diagnosis, evaluation, and treatment of urolithiasis. In urolithiasis, AI has been applied to the segmentation and classification of stones in imaging studies, prediction of stone clearance after surgery, and optimization of surgical planning and outcomes [ 5 ]. With the continual development of AI technology, it is expected to further improve the accuracy and efficiency of stone disease diagnosis and treatment.…”

mentioning

confidence: 99%