Detection Of Stones Research Articles

UrologiQ: AI-based accurate detection, measurement and reporting of stones in CT-KUB scans.

Kidney stone disease is becoming increasingly common worldwide, with its prevalence increasing annually across all age groups, races, and geographic regions. This sharp increase may be due to significant changes in dietary habits. Early and accurate detection of kidney stones is crucial for timely intervention and prevention of complications. This article discusses the role of artificial intelligence (AI) in detecting kidney stones and managing surgical treatments. Recent advances in AI techniques have introduced new tools that improve the diagnosis and analysis of medical images. AI can use CT-KUB image data to accurately detect the location of kidney stones and measure their size more efficiently than manual methods. AI-based detection methods ensure greater precision and consistency in stone identification and measurement. These improvements can help doctors plan treatments more effectively, resulting in a higher success rate for patients. Integrating AI into kidney stone detection and analysis significantly improves treatment planning and patient management, leading to better patient outcomes and overall quality of healthcare.

Evaluating the effectiveness of AI-powered UrologiQ's in accurately measuring kidney stone volume in urolithiasis patients.

Kidney stones and urolithiasis are kidney diseases that have a significant impact on health and well-being, and their incidence is increasing annually owing to factors such as age, sex, ethnicity, and geographical location. Accurate identification and volume measurement of kidney stones are critical for determining the appropriate surgical approach, as timely and precise treatment is essential to prevent complications and ensure successful outcomes. Larger stones often require more invasive procedures, and precise volume measurements are essential for effective surgical planning and patient outcomes. This study aimed to compare the ability of artificial intelligence (AI) to detect and measure kidney stone volume via CT-KUB images. CT KUB imaging data were analyzed to determine the effectiveness of AI in identifying the volume of kidney stones. The results were compared with measurements taken by radiologists. Compared with radiologists, the AI had greater accuracy, efficiency, and consistency in measuring kidney stone volume. The AI calculates the volume of kidney stones with an average difference of 80% compared with the volumes calculated by radiologists, highlighting a significant discrepancy that is critical for accurate surgical planning. The results suggest that artificial intelligence (AI) outperforms radiologists' manual calculations in measuring kidney stone volume. By integrating AI with kidney stone detection and treatment, there is potential for greater diagnostic precision and treatment effectiveness, which could ultimately improve patient outcomes.

A Review on Kidney Stone Detection using ML and DL Techniques

Kidney stone detection is a critical healthcare challenge, as timely and accurate diagnosis can prevent complications. The motivation behind this review is the increasing prevalence of kidney stones and the need for more effective, non-invasive detection methods. Machine learning (ML) and deep learning (DL) techniques offer promising solutions, leveraging medical imaging data to enhance diagnostic accuracy. However, limitations such as high computational cost and reliance on large datasets hinder their full potential. The aim of this review is to analyze the latest advancements in kidney stone detection using ML and DL techniques. The objective is to compare existing methodologies, highlight their strengths and weaknesses, and suggest future research directions, particularly in integrating transfer learning and fine-tuning techniques to enhance performance.

Kidney Stone Detection based on Improved YOLOv7 with Attention Module and Super Resolution Techniques Under Limited Training Samples

Kidney Stone Detection based on Improved YOLOv7 with Attention Module and Super Resolution Techniques Under Limited Training Samples

Urinary stone assessment in a single-phase may replace the unenhanced and multiphase computed tomography protocol in painless visible haematuria.

Painless visible haematuria (VH) necessitates a computed tomography (CT) usually consisting of one unenhanced and two to three contrast enhanced acquisitions to detect urinary tract stones and malignancy. Recently, we demonstrated that a single nephrographic phase (NP) CT sufficed in detecting malignancy in patients with painless VH. Now, we aim to evaluate the diagnostic performance of single NP CT in stone detection and size measurements in the same cohort. "A Prospective Trial for Examining Haematuria using Computed Tomography" (PROTEHCT) was a single-center prospective diagnostic study in patients with painless VH between September 2019 and June 2021. All underwent four-phase CT (reference standard) from which a single NP CT (experimental) was extracted. Two randomised readers independently assessed the experimental CT for urinary stones and size. Statistical analysis included diagnostic accuracies and inter-reader agreement (kappa) of experimental CT, and size correlation (Spearman's ρ) between experimental CT and reference standard. In 308 included patients (median age: 68 years, 250 males), urinary stones (median size 5 mm) were diagnosed in 21%. The per-patient experimental CT sensitivity was 86% (97% for stones ≥ 5 mm), specificity was 98% and accuracy was 96%. The experimental CT sensitivity for detecting kidney stones was 78% (89% for stones ≥ 5 mm), and 100% for bladder and ureteral stones. No missed stone required active treatment. The inter-reader agreement was almost perfect (96%, k = 0.85). The correlation in stone size was very strong (ρ = 0.91). Conclusions: A single NP CT is sufficient in detecting and measuring urinary stones in patients with painless VH.

The impact of deep learning image reconstruction of spectral CTU virtual non contrast images for patients with renal stones

PurposeTo compare image quality and detection accuracy of renal stones between deep learning image reconstruction (DLIR) and Adaptive Statistical Iterative Reconstruction-Veo (ASIR-V) reconstructed virtual non-contrast (VNC) images and true non-contrast (TNC) images in spectral CT Urography (CTU). MethodsA retrospective analysis was conducted on images of 70 patients who underwent abdominal-pelvic CTU in TNC phase using non-contrast scan and contrast-enhanced corticomedullary phase (CP) and excretory phase (EP) using spectral scan. The TNC scan was reconstructed using ASIR-V70 % (TNC-AR70), contrast-enhanced scans were reconstructed using AR70, DLIR medium-level (DM), and high-level (DH) to obtain CP-VNC-AR70/DM/DH and EP-VNC-AR70/DM/DH image groups, respectively. CT value, image quality and kidney stones quantification accuracy were measured and compared among groups. The subjective evaluation was independently assessed by two senior radiologists using the 5-point Likert scale for image quality and lesion visibility. ResultsDH images were superior to AR70 and DM images in objective image quality evaluation. There was no statistical difference in the liver and spleen (both P > 0.05), or within 6HU in renal and fat in CT value between VNC and TNC images. EP-VNC-DH had the lowest image noise, highest SNR, and CNR, and VNC-AR70 images had better noise and SNR performance than TNC-AR70 images (all p < 0.05). EP-VNC-DH had the highest subjective image quality, and CP-VNC-DH performed the best in lesion visibility. In stone CT value and volume measurements, there was no statistical difference between VNC and TNC (P > 0.05). ConclusionThe DLIR-reconstructed VNC images in CTU provide better image quality than the ASIR-V reconstructed TNC images and similar quantification accuracy for kidney stones for potential dose savings.The study highlights that deep learning image reconstruction (DLIR)-reconstructed virtual non-contrast (VNC) images in spectral CT Urography (CTU) offer improved image quality compared to traditional true non-contrast (TNC) images, while maintaining similar accuracy in kidney stone detection, suggesting potential dose savings in clinical practice.

Comparison of automated kidney stone size measurement and volumetry in photon counting CT compared to 3rd generation dual energy CT and physically measurements - an ex vivo study.

This ex vivo study aimed to compare a newly developed dual-source photon-counting CT (PCCT) with a 3rd generation dual-source dual-energy CT (DECT) for the detection and measurement (stone lengths and volumetrics) of urinary stones. 143 urinary stones with a known geometry were physically measured and defined as reference values. Next, urinary stones were placed in an anthropomorphic abdomen-model and were scanned with DECT and PCCT. Images were read by two experienced examiners and automatically evaluated using a specific software. DECT and PCCT showed a high sensitivity for manual stone detection of 97.9% and 94.4%, and for automatic detection of 93.0% and 87.4%, respectively. Compared to that uric acid and xanthine stones were recognized slightly worse by DECT and PCCT with manual stone detection (93.3% and 82.2%), and with automatic detection (77.8% and 60.0%). All other stone entities were completely recognized. By comparing the maximum diameter of the reference value and DECT, Pearson-correlation was 0.96 (p < 0.001) for manual and 0.97 (p < 0.001) for automatic measurement, and for PCCT it was 0.94 (p < 0.001) for manual and 0.97 (p < 0.001) for automatic measurements. DECT and PCCT can also reliably determine volume manually and automatically with a Pearson-correlation of 0.99 (p < 0.001), respectively. Both CTs showed comparable results in stone detection, length measurement and volumetry compared to the reference values. Automatic measurement tends to underestimate the maximum diameter. DECT proved to be slightly superior in the recognition of xanthine and uric acid stones.

Real-Time Object Detection in Medical Imaging Using YOLO Models for Kidney Stone Detection

Real-Time Object Detection in Medical Imaging Using YOLO Models for Kidney Stone Detection

Deployment of Web-Based YOLO for CT Scan Kidney Stone Detection

This research aims to develop a kidney stone object detection system using machine learning techniques like YOLO and object detection, integrated into a Flask-based web interface to support early diagnosis by medical professionals. The trained model demonstrates strong pattern learning capabilities. Evaluation of the public dataset model reveals an average mean Average Precision (mAP) of 0.9698 for 'kidney stone' labels. This detection model exhibits high performance with an accuracy rate of 96.33%, precision of 96.98%, recall of 99.23%, and an F1-score of 98.1%. Clinical data evaluation shows that the YOLOv5-based detection system performs exceptionally well, with an average mAP of 0.9571, accuracy of 93.06%, precision of 95.71%, recall of 97.1%, and F1-score of 96.49%, indicating the model's capability to detect kidney stones with high precision and accuracy. Thus, both the evaluation on the public dataset and clinical dataset performance support accurate diagnosis processes and further treatment planning. Moreover, this research advances to the stage where the detection model can be directly utilized through implementation via Flask web deployment.

Exploring the potential of combined B-mode features and color Doppler ultrasound in the diagnosis of ureteric stone as an alternative to ionizing radiation exposure by computed tomography.

To assess the diagnostic efficacy of integrating B-mode and color Doppler capabilities of ultrasound (US) to establish a robust standalone diagnostic tool for the diagnosis of ureteric stones as an alternative to non-contrast-enhanced computed tomography (NCCT). A total of 140 consecutive patients diagnosed with ureteric stones using NCCT were enrolled. On the same day, US in both B-mode and Color Doppler was performed by an experienced radiologist who was blinded to the NCCT scan results. The diagnostic rate of US for stone detection was recorded. Additionally, baseline patient and stone characteristics were analyzed for their association with the accuracy of stone detection using US. US exhibited a high sensitivity of 91.43%, detecting 128 out of 140 stone foci. Notably, ureteric stones in the proximal and uretero-vesical junction (UVJ) segments were readily identifiable compared to those in the pelvic region (p = 0.0003). Additionally, hydronephrosis enhanced the US's ability to detect stones (p < 0.0001). Conversely, abdominal gases and obesity adversely affected US capabilities (p < 0.0001 and p = 0.009, respectively). Stone side, size, and density showed no statistically significant impact (p > 0.05). US with its color Doppler capabilities could serve as a reliable and safe alternative imaging modality in the diagnostic work up of patients with ureterolithiasis. Factors including stone location, Hydronephrosis, weight and abdominal gases significantly influenced its accuracy.

Using Machine Learning for Non-Invasive Detection of Kidney Stones Based on Laboratory Test Results: A Case Study from a Saudi Arabian Hospital.

Kidney stone disease is a widespread urological disorder affecting millions globally. Timely diagnosis is crucial to avoid severe complications. Traditionally, renal stones are detected using computed tomography (CT), which, despite its effectiveness, is costly, resource-intensive, exposes patients to unnecessary radiation, and often results in delays due to radiology report wait times. This study presents a novel approach leveraging machine learning to detect renal stones early using routine laboratory test results. We utilized an extensive dataset comprising 2156 patient records from a Saudi Arabian hospital, featuring 15 attributes with challenges such as missing data and class imbalance. We evaluated various machine learning algorithms and imputation methods, including single and multiple imputations, as well as oversampling and undersampling techniques. Our results demonstrate that ensemble tree-based classifiers, specifically random forest (RF) and extra tree classifiers (ETree), outperform others with remarkable accuracy rates of 99%, recall rates of 98%, and F1 scores of 99% for RF, and 92% for ETree. This study underscores the potential of non-invasive, cost-effective laboratory tests for renal stone detection, promoting prompt and improved medical support.

Integrative approach for efficient detection of kidney stones based on improved deep neural network architecture

In today's digital world, with growing population and increasing pollution, unhealthy lifestyle habits like irregular eating, junk food consumption, and lack of exercise are becoming more common, leading to various health problems, including kidney issues. These factors directly affect human kidney health. To address this, we require early detection techniques that rely on text data. Text data contains detailed information about a patient's medical history, symptoms, test results, and treatment plans, giving a complete picture of kidney health and enabling timely intervention. In this research paper, we proposed a range of sophisticated models, such as Gradient Boosting Classifier, Light GBM, CatBoost, Support Vector Classifier (SVC), Random Boost, Logistic Regression, XGBoost, Deep Neural Network (DNN), and an Improved DNN. The Improved DNN demonstrated exceptional performance, with an accuracy of 90 %, precision of 89 %, recall of 90 %, and an F1-Score of 89.5 %. By combining traditional machine learning and deep neural networks, this integrative approach enables the identification of intricate patterns in datasets. The model's data-driven processes consistently update internal parameters, guaranteeing flexibility in response to evolving healthcare settings. This research represents a notable advancement in the progress of creating a more detailed and individualised ability to diagnose kidney stones, which could potentially lead to better clinical results and patient treatment.

Laparoscopic Ultrasound-Guided Transcystic Approach for the Treatment of Common Bile Duct Stones.

Background: The treatment of choledocholithiasis with nondilated common bile duct (CBD) is a challenge for surgeons who often choose endoscopic retrograde cholangiopancreatography with laparoscopic cholecystectomy (LC) staging surgery instead of simultaneous laparoscopic CBD exploration with LC because of the small CBD diameter. This study aims to introduce and assess the clinical applicability of a technique we developed to identify and extract CBD stones using laparoscopic ultrasound (LUS). Methods: We retrospectively reviewed surgical procedures and clinical data of 13 patients who underwent LC and CBD exploration using LUS between May 2022 and August 2023. The cystic duct was used for CBD stone removal. Results: Ten patients were successfully treated; 2 patients with residual stones were treated with ursodeoxycholic acid, whereas 1 patient required a microincision near the CBD and choledochoscopy because of stone incarceration in the duodenal papilla. The CBD diameter was 6 mm (5-9 mm). There were less than three CBD stones, with diameters of 2-6 mm; the median operative time was 105 minutes (range, 52-155 minutes). One patient developed postoperative cholangitis. The median postoperative hospital stay was 6 days (3-8 days). The stone clearance rate was 76.9%, and the CBD stone detection rate was 100%. No intraoperative complications, postoperative bile leakage, and mortality occurred. Conclusions: CBD exploration and transcystic stone extraction under LUS guidance are safe and effective approaches for patients with choledocholithiasis; strict control over surgical indications is necessary. This study could provide new strategies for effectively treating choledocholithiasis.

A Comprehensive Study of Deep Learning Methods for Kidney Tumor, Cyst, and Stone Diagnostics and Detection Using CT Images

A Comprehensive Study of Deep Learning Methods for Kidney Tumor, Cyst, and Stone Diagnostics and Detection Using CT Images

Mask R-CNN-Based Stone Detection and Segmentation for Underground Pipeline Exploration Robots

Stones are one of the primary objects that impede the normal activity of underground pipelines. As human intervention is difficult inside a narrow underground pipe, a robot with a machine vision system is required. In order to remove the stones during regular robotic inspections, precise stone detection, segmentation, and measurement of their distance from the robot are needed. We applied Mask R-CNN to perform an instant segmentation of stones. The distance between the robot and the segmented stones was calculated using spatial information obtained from a lidar camera. Artificial light was used for both image acquisition and testing, as natural light is not available inside the underground pipe. ResNet101 was chosen as the foundation of the Mask R-CNN, and transfer learning was utilized to shorten the training time. The experimental results of our model showed that the average detection precision rate reached 92.0; the recall rate was 90.0%; and the F1 score rate reached 91.0%. The distance values were calculated efficiently with an error margin of 11.36 mm. Moreover, the Mask R-CNN-based stone detection model can detect asymmetrically shaped stones in complex background and lighting conditions.

Can Artificial Intelligence Accurately Detect Urinary Stones? A Systematic Review.

Objectives: To perform a systematic review on artificial intelligence (AI) performances to detect urinary stones. Methods: A PROSPERO-registered (CRD473152) systematic search of Scopus, Web of Science, Embase, and PubMed databases was performed to identify original research articles pertaining to AI stone detection or measurement, using search terms ("automatic" OR "machine learning" OR "convolutional neural network" OR "artificial intelligence" OR "detection" AND "stone volume"). Risk-of-bias (RoB) assessment was performed according to the Cochrane RoB tool, the Joanna Briggs Institute Checklist for nonrandomized studies, and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: Twelve studies were selected for the final review, including three multicenter and nine single-center retrospective studies. Eleven studies completed at least 50% of the CLAIM checkpoints and only one presented a high RoB. All included studies aimed to detect kidney (5/12, 42%), ureter (2/12, 16%), or urinary (5/12, 42%) stones on noncontrast computed tomography (NCCT), but 42% intended to automate measurement. Stone distinction from vascular calcification interested two studies. All studies used AI machine learning network training and internal validation, but a single one provided an external validation. Trained networks achieved stone detection, with sensitivity, specificity, and accuracy rates ranging from 58.7% to 100%, 68.5% to 100%, and 63% to 99.95%, respectively. Detection Dice score ranged from 83% to 97%. A high correlation between manual and automated stone volume (r = 0.95) was noted. Differentiate distal ureteral stones and phleboliths seemed feasible. Conclusions: AI processes can achieve automated urinary stone detection from NCCT. Further studies should provide urinary stone detection coupled with phlebolith distinction and an external validation, and include anatomical abnormalities and urologic foreign bodies (ureteral stent and nephrostomy tubes) cases.

The Detection of Pulp Stones with Automatic Deep Learning in Panoramic Radiographies: An AI Pilot Study.

This study aims to evaluate the effectiveness of employing a deep learning approach for the automated detection of pulp stones in panoramic imaging. A comprehensive dataset comprising 2409 panoramic radiography images (7564 labels) underwent labeling using the CranioCatch labeling program, developed in Eskişehir, Turkey. The dataset was stratified into three distinct subsets: training (n = 1929, 80% of the total), validation (n = 240, 10% of the total), and test (n = 240, 10% of the total) sets. To optimize the visual clarity of labeled regions, a 3 × 3 clash operation was applied to the images. The YOLOv5 architecture was employed for artificial intelligence modeling, yielding F1, sensitivity, and precision metrics of 0.7892, 0.8026, and 0.7762, respectively, during the evaluation of the test dataset. Among deep learning-based artificial intelligence algorithms applied to panoramic radiographs, the use of numerical identification for the detection of pulp stones has achieved remarkable success. It is expected that the success rates of training models will increase by using datasets consisting of a larger number of images. The use of artificial intelligence-supported clinical decision support system software has the potential to increase the efficiency and effectiveness of dentists.

Comparison of Endoscopic Ultrasound and Transabdominal Ultrasound in the Detection of Gallbladder and Common Bile Duct Microlithiasis.

Endoscopic ultrasonography (EUS) is an emerging method with a wide range of potential uses in gastroenterology, including the detection of bile duct stones and the identification of early ductal alterations in suspected patients. This study was designed to compare the diagnostic yield of EUS and transabdominal ultrasound (TUS) in the detection of gallbladder and common bile duct (CBD) microlithiasis. Patients with biliary colic with normal initial TUS were the subjects of this prospective study. EUS scan was performed on all recruited patients and linear endoscopes were used for the EUS examination. Cholecystectomy and histological analysis were done in patients within two weeks after EUS revealing cholelithiasis whereas the cases of CBD stone/microlithiasis were confirmed by endoscopic retrograde cholangiopancreatography (ERCP). The mean values of all hematological characteristics were independently determined for males and females and then compared using Student's t-test. For statistical significance, a p-value of 0.05 or below was used. A total of 131 patients, including 77 females and 54 males, with a mean age of 38.41 ± 14.78 years were examined. All 78 (59.5%) individuals who had cholecystectomy were found to have gallstones or microlithiasis as successfully diagnosed by EUS. The sensitivity and specificity of EUS were 92.9% and 100%, respectively, for CBD stones and 98.8% and 100%, respectively, for the detection of gallbladder microlithiasis. The agreement between EUS and TUS was fair for CBD stones (κ = 0.214) and very weak for microlithiasis (κ = -0.093). EUSdemonstrates a superior yield over TUSin detecting gallbladder stones and CBD microlithiasis, offering a more reliable diagnostic modality. This was a single-center study.

Detection of residual stones by peroral direct cholangioscopy in patients with intrahepatic stones after hepaticojejunostomy: a prospective study (with video)

Background and AimsThe difficulty of radiographic confirmation of the presence of stones remains a challenge in the treatment of intrahepatic bile duct (IHBD) stones in patients after hepaticojejunostomy (HJ). Peroral direct cholangioscopy (PDCS) enables direct observation of the bile duct and is useful for detecting and removing residual stones; however, its effectiveness is not clearly established in this clinical context. MethodsThis single-center, single-arm, prospective study included 44 patients with IHBD who underwent bowel reconstruction with HJ during the study period. Stone removal was performed by short-type double-balloon enteroscopy (DBE). Following balloon-occluded cholangiography, the DBE was exchanged for an ultraslim endoscope through the balloon overtube for PDCS. The primary endpoint was the rate of residual stones detected by PDCS. Secondary endpoints were success rate of PDCS, residual stone removal with PDCS, procedure time for PDCS, procedure-related adverse events, and stone recurrence rate. ResultsPDCS was successful in 39/44 patients (89%), among whom residual stones were detected in 16 (41%) (95% CI: 28%–54%). Twelve patients (75%) had residual stones <5 mm. Stone removal was successful in 15 (94%) patients and median procedure time for PDCS was 16 (IQR: 10–26) min. The rate of procedure-related adverse events was 7% (3/44), all of which improved with conservative treatment. During median follow-up of 2.1 years (IQR: 1.4–3.3), the overall probability of recurrence-free status at 1, 2, and 3 years was 100%, 92%, and 86%, respectively. ConclusionsPDCS is a safe and effective procedure for complete stone removal in patients with IHBD stones after HJ.

B-Mode Sonography Versus Color Doppler Twinkling Artifact in the Diagnosis of Nephrolithiasis

Background: Nephrolithiasis, or kidney stones, is a prevalent condition that prompts numerous patient visits to emergency departments worldwide. The diagnosis of this condition and its complications, such as hydronephrosis, has traditionally relied on various imaging modalities, with ultrasound being a primary, non-invasive option. Recent advancements, including the utilization of the color Doppler twinkling artifact, have potentially enhanced the diagnostic capabilities of ultrasound for nephrolithiasis. Objective: This study aims to evaluate the effectiveness of B-mode sonography and the color Doppler twinkling artifact in the diagnosis of nephrolithiasis and to compare their sensitivity in detecting renal stones and associated hydronephrosis. Methods: A cross-sectional study was conducted at the Department of Radiology, Mahaban Medical and Research Hospital, Topi, Pakistan, from December 2023 to March 2024. Seventy patients presenting with flank pain and aged above 18 years were enrolled. Sonographic examinations were performed using a TOSHIBA Xario Prime ultrasound machine. Data were analyzed using SPSS version 25.0, focusing on the presence of renal stones and hydronephrosis as detected by B-mode sonography and the color Doppler twinkling artifact. Results: Of the 70 patients studied, renal stones were detected in 70% (n=49) via the color Doppler twinkling artifact, while 30% (n=21) showed no stones. Hydronephrosis was observed in 30% (n=21) of patients, with an equal distribution between the left and right kidneys. The mean age of participants was 34.56 years, with a gender distribution of 62.9% male and 37.1% female. The twinkling artifact demonstrated a 100% sensitivity in identifying renal calculi among patients presenting with flank pain. Conclusion: The color Doppler twinkling artifact, when used alongside B-mode sonography, provides a highly sensitive diagnostic tool for nephrolithiasis, underscoring its potential as a primary imaging modality in the evaluation of patients with suspected renal stones. This study highlights the importance of ultrasound in the early detection and management of kidney stones, offering significant implications for improving patient care in healthcare settings lacking advanced imaging technologies.