Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach: refining parameters on an expanded dataset

Transforming urinary stone disease management by artificial intelligence-based methods: A comprehensive review

Objective

To provide a comprehensive review on the existing research and evidence regarding artificial intelligence (AI) applications in the assessment and management of urinary stone disease.

Methods

A comprehensive literature review was performed using PubMed, Scopus, and Google Scholar databases to identify publications about innovative concepts or supporting applications of AI in the improvement of every medical procedure relating to stone disease. The terms ''endourology'', ''artificial intelligence'', ''machine learning'', and ''urolithiasis'' were used for searching eligible reports, while review articles, articles referring to automated procedures without AI application, and editorial comments were excluded from the final set of publications. The search was conducted from January 2000 to September 2023 and included manuscripts in the English language.

Results

A total of 69 studies were identified. The main subjects were related to the detection of urinary stones, the prediction of the outcome of conservative or operative management, the optimization of operative procedures, and the elucidation of the relation of urinary stone chemistry with various factors.

Conclusion

AI represents a useful tool that provides urologists with numerous amenities, which explains the fact that it has gained ground in the pursuit of stone disease management perfection. The effectiveness of diagnosis and therapy can be increased by using it as an alternative or adjunct to the already existing data. However, little is known concerning the potential of this vast field. Electronic patient records, containing big data, offer AI the opportunity to develop and analyze more precise and efficient diagnostic and treatment algorithms. Nevertheless, the existing applications are not generalizable in real-life practice, and high-quality studies are needed to establish the integration of AI in the management of urinary stone disease.

Dual-energy Computed Tomographic Pulmonary Angiography Accurately Estimates Lobar Perfusion Before Lung Volume Reduction for Severe Emphysema

PURPOSE

To assess if dual-energy computed tomographic pulmonary angiography (DECTPA) derived lobar iodine quantification can provide an accurate estimate of lobar perfusion in patients with severe emphysema, and offer an adjunct to single-photon emission CT perfusion scintigraphy (SPECT-PS) in assessing suitability for lung volume reduction (LVR).

MATERIALS AND METHODS

Patients with severe emphysema (forced expiratory volume in 1 s <49% predicted) undergoing evaluation for LVR between May 2018 and April 2020 imaged with both SPECT-PS and DECTPA were included in this retrospective study. DECTPA perfused blood volume maps were automatically segmented and lobar iodine mass was estimated and compared with lobar technetium (Tc99m) distribution acquired with SPECT-PS. Pearson correlation and Bland-Altman analysis were used for intermodality comparison between DECTPA and SPECT-PS. Univariate and adjusted multivariate linear regression were modelled to ascertain the effect sizes of possible confounders of disease severity, sex, age, and body mass index on the relationship between lobar iodine and Tc99m values. Effective radiation dose and adverse reactions were recorded.

RESULTS

In all, 123 patients (64.5±8.8 y, 71 men; mean predicted forced expiratory volume in 1 s 32.1 ±12.7%,) were eligible for inclusion. There was a linear relationship between lobar perfusion values acquired using DECTPA and SPECT-PS with statistical significance ( P <0.001). Lobar relative perfusion values acquired using DECTPA and SPECT-PS had a consistent relationship both by linear regression and Bland-Altman analysis (mean bias, -0.01, mean r2 0.64; P <0.0001). Individual lobar comparisons demonstrated moderate correlation ( r =0.79, 0.78, 0.84, 0.78, 0.8 for the right upper, middle, lower, left upper, and lower lobes, respectively, P <0.0001). The relationship between lobar iodine and Tc99m values was not significantly altered after controlling for confounders including symptom and disease severity, age, sex, and body mass index.

CONCLUSIONS

DECTPA provides an accurate estimation of lobar perfusion, showing good agreement with SPECT-PS and could potentially streamline preoperative assessment for LVR.

Clinical Applications of Machine Learning for Urolithiasis and Benign Prostatic Hyperplasia: A Systematic Review

INTRODUCTION

Previous systematic reviews related to machine learning (ML) in urology often overlooked the literature related to endourology. Therefore, we aim to conduct a more focused systematic review examining the use of ML algorithms for benign prostatic hyperplasia (BPH) or urolithiasis. In addition, we are the first group to evaluate these articles using the STREAM-URO framework.

METHODS

Searches of MEDLINE, Embase, and the Cochrane CENTRAL databases were conducted from inception through July 12, 2021. Keywords included those related to ML, endourology, urolithiasis, and BPH. Two reviewers screened the citations that were eligible for title, abstract and full-text screening, with conflicts resolved by a third reviewer. Two reviewers extracted information from the studies, with discrepancies resolved by a third reviewer. The data collected was then qualitatively synthesized by consensus. Two reviewers evaluated each article according to the STREAM-URO checklist with discrepancies resolved by a third reviewer.

RESULTS

After identifying 459 unique citations, 63 articles were retained for data extraction. Most articles consisted of tabular (n=32) and computer vision (n=23) tasks. The two most common problem types were classification (n=40) and regression (n=12). In general, most studies utilized neural networks as their ML algorithm (n=36). Among the 63 studies retrieved, 58 were related to urolithiasis and five focused on BPH. The urolithiasis studies were designed for outcome prediction (n=20), stone classification (n=18), diagnostics (n=17), and therapeutics (n=3). The BPH studies were designed for outcome prediction (n=2), diagnostics (n=2), and therapeutics (n=1). On average, the urolithiasis and BPH articles met 13.8 (SD 2.6), and 13.4 (4.1) of the 26 STREAM-URO framework criteria, respectively.

CONCLUSIONS

The majority of the retrieved studies successfully helped with outcome prediction, diagnostics, and therapeutics for both urolithiasis and BPH. While ML shows great promise in improving patient care, it is important to adhere to the recently developed STREAM-URO framework to ensure the development of high-quality ML studies.

The use and applicability of machine learning algorithms in predicting the surgical outcome for patients with benign prostatic enlargement. Which model to use?

OBJECTIVES

Artificial intelligence (AI) is increasingly used in medicine, but data on benign prostatic enlargement (BPE) management are lacking. This study aims to test the performance of several machine learning algorithms, in predicting clinical outcomes during BPE surgical management.

METHODS

Clinical data were extracted from a prospectively collected database for 153 men with BPE, treated with transurethral resection (monopolar or bipolar) or vaporization of the prostate. Due to small sample size, we applied a method for increasing our dataset, Synthetic Minority Oversampling Technique (SMOTE). The new dataset created with SMOTE has been expanded by 453 synthetic instances, in addition to the original 153. The WEKA Data Mining Software was used for constructing predictive models, while several appropriate statistical measures, like Correlation coefficient (R), Mean Absolute Error (MAE), Root Mean-Squared Error (RMSE), were calculated with several supervised regression algorithms - techniques (Linear Regression, Multilayer Perceptron, SMOreg, k-Nearest Neighbors, Bagging, M5Rules, M5P - Pruned Model Tree, and Random forest).

RESULTS

The baseline characteristics of patients were extracted, with age, prostate volume, method of operation, baseline Qmax and baseline IPSS being used as independent variables. Using the Random Forest algorithm resulted in values of R, MAE, RMSE that indicate the ability of these models to better predict % Qmax increase. The Random Forest model also demonstrated the best results in R, MAE, RMSE for predicting % IPSS reduction.

CONCLUSIONS

Machine Learning techniques can be used for making predictions regarding clinical outcomes of surgical BPRE management. Wider-scale validation studies are necessary to strengthen our results in choosing the best model.

Value of artificial intelligence model based on unenhanced computed tomography of urinary tract for preoperative prediction of calcium oxalate monohydrate stones in vivo

Background

Urolithiasis is a global disease with a high incidence and recurrence rate, and stone composition is closely related to the choice of treatment and preventive measures. Calcium oxalate monohydrate (COM) is the most common in clinical practice, which is hard and difficult to fragment. Preoperative identification of its components and selection of effective surgical methods can reduce the risk of patients having a second operation. Methods that can be used for stone composition analysis include infrared spectroscopy, X-ray diffraction, and polarized light microscopy, but they are all performed on stone specimens in vitro after surgery. This study aimed to design and develop an artificial intelligence (AI) model based on unenhanced computed tomography (CT) images of the urinary tract, and to investigate the predictive ability of the model for COM stones in vivo preoperatively, so as to provide surgeons with more accurate diagnostic information.

Methods

Preoperative unenhanced CT images of patients with urinary calculi whose components were determined by infrared spectroscopy in a single center were retrospectively analyzed, including 337 cases of COM stones and 170 of non-COM stones. All images were manually segmented and the image features were extracted, and randomly divided into the training and testing sets in a ratio of 7:3. The least absolute shrinkage and selection operation algorithm (LASSO) was used to construct the AI model, and classification of the training and testing sets was carried out.

Results

A total of 1,218 radiomics imaging features were extracted, and 8 features with non-zero coefficients were finally obtained. The sensitivity, specificity and accuracy of the AI model were 90.5%, 84.3% and 88.5% for the training set, and 90.1%, 84.3% and 88.3% for the testing set. The area under the curve was 0.935 for the training set and 0.933 for the testing set.

Conclusions

The AI model based on unenhanced CT images of the urinary tract can predict COM and non-COM stones in vivo preoperatively, and the model has high sensitivity, specificity and accuracy.

Innovations in urolithiasis management

PURPOSE OF REVIEW

This review provides a forecast about ongoing developments in the management of urolithiasis with a potential to challenge the current standard of care. We therefore emphasized innovative technology, which might be considered still experimental in the daily clinic or needs further clinical validation, but harbors the great potential to become a game changer for future stone management.

RECENT FINDINGS

Especially in the endoscopic stone treatment, we observed a multitude of groundbreaking technical innovations, which changed our treatment algorithms over the last decades. Some of this technology already found its way into daily practice. Others like artificial intelligence, burst wave lithotripsy, smart laser systems or gene therapy may not be standardized yet, but have the potential to further revolutionize current practice. Besides those technical features, we included innovations in prevention and diagnostics, as well as patient expectations and patient satisfaction into the analysis. A proper metaphylaxis and patient communication seems to be essential for a long-lasting treatment success.

SUMMARY

The combination of technical innovations, improved stone metaphylaxis and proper patient communication presents the cornerstone of future kidney stone management.

Precision Medicine, Artificial Intelligence, and Genomic Markers in Urology. Do we need to Tailor our Clinical Practice?

Precision medicine plays a key role in urological oncology practice nowadays, with the breakthrough of the poly (ADP-ribose) polymerase inhibitors (PARPi), which play a critical role in different DNA damage repair (DDR) pathways, the immune checkpoint inhibitors, the genomic expression profiles and current genome manipulation-directed targeted therapy. Information and technology (IT) are set to change the way we assess and treat patients and should be reviewed and discussed. The aim of the present article is to demonstrate a detailed revision on precision medicine, including novel therapeutic targets, genomic markers, genomic stratification of urological patients, and the top-notch technological breakthroughs that could change our clinical practice

We performed a review of the literature in four different databases (PubMed, Embase, Lilacs, and Scielo) on any information concerning prostate, bladder, kidney and urothelial cancer novel treatments with PARPi, immune checkpoint inhibitors (ICIs), targeted therapy with fibroblast growth factor receptor inhibitors (FGFRi), and theranostics with prostate-specific membrane antigen (PSMA) targeted monoclonal antibodies. Artificial intelligence, machine learning, and deep learning algorithm in urological practice were also part of the search. We included all articles written in English, published within the past 7 years, that discussed outstanding therapies and genomics in urological cancer and artificial intelligence applied to urology. Meanwhile, we excluded articles with lack of a clear methodology and written in any other language than English.

One-hundred and twenty-six articles of interest were found; of these, 65 articles that presented novel treatments of urological neoplasms, discussed precision medicine, genomic expression profiles and biomarkers in urology, and latest deep learning and machine learning algorithms as well as the use of artificial intelligence in urological practice were selected. A critical review of the literature is presented in the present article.

Urology is a constantly changing specialty with a wide range of therapeutic breakthroughs, a huge understanding of the genomic expression profiles for each urological cancer and a tendency to use cutting-edge technology to treat our patients. All of these major developments must be analyzed objectively, taking into account costs to the health systems, risks and benefits to the patients, and the legal background that comes with them. A critical analysis of these new technologies and pharmacological breakthroughs should be made before considering changing our clinical practice. Nowadays, research needs to be strengthened to help us improve results in assessing and treating our patients.

Efficacy of single-source rapid kV-switching dual-energy CT for characterization of non-uric acid renal stones: a prospective ex vivo study using anthropomorphic phantom

PURPOSE

To investigate the accuracy of rapid kV-switching single-source dual-energy computed tomography (rsDECT) for prediction of classes of non-uric-acid stones.

MATERIALS AND METHODS

Non-uric-acid renal stones retrieved via percutaneous nephrolithotomy were prospectively collected between January 2017 and February 2018 in a single institution. Only stones ≥ 5 mm and with pure composition (i.e., ≥ 80% composed of one component) were included. Stone composition was determined using Fourier Transform Infrared Spectroscopy. The stones were scanned in 32-cm-wide anthropomorphic whole-body phantom using rsDECT. The effective atomic number (Zeff), the attenuation at 40 keV (HU40), 70 keV (HU70), and 140 keV (HU140) virtual monochromatic sets of images as well as the ratios between the attenuations were calculated. Values of stone classes were compared using ANOVA and Mann-Whitney U test. Receiver operating curves and area under curve (AUC) were calculated. A p value < 0.05 was considered statistically significant.

RESULTS

The final study sample included 31 stones from 31 patients consisting of 25 (81%) calcium-based, 4 (13%) cystine, and 2 (6%) struvite pure stones. The mean size of the stones was 9.9 ± 2.4 mm. The mean Zeff of the stones was 12.01 ± 0.54 for calcium-based, 11.10 ± 0.68 for struvite, and 10.23 ± 0.75 for cystine stones (p < 0.001). Zeff had the best efficacy to separate different classes of stones. The calculated AUC was 0.947 for Zeff; 0.833 for HU40; 0.880 for HU70; and 0.893 for HU140.

CONCLUSION

Zeff derived from rsDECT has superior performance to HU and attenuation ratios for separation of different classes of non-uric-acid stones.

Dose independent characterization of renal stones by means of dual energy computed tomography and machine learning: an ex-vivo study

OBJECTIVES

To predict the main component of pure and mixed kidney stones using dual-energy computed tomography and machine learning.

METHODS

200 kidney stones with a known composition as determined by infrared spectroscopy were examined using a non-anthropomorphic phantom on a spectral detector computed tomography scanner. Stones were of either pure (monocrystalline, n = 116) or compound (dicrystalline, n = 84) composition. Image acquisition was repeated twice using both, normal and low-dose protocols, respectively (ND/LD). Conventional images and low and high keV virtual monoenergetic images were reconstructed. Stones were semi-automatically segmented. A shallow neural network was trained using data from ND1 acquisition split into training (70%), testing (15%) and validation-datasets (15%). Performance for ND2 and both LD acquisitions was tested. Accuracy on a per-voxel and a per-stone basis was calculated.

RESULTS

Main components were: Whewellite (n = 80), weddellite (n = 21), Ca-phosphate (n = 39), cysteine (n = 20), struvite (n = 13), uric acid (n = 18) and xanthine stones (n = 9). Stone size ranged from 3 to 18 mm. Overall accuracy for predicting the main component on a per-voxel basis attained by ND testing dataset was 91.1%. On independently tested acquisitions, accuracy was 87.1-90.4%.

CONCLUSIONS

Even in compound stones, the main component can be reliably determined using dual energy CT and machine learning, irrespective of dose protocol.

KEY POINTS

• Spectral Detector Dual Energy CT and Machine Learning allow for an accurate prediction of stone composition. • Ex-vivo study demonstrates the dose independent assessment of pure and compound stones. • Lowest accuracy is reported for compound stones with struvite as main component.

How to compete with Google and Co.: big data and artificial intelligence in stones

PURPOSE OF REVIEW

To elucidate the keywords big data and artificial intelligence and corresponding literature in the field of urolithiasis.

RECENT FINDINGS

Numbers of publications on big data and artificial intelligence in the field of urolithiasis are rising, but still low. Most publications describe the development, testing, and validation of automated computational analyses of clinical data sets and/or images in a preclinical setting.

SUMMARY

In the field of digital health services, there is a discrepancy between the enormous commitment of large private companies and investments of public funds. This situation means a still small number of medical publications on this topic in the urolithiasis field. Nevertheless, as doctors and scientists, we should try to provide our patients with secure and worthwhile digital services.