Kidney Stone Detection Research Articles

Modified Distance Regularized Level Set Segmentation Based Analysis for Kidney Stone Detection

The abnormalities of the kidney can be identified by ultrasound imaging. The kidney may have structural abnormalities like kidney swelling, change in its position and appearance. Kidney abnormality may also arise due to the formation of stones, cysts, cancerous cells, congenital anomalies, blockage of urine etc. For surgical operations it is very important to identify the exact and accurate location of stone in the kidney. The ultrasound images are of low contrast and contain speckle noise. This makes the detection of kidney abnormalities rather challenging task. Thus preprocessing of ultrasound images is carried out to remove speckle noise. In preprocessing, first image restoration is done to reduce speckle noise then it is applied to Gabor filter for smoothening. Next the resultant image is enhanced using histogram equalization. The preprocessed ultrasound image is segmented using distance regularized level set segmentation (DR-LSS), since it yields better results. It uses a two-step splitting methods to iteratively solve the DR-LSS equation, first step is iterating LSS equation, and then solving the Sign distance equation. The second step is to regularize the level set function which is the obtained from first step for better stability. The DR is included for LSS for eliminating of anti-leakages on image boundary. The DR-LSS does not require any expensive re-initialization and it is very high speed of operation. The RD-LSS results are compared with distance regularized level set evolution DRLSE1, DRLSE2 and DRLSE3. Extracted region of the kidney after segmentation is applied to Symlets (Sym12), Biorthogonal (bio3.7, bio3.9 & bio4.4) and Daubechies (Db12) lifting scheme wavelet subbands to extract energy levels. These energy level gives an indication about presence of stone in that particular location which significantly vary from that of normal energy level. These energy levels are trained by Multilayer Perceptron (MLP) and Back Propagation (BP) ANN to identify the type of stone with an accuracy of 98.6%.

Analysis and Implementation of Kidney Stone Detection by Reaction Diffusion Level Set Segmentation Using Xilinx System Generator on FPGA

Ultrasound imaging is one of the available imaging techniques used for diagnosis of kidney abnormalities, which may be like change in shape and position and swelling of limb; there are also other Kidney abnormalities such as formation of stones, cysts, blockage of urine, congenital anomalies, and cancerous cells. During surgical processes it is vital to recognize the true and precise location of kidney stone. The detection of kidney stones using ultrasound imaging is a highly challenging task as they are of low contrast and contain speckle noise. This challenge is overcome by employing suitable image processing techniques. The ultrasound image is first preprocessed to get rid of speckle noise using the image restoration process. The restored image is smoothened using Gabor filter and the subsequent image is enhanced by histogram equalization. The preprocessed image is achieved with level set segmentation to detect the stone region. Segmentation process is employed twice for getting better results; first to segment kidney portion and then to segment the stone portion, respectively. In this work, the level set segmentation uses two terms, namely, momentum and resilient propagation (Rprop) to detect the stone portion. After segmentation, the extracted region of the kidney stone is given to Symlets, Biorthogonal (bio3.7, bio3.9, and bio4.4), and Daubechies lifting scheme wavelet subbands to extract energy levels. These energy levels provide evidence about presence of stone, by comparing them with that of the normal energy levels. They are trained by multilayer perceptron (MLP) and back propagation (BP) ANN to classify and its type of stone with an accuracy of 98.8%. The prosed work is designed and real time is implemented on both Filed Programmable Gate Array Vertex-2Pro FPGA using Xilinx System Generator (XSG) Verilog and Matlab 2012a.

MP38-06 ULTRA LOW DOSE CT-KUB TO DETECT KIDNEY STONES WITH 44% LESS RADIATION: IS THE PLAIN RADIOGRAPH OBSOLETE?

You have accessJournal of UrologyStone Disease: Surgical Therapy IV1 Apr 2015MP38-06 ULTRA LOW DOSE CT-KUB TO DETECT KIDNEY STONES WITH 44% LESS RADIATION: IS THE PLAIN RADIOGRAPH OBSOLETE? Ben H. Chew, Patrick McLaughlin, Ryan F. Paterson, Elspeth M. McDougall, James Nugent, Allen V. Rowley, Jean Buckley, and Charles Zwirewich Ben H. ChewBen H. Chew More articles by this author , Patrick McLaughlinPatrick McLaughlin More articles by this author , Ryan F. PatersonRyan F. Paterson More articles by this author , Elspeth M. McDougallElspeth M. McDougall More articles by this author , James NugentJames Nugent More articles by this author , Allen V. RowleyAllen V. Rowley More articles by this author , Jean BuckleyJean Buckley More articles by this author , and Charles ZwirewichCharles Zwirewich More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2015.02.1381AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES At our institution, Kidney-Ureter-Bladder (KUB) radiographs are performed immediately prior to shockwave lithotripsy (SWL). Conventional low dose CT-KUBs (radiation effective dose of 2.2-3.0 mSv) are only performed if stones are not visible on KUB. Recent advances in CT detector design and image reconstruction algorithms have made sub-milliSievert ultra-low dose CT (ULDCT) acquisition feasible, but the diagnostic performance of these exams has not yet been reported. We sought to compare the radiation dose and diagnostic performance of ULDCT to KUB in patients prior to SWL. We hypothesized that ULDCT would provide at least the same amount of information as a KUB immediately prior to SWL. METHODS Patients enrolled in this study consented and received both a KUB radiograph and an ULDCT prior to SWL. If no stones were identified, then a standard low dose abdominal CT was obtained. Radiation exposure parameters were recorded and both examinations were read in random order by blinded radiologists to determine the correlation between the two modalities. RESULTS 51 patients (M:F, 34:17) with a mean age of 56.2 ± 13.8y were enrolled. The effective radiation dose was significantly lower with ULDCT (0.28 ±0.10 mSv) compared to KUB (0.50±0.10 mSv, p=0.014). The number of stones seen on both modalities was equivalent: KUB was 1.59±1.27 vs 1.92±01.51 for ULDCT (p=0.35). Measurement of stone size was equivalent using ULDCT (6.47±3.34mm) compared to KUB (6.98±3.41mm, p=0.455). In 3 cases (5.9%), the ULDCT helped localize ureteral stones that were not visible on KUB. ULDCT altered treatment priority of treating the ureteral stones first. CONCLUSIONS Sub-milliSievert ULDCT delivers 44% less radiation than a plain KUB radiograph and was equivalent in detecting the number and size of stones. In 5.9% of cases, CT localized stones prior to SWL better than KUB. In future, ULDCT may replace KUB as it delivers less radiation with potentially more information immediately prior to SWL. Validation of this technology in the acute care setting in the Emergency Room will be necessary. © 2015 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 193Issue 4SApril 2015Page: e448 Advertisement Copyright & Permissions© 2015 by American Urological Association Education and Research, Inc.MetricsAuthor Information Ben H. Chew More articles by this author Patrick McLaughlin More articles by this author Ryan F. Paterson More articles by this author Elspeth M. McDougall More articles by this author James Nugent More articles by this author Allen V. Rowley More articles by this author Jean Buckley More articles by this author Charles Zwirewich More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...

Image Quality Improvement in Kidney Stone Detection on Computed Tomography Images

Image Quality Improvement in Kidney Stone Detection on Computed Tomography Images

VLSI Implementation and Analysis of Kidney Stone Detection by Level Set Segmentation and ANN Classification

Abstract The abnormalities of the kidney can be identified by ultrasound imaging. The kidney may have structural abnormalities like kidney swelling, change in its position and appearance. Kidney abnormality may also arise due to the formation of stones, cysts, cancerous cells, congenital anomalies, blockage of urine etc. For surgical operations it is very important to identify the exact and accurate location of stone in the kidney. The ultrasound images are of low contrast and contain speckle noise. This makes the detection of kidney abnormalities rather challenging task. Thus preprocessing of ultrasound images is carried out to remove speckle noise. In preprocessing, first image restoration is done to reduce speckle noise then it is applied to Gabor filter for smoothening. Next the resultant image is enhanced using histogram equalization. Level set segmentation is applied two times, first to segment kidney portion and its output is the input to second to segment stone portion, since it yields better results. In level set segmentation two terms are used in our work. First is using a momentum term and second is based on resilient propagation (R prop ). Extracted region of the kidney stone after segmentation is applied to Symlets, Biorthogonal (bio3.7, bio3.9 & bio4.4) and Daubechies lifting scheme wavelet subbands to extract energy levels. These energy level gives an indication about presence of stone, which significantly vary from that of normal energy level. These energy levels are trained by Multilayer Perceptron (MLP) and Back Propagation (BP) ANN to identify the type of stone with an accuracy of 98.8% and real time implementation is done using Verilog on Vertex-2Pro FPGA.

Commentary on Silent Renal Stones in Primary Hyperparathyroidism: Prevalence and Clinical Features

Commentary on Silent Renal Stones in Primary Hyperparathyroidism: Prevalence and Clinical Features

Stones: ultrasonography and computed tomography: performance in detection of kidney stones.

Stones: ultrasonography and computed tomography: performance in detection of kidney stones.

Improved Detection of Kidney Stones Using an Optimized Doppler Imaging Sequence.

Kidney stones have been shown to exhibit a "twinkling artifact" (TA) under Color-Doppler ultrasound. Although this technique has better specificity than conventional Bmode imaging, it has lower sensitivity. To improve the overall performance of using TA as a diagnostic tool, Doppler output parameters were optimized in-vitro. The collected data supports a previous hypothesis that TA is caused by random oscillations of micron sized bubbles trapped in the cracks and crevices of kidney stones. A set of optimized parameters were implemented such that that the MI & TI remained within the FDA approved limits. Several clinical kidney scans were performed with the optimized settings and were able to detect stones with improved SNR relative to the default settings.

Homozygous and compound heterozygous mutations in the ATP6V1B1 gene in patients with renal tubular acidosis and sensorineural hearing loss

Distal renal tubular acidosis (dRTA) is characterized by the inability to excrete acid in the renal collecting ducts resulting in inappropriately alkaline urine and hyperchloremic (normal anion gap) metabolic acidosis in the context of a normal (or near-normal) glomerular filtration rate. Inborn dRTA can be due to autosomal dominant or recessive gene defects. Clinical symptoms vary from mild acidosis, incidental detection of kidney stones or renal tract calcification to severe findings such as failure to thrive, severe metabolic acidosis, and nephrocalcinosis. The majority of patients with recessive dRTA present with sensorineural hearing loss (SNHL). Few cases with abnormal widening of the vestibular aqueduct have been described with dRTA. Mutations in three different genes have been identified, namely SLC4A1, ATP6V1B1, and ATP6V0A4. Patients with mutations in the ATP6V1B1 proton pump subunit develop dRTA and in most of the cases sensorineural hearing loss early in childhood. We present two patients from two different and non-consanguineous families with dRTA and SNHL. Direct sequencing of the ATP6V1B1 gene revealed that one patient harbors two homozygous mutations and the other one is a compound heterozygous. To our knowledge, this is the first case in the literature describing homozygosity in the same dRTA gene on both alleles.

B-mode Ultrasound Versus Color Doppler Twinkling Artifact in Detecting Kidney Stones

To compare color Doppler twinkling artifact and B-mode ultrasonography in detecting kidney stones. Nine patients with recent CT scans prospectively underwent B-mode and twinkling artifact color Doppler ultrasonography on a commercial ultrasound machine. Video segments of the upper pole, interpolar area, and lower pole were created, randomized, and independently reviewed by three radiologists. Receiver operator characteristics were determined. There were 32 stones in 18 kidneys with a mean stone size of 8.9±7.5 mm. B-mode ultrasonography had 71% sensitivity, 48% specificity, 52% positive predictive value, and 68% negative predictive value, while twinkling artifact Doppler ultrasonography had 56% sensitivity, 74% specificity, 62% positive predictive value, and 68% negative predictive value. When used alone, B-mode is more sensitive, but twinkling artifact is more specific in detecting kidney stones. This information may help users employ twinkling and B-mode to identify stones and developers to improve signal processing to harness the fundamental acoustic differences to ultimately improve stone detection.

Low Power VLSI based Design and Implementation of MLP-BP Neural Network for Detection of Kidney Stone in Real Time

In recent years one of the most common problems that occur in the human urinary system is kidney stones or urinary stones. There are many Methods of medical imaging that can be used to examine parameters of human kidneys, for example magnetic resonance imaging (MRI), x-ray computed tomography (CT), ultrasound imaging (US), and many others. This detection is very important for the doctor to determine the status of the kidneys and also to visualize any abnormalities present in the kidney [2]. Any person affected with a problem in kidney suffers with a pain in early stage. The detection of abnormalities of kidney inside the body is a main field of study in medical research by bio-medical image processing[1-4], Due to some abnormalities (speckle noise) in ultrasound or MRI images and artifacts, wrong diagnosis may happen by analyzing the scanned image. Therefore in this work the main focus is on development of new hardware implementation based on neural network architecture for detection of kidney stone in real time by optimizing area, power and speed on FPGA [5]. This algorithm implemented on Vertex-II Pro FPGA device and simulated in matlab [9].

Autoregressive ultrasound imaging method to enhance kidney stone twinkling and suppress blood flow.

“Twinkling” is a widely reported ultrasound artifact whereby kidney stones and other similar calcified, strongly reflective objects appear as turbulent, flowing blood in color and power Doppler. The twinkling artifact has been shown to improve kidney stone detection over B‐mode imaging alone, but its use has several limitations. Principally, twinkling can be confused with blood flow, potentially leading to an incorrect diagnosis. Here a new method is reported for explicitly suppressing the display of color from blood flow to enhance and/or isolate the twinkle signal. The method applies an autoregressive model to standard Doppler pulses in order to differentiate tissue, blood flow, and twinkling. The algorithm was implemented on a software‐based, open architecture ultrasound system and tested by a sonographer on phantoms and on stones implanted in a live porcine kidney. Stones of 3–10 mm were detected reproducibly while suppressing blood flow in the image. In conclusion, a new algorithm designed to specifically detect stones has been tested and has potential clinical utility especially as efforts are made to reduce radiation exposure on diagnosis and monitoring. [This work was supported by the National Institutes of Health (NIH Grant No. DK43881) and the National Space Biomedical Research Institute through Grant No. NASA NCC 9‐58.]

Computer Aided Diagnosis System for Stone Detection and Early Detection of Kidney Stones

Problem statement: Most of the previous study in diagnosis of kidney stone identifies a mere presence or absence of the stones in the kidney. However proposal in our study even present an early detection of kidney stones which helps to change the diet conditions and prevent the formation of stones. Approach: The study presented a scheme for ultrasound kidney image diagnosis for stone and its early detection based on improved seeded region growing based segmentation and classification of kidney images with stone sizes. With segmented portions of the images the intensity threshold variation helps in identifying multiple classes to classify the images as normal, stone and early stone stages. The improved semiautomatic Seeded Region Growing (SRG) based image segmentation process homogeneous region depends on the image granularity features, where the interested structures with dimensions comparable to the speckle size are extracted. The shape and size of the growing regions depend on this look up table entries. The region merging after the region growing also suppresses the high frequency artifacts. The diagnosis process is done based on the intensity threshold variation obtained from the segmented portions of the image and size of the portions compared to that of the standard stone sizes (less than 2 mm absence of stone, 2-4 mm early stages and 5mm and above presence of kidney stones). Results: The parameters of texture values, intensity threshold variation and stones sizes are evaluated with experimentation of various Ultrasound kidney image samples taken from the clinical laboratory. The texture extracted from the segmented portion of the kidney images presented in our study precisely estimate the size of the stones and the position of the stones in the kidney which was not done in the earlier studies. Conclusion: The integrated improved SRG and classification mechanisms presented in this study diagnosis the kidney stones presence and absence along with the early stages of stone formation.

Application of artificial tactile sensing approach in kidney-stone-removal laparoscopy

Artificial tactile sensing is a novel method for obtaining different characteristics of a hard object embedded in a soft tissue. In this regard, artificial palpation is one of the most valuable achievements of artificial tactile sensing that can be used in various fields of medicine and more specifically in surgery. In this study, considering the present problems and limitations in kidney-stone-removal laparoscopy, a new application will be presented for artificial tactile sensing approach. Having imitated surgeon's palpation during open surgery and modeled it conceptually, indications of stone existence that appear on the surface of kidney (due to exerting mechanical load) were determined. A number of different cases were created and solved by the software. Using stress distribution contours and stress graphs, it is illustrated that the created stress patterns on the surface of kidney not only show the existence of stone inside, but also its exact location. In fact, the reliability and accuracy of artificial tactile sensing method in detection of kidney stone during laparoscopy is demonstrated by means of finite element analysis. Also, in this paper, the functional principles of tactile system capable of determining the exact location of stone during laparoscopy will be presented.

Evaluation of a New Method for Detection of Kidney Stone during Laparoscopy Using 3D Conceptual Modeling

Minimally invasive surgery (MIS) is now being widely used as a preferred choice for various types of operations. The need to detect various tactile properties, justifies the key role of tactile sensing that is currently missing in MIS. In this regard, Laparoscopy is one of the methods of minimally invasive surgery that can be used in kidney stone removal surgeries. At this moment, determination of the exact location of stone during laparoscopy is one of the limitations of this method that no scientific solution has been found for so far. Artificial tactile sensing is a new method for obtaining the characteristics of a hard object embedded in a soft tissue. Artificial palpation is an important application of artificial tactile sensing that can be used in different types of surgeries. In this study, a new method for determining the exact location of stone during laparoscopy is presented. In the present study, the effects of stone existence on the surface of kidney were investigated using conceptual 3D model of kidney containing a simulated stone. Having imitated palpation and modeled it conceptually, indications of stone existence that appear on the surface of kidney were determined. A number of different cases were created and solved by the software and using stress distribution contours and stress graphs, it is illustrated that the created stress patterns on the surface of kidney show not only the existence of stone inside, but also its exact location. So three-dimensional analysis leads to a novel method of predicting the exact location of stone and can be directly applied to the incorporation of tactile sensing in artificial palpation, helping surgeons in non-invasive procedures. Keywords—Kidney Stone, Laparoscopic Surgery, Artificial Tactile Sensing, Finite Element Method.

TU‐D‐L100J‐07: The Use of CT Dual‐Energy Subtraction Imaging to Detect Kidney Stones Amid Iodinated Contrast Material

Purpose: Iodinated contrast excreted into the renal collecting systems and ureters is of similar CT attenuation as kidney stones, making stones difficult or impossible to detect in contrast‐enhanced CT scans. This necessitates precontrast imaging for kidney stone work‐up. Our purpose was to determine the ability of CT dual‐energy subtraction imaging to selectively remove iodine signal while preserving the signal from kidney stones. Method and Materials: A phantom containing twenty kidney stones with different composition (calcium oxalate monohydrate, calcium hydroxyapatite, uric acid) and size (2 – 6 mm) was scanned with the stones surrounded by water or an iodine/water solution (500, 1000, 1400, 1900, 2300 HU at 120 kV) using a dual‐source CT system (Siemens Definition) and 80/140 kV tube potentials. Iodine calibration curves were generated to determine the CT‐number ratio between the low and high‐kV images and energy subtraction images created. Patients with known stone disease were scanned using the same radiation dose as for single‐energy CT as part of clinically‐indicated examinations. Subtraction images were created and compared to images of the known stone location. Results: Image subtraction performed using the empirical calibration curves was successful in removing iodine signal and preserving stone signal for all evaluated stones. One calibration factor to remove iodine signal was successful for all concentrations below the saturation limit, demonstrating independence of the technique on iodine concentration. In initial patient studies, the stone(s) remained visible after subtraction of the iodine signal, demonstrating the potential of the technique in vivo. Conclusion: Dual energy CT can successfully remove iodine while preserving the signal associated with renal stones. This capability may allow the elimination of the non‐contrast phase of CT urogram studies, which may decrease the radiation dose to the patient by 50%. Conflict of Interest: Partial research support from Siemens Medical Solutions.

Radiation force imparted on a kidney stone by a Doppler‐mode diagnostic pulse

Detection of kidney stones and estimation of their sizes is an important part of the lithotripsy treatment. Fluoroscopy is often used to target stones, but not every stone is radio‐opaque and, in addition, fluoroscopy produces ionizing radiation. Acoustic waves offer an alternative way to visualize stones. The acoustic impedance of kidney stones typically differs significantly from that of surrounding tissue. A useful consequence of the impedance mismatch is the possibility to target stones with diagnostic mode ultrasound. Another consequence is that radiation force pushes the stone. Stone displacement may be responsible for the twinkling artifact that has been observed by several authors in color Doppler mode of ultrasound imaging. This effect can be used to detect not only renal and ureteral stones, but also calcifications in other organs (e.g., breast). In this paper we model the radiation force associated with the Doppler diagnostic pulse. The problem is divided into three parts: (1) acoustic scattering; it is solved in finite differences; (2) radiation force calculation; (3) stone velocity estimation supposing the stone sits in soft tissue. [Work supported by NIH DK43881, DK55674, NSBRI SMS00402, and RFBR.]

Characterization of a vibro-acoustography system designed to detect kidney stones during lithotripsy

Acoustic properties of a vibro-acoustography system designed to detect kidney stones were measured. Our system was formed with two spherical transducers (10 cm diameter, 20 cm curvature) in degassed water that were confocal and separated by an angle of 30 degrees. They were driven at 1.1 MHz and 1.125 MHz to generate a difference frequency of 25 kHz. The acoustic field was characterized by scattering from a known target, the curved surface of a steel cylinder with 6.4 mm diameter. Waveforms of both the low and high frequency scattered signals were measured for different target locations, different hydrophone locations encircling the target, and different acoustic pressures. Focal dimensions of the −6 db pressure profile measured at 25 kHz and the fundamental were both 3×10 mm, in an elliptical shape, which is highly localized. Scatter amplitude was rather insensitive to hydrophone position when the target was in the focus, quite sensitive to hydrophone position when the target was out of the focus, and increased linearly with the sum of the sources. It is hoped that this characterization will help improve the understanding of the mechanisms of the targeting technique. [Work supported by NIH grants DK43881 and DK55674, and NSBRI grant SMS00203.]