Automatic Detection and Scoring of Kidney Stones on Noncontrast CT Images Using S.T.O.N.E. Nephrolithometry: Combined Deep Learning and Thresholding Methods

Cui, Yingpu; Sun, Zhaonan; Ma, Shuai; Liu, Weipeng; Wang, Xiangpeng; Zhang, Xiaodong; Wang, Xiaoying

doi:10.1007/s11307-020-01554-0

Cited by 37 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two challenges encountered in this work were dealing with large amounts of image noise and distinguishing plaques from kidney stones. The issue of plaques causing false positives and false negatives has also been noted in another recent work 27 . Solving this problem was outside the scope of this work but might be tackled by assembling a joint training dataset to train a multiclass deep learning system to detect and segment both plaque and kidney stones.…”

Section: Discussionmentioning

confidence: 80%

“…The cropped box is fed into a second 3D U‐Net that segments the renal sinus area, where most kidney stones are located. The system achieved a sensitivity of 96% with a false positive rate of 0.03 per patient for detecting stones

&gt;

2 mm in diameter (volume

&gt;

4.18 mm

^3

) 27 . A major weakness of their system is their threshold‐based detection system that leads to many false positives on low‐dose CT scans.…”

Section: Introductionmentioning

confidence: 99%

“…The importance of stone volume measurement (as opposed to linear measurement) has been neglected in the recent works on automated kidney stone detection, even though it has been shown to be highly correlated with patient outcomes. Another major deficiency of the works reported so far is that none of the works test their system on an external dataset 25–27 . In this work, we seek to meet what is actually needed for clinical use—a robust system validated on a large dataset capable of detecting and segmenting small stones on both noisy CT (the type of CT often used for kidney stone screening) and less noisy CT taken for CT colonography (for opportunistic detection).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans

et al. 2022

View full text Add to dashboard Cite

Purpose Early detection and size quantification of renal calculi are important for optimizing treatment and preventing severe kidney stone disease. Prior work has shown that volumetric measurements of kidney stones are more informative and reproducible than linear measurements. Deep learning‐based systems that use abdominal noncontrast computed tomography (CT) scans may assist in detection and reduce workload by removing the need for manual stone volume measurement. Prior to this work, no such system had been developed for use on noisy low‐dose CT or tested on a large‐scale external dataset. Methods We used a dataset of 91 CT colonography (CTC) scans with manually marked kidney stones combined with 89 CTC scans without kidney stones. To compare with a prior work half the data was used for training and half for testing. A set of CTC scans from 6185 patients from a separate institution with patient‐level labels were used as an external validation set. A 3D U‐Net model was employed to segment the kidneys, followed by gradient‐based anisotropic denoising, thresholding, and region growing. A 13 layer convolutional neural network classifier was then applied to distinguish kidney stones from false positive regions. Results The system achieved a sensitivity of 0.86 at 0.5 false positives per scan on a challenging test set of low‐dose CT with many small stones, an improvement over an earlier work that obtained a sensitivity of 0.52. The stone volume measurements correlated well with manual measurements (r2=0.95$r^2 = 0.95$). For patient‐level classification, the system achieved an area under the receiver‐operating characteristic of 0.95 on an external validation set (sensitivity = 0.88, specificity = 0.91 at the Youden point). A common cause of false positives were small atherosclerotic plaques in the renal sinus that simulated kidney stones. Conclusions Our deep‐learning‐based system showed improvements over a previously developed system that did not use deep learning, with even higher performance on an external validation set.

show abstract

Section: Discussionmentioning

confidence: 80%

&gt;

2 mm in diameter (volume

&gt;

4.18 mm

^3

) 27 . A major weakness of their system is their threshold‐based detection system that leads to many false positives on low‐dose CT scans.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Comprehensive clinical research based on deep learning is usually divided into multiple sequential steps, with each step employing deep learning or traditional image processing methods [ 28 , 29 ]. Regarding the segmentation of kidney stones on CT images, the kidney is firstly segmented by the deep learning method, after which the high-density stone is identified using the traditional threshold segmentation method [ 30 ]. The division of the complex clinical tasks can not only improve the acceptability of the model but can also save training resources, which highlights the value of the clinicians participating in model training.…”

Section: Discussionmentioning

confidence: 99%

Fully automated pelvic bone segmentation in multiparameteric MRI using a 3D convolutional neural network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Accurate segmentation of pelvic bones is an initial step to achieve accurate detection and localisation of pelvic bone metastases. This study presents a deep learning-based approach for automated segmentation of normal pelvic bony structures in multiparametric magnetic resonance imaging (mpMRI) using a 3D convolutional neural network (CNN). Methods This retrospective study included 264 pelvic mpMRI data obtained between 2018 and 2019. The manual annotations of pelvic bony structures (which included lumbar vertebra, sacrococcyx, ilium, acetabulum, femoral head, femoral neck, ischium, and pubis) on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images were used to create reference standards. A 3D U-Net CNN was employed for automatic pelvic bone segmentation. Additionally, 60 mpMRI data from 2020 were included and used to evaluate the model externally. Results The CNN achieved a high Dice similarity coefficient (DSC) average in both testing (0.80 [DWI images] and 0.85 [ADC images]) and external (0.79 [DWI images] and 0.84 [ADC images]) validation sets. Pelvic bone volumes measured with manual and CNN-predicted segmentations were highly correlated (R2 value of 0.84–0.97) and in close agreement (mean bias of 2.6–4.5 cm3). A SCORE system was designed to qualitatively evaluate the model for which both testing and external validation sets achieved high scores in terms of both qualitative evaluation and concordance between two readers (ICC = 0.904; 95% confidence interval: 0.871–0.929). Conclusions A deep learning-based method can achieve automated pelvic bone segmentation on DWI and ADC images with suitable quantitative and qualitative performance.

show abstract

“…Finally, the location of the stone was determined. As a result, the stone detection method reached 95.9% sensitivity and 98.7% positive predictive value (PPV) [13].…”

Section: Related Workmentioning

confidence: 97%

Kidney X-ray Images Classification using Machine Learning and Deep Learning Methods

Aksakalli

Kaçdioğlu

Hanay

2021

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Today, kidney stone detection is performed manually by humans on medical images. This process is timeconsuming and subjective as it depends on the physician. This study aims to classify healthy or patient individuals according to the status of kidney stones from medical images using various machine learning methods and Convolutional Neural Network (CNN). We evaluated various machine learning methods such as Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), Multilayer Perceptron (MLP), K-Nearest Neighbor (kNN), Naive Bayes (BernoulliNB), and deep neural networks using CNN. According to the experiments, the Decision Tree Classifier (DT) has the best classification result. This method has the highest F1 score rate with a success rate of 85.3% using the S+U sampling method. The experimental results show that the Decision Tree Classifier (DT) is a feasible method for distinguishing the kidney x-ray images.

show abstract

Automatic Detection and Scoring of Kidney Stones on Noncontrast CT Images Using S.T.O.N.E. Nephrolithometry: Combined Deep Learning and Thresholding Methods

Cited by 37 publications

References 27 publications

A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans

A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans

Fully automated pelvic bone segmentation in multiparameteric MRI using a 3D convolutional neural network

Kidney X-ray Images Classification using Machine Learning and Deep Learning Methods

Contact Info

Product

Resources

About