Urine Sediment Recognition Method Based on SVM and AdaBoost

Shen, Mei-Li; Zhang, Rui

doi:10.1109/cise.2009.5365881

Cited by 13 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with other papers, the method proposed in this paper has obvious advantages, as shown in Table 4. It can be seen that the accuracy of the proposed method is slightly lower than that of the CNN method proposed in [37], and higher than that of the traditional method proposed in [30], [31] and CNN mothods proposed in [35], [36], [38]. The recognition task of this paper is 10 categories, and the methods proposed in [37] only have 3 categories.…”

Section: B Experiments and Analysismentioning

confidence: 83%

“…After segmentation by watershed algorithm and combining Gabor filter with scattering transform, by robust feature description, it can not only keeps the invariance of scaling, rotation and translation, but also shows good performance in SVM classification process. Shen and Zhang [31] used AdaBoost algorithm and SVM algorithm to classify through Harr feature, and used cascade acceleration algorithm to improve the computing speed. Zhou et al [32] combined LHS and D-GDCM with SVM and used them for classification.…”

Section: B Automatic Recognition Of Urine Sediment Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Research on Urine Sediment Images Recognition Based on Deep Learning

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Detection of urine sediment microscopic images of human urine samples plays an important part in vitro examination. Doctors usually use automatic urine sediment analyzer to assist manual examine. At present, automatic urine sediment analyzers mostly use traditional method of artificial feature extraction to recognize urine sediment images. However, traditional image processing methods based on the selection and combination of feature operators and classifiers require a lot of work and subjective experience for engineers in the implementation process. It's also difficult to deal with urine sediment images recognition tasks with large scale categories, and particles in some different categories are often confused in recognition using traditional image processing methods, such as red blood cells (RBCs) and white blood cells (WBCs). In this paper, a combination convolution neural network (CNN) recognition method with area feature algorithm is proposed. The disadvantage that CNN can weaken the area feature of input image is solved by area feature algorithm (AFA) proposed in this paper. The network models which use 300,000 urine sediment images for training can quickly and accurately recognize 10 categories of urine sediment images, and several confusing categories' recognition indexes are remarkably improved. The test accuracy in the test set reached 97%. INDEX TERMS Automatic diagnosis, deep learning, image processing, urine sediment.

show abstract

Section: B Experiments and Analysismentioning

confidence: 83%

Section: B Automatic Recognition Of Urine Sediment Imagesmentioning

confidence: 99%

Research on Urine Sediment Images Recognition Based on Deep Learning

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…After features extraction by a novel local jet context feature scheme, they proposed a two-tier classification strategy to better reduce the false positive rate caused by impurity and poor focused regions. Shen et al [5] used AdaBoost to select a little part typical Harr features for SVM classification, and improved system speed via cascade accelerating algorithm. Zhou et al [17] demonstrated an easy-implemented automatic urinalysis system employing a SVM classifier to distinguish casts from other particles.…”

Section: Urine Particles Recognitionmentioning

confidence: 99%

“…The issues involved in the manual analysis have motivated lots of automated methods for the analysis of urine microscope images (e.g. [3,4,5,6,7,8]). As shown in figure 1(a), almost all of them follow the multi-stage pipeline, i.e., first generating candidate regions based on segmentation and then extracting hand-crafted features over regions for classification.…”

Section: Introductionmentioning

confidence: 99%

CNN-Based Automatic Urinary Particles Recognition

Kang,

Liang,

Lian

et al. 2018

Preprint

View full text Add to dashboard Cite

The urine sediment analysis of particles in microscopic images can assist physicians in evaluating patients with renal and urinary tract diseases. Manual urine sediment examination is labor-intensive, subjective and time-consuming, and the traditional automatic algorithms often extract the hand-crafted features for recognition. Instead of using the hand-crafted features, in this paper, we exploit CNN to learn features in an end-to-end manner to recognize the urine particles. We treat the urine particles recognition as object detection and exploit two state-of-the-art CNN-based object detection methods, Faster R-CNN and SSD, as well as their variants for urine particles recognition. We further investigate different factors involving these CNN-based object detection methods for urine particles recognition. We comprehensively evaluate these methods on a dataset consisting of 5,376 annotated images corresponding to 7 categories of urine particles, i.e., erythrocyte, leukocyte, epithelial cell, crystal, cast, mycete, epithelial nuclei, and obtain a best mAP (mean average precision) of 84.1% while taking only 72 ms per image on a NVIDIA Titan X GPU.

show abstract

“…Finally, they proposed a two‐layer classification strategy that achieved reductions in the false positive rate owing to impurities and focus blur. Shen et al 16 used the AdaBoost to select a small sample of typical Harr features for support vector machine (SVM 17 ) classification, and cascading acceleration algorithms to speed up the detection. Another method proposed the use of an adaptive discrete wavelet entropy energy (ADWEE) for adaptive feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Inspection of visible components in urine based on deep learning

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Urinary particles are particularly important parameters in clinical urinalysis, especially for the diagnosis of nephropathy. Therefore, it is highly important to precisely detect urinary particles in the clinical setting. However, artificial microscopy is subjective and time consuming, and various previous detection algorithms lack the adequate accuracy. In this study, a method is proposed for the analysis of urinary particles based on deep learning. Methods: We used seven cellular components (i.e., erythrocytes, leukocytes, epithelial, low-transitional epithelium, casts, crystal, and squamous epithelial cells) in the microscopic imaging of urine as the detection targets. After the extraction of features using Resnet50, feature maps of different sizes are obtained in the last few layers of the feature pyramid net (FPN). The feature maps are then input into the classification subnetwork and regression subnetwork for classification and localization respectively, and detection results are obtained. First, we introduce the basic model (RetinaNet) to detect the cellular components in urinary particles, and the features of the objects can then be extracted more effectively by replacing different basic networks. Lastly, the effects of different weight initialization methods and different anchor scales on the performance of the model are investigated. Results: We obtained the optimal network structure based on the adjustment of the loss functional parameters, thereby achieving the best results in the test set of urinary particles. The experimental data yielded an accuracy of 88.65% with a processing time of only 0.2 s for each image on a GeForce GTX 1080 graphics processing unit (GPU). Our results demonstrate that this method cannot only achieve the speed of the first-stage target detector, but also the accuracy of the two-stage target algorithm in the analysis of urinary particles. Conclusion:This study developed new automated analysis urinary particles based on deep learning, and this method is expected to be used for the automated analysis and detection of urinary particles. Moreover, our approach will be useful for the detection of other cells in the clinical setting.

show abstract

Urine Sediment Recognition Method Based on SVM and AdaBoost

Cited by 13 publications

References 8 publications

Research on Urine Sediment Images Recognition Based on Deep Learning

Research on Urine Sediment Images Recognition Based on Deep Learning

CNN-Based Automatic Urinary Particles Recognition

Inspection of visible components in urine based on deep learning

Contact Info

Product

Resources

About