An End-to-End System for Automatic Urinary Particle Recognition with Convolutional Neural Network

Liang, Yixiong; Kang, Rui; Lian, Chunyan; Mao, Yuan

doi:10.1007/s10916-018-1014-6

Cited by 35 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Liang et al [46] treated the urinary particle recognition as object detection and employed Faster RCNN [36] and SSD [45] methods, along with their variants, for urinary particle recognition. And what's more, the result of their study was encouraging.…”

Section: Introductionmentioning

confidence: 99%

Deep learning approach to peripheral leukocyte recognition

et al. 2019

View full text Add to dashboard Cite

Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once . To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning approach to peripheral leukocyte recognition

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Urine sediment analysis is an important component in evaluating urological and nephrological diseases. Nevertheless, manual urine sediment examination is time-consuming, labor-intensive, and prone to errors [34,35]. While several automated urine microscopy analyzers are currently available, these analyzers often rely on more traditional ML frameworks encompassing preprocessing steps, segmentation, handcrafted feature extraction, selection, and image classification using pattern recognition methods.…”

Section: Automated Urine Sediment Analysismentioning

confidence: 99%

“…It has been documented that pretrained CNNs with adequate fine-tuning have the potential to outperform CNNs trained from scratch [38]. Instead of using hand-designed heuristics, fine-tuned, and pre-trained CNNs have been employed by Liang et al [35] in the automatic recognition of seven categories of urine particles (i.e. leukocytes, erythrocytes, casts, crystals, epithelial cells, epithelial nuclei, and mycetes).…”

Section: Automated Urine Sediment Analysismentioning

confidence: 99%

Recent evolutions of machine learning applications in clinical laboratory medicine

Bruyne

Speeckaert

Biesen

et al. 2020

Critical Reviews in Clinical Laboratory Sciences

View full text Add to dashboard Cite

Machine learning (ML) is gaining increased interest in clinical laboratory medicine, mainly triggered by the decreased cost of generating and storing data using laboratory automation and computational power, and the widespread accessibility of open source tools. Nevertheless, only a handful of ML-based products are currently commercially available for routine clinical laboratory practice. In this review, we start with an introduction to ML by providing an overview of the ML landscape, its general workflow, and the most commonly used algorithms for clinical laboratory applications. Furthermore, we aim to illustrate recent evolutions (2018 to mid-2020) of the techniques used in the clinical laboratory setting and discuss the associated challenges and opportunities. In the field of clinical chemistry, the reviewed applications of ML algorithms include quality review of lab results, automated urine sediment analysis, disease or outcome prediction from routine laboratory parameters, and interpretation of complex biochemical data. In the hematology subdiscipline, we discuss the concepts of automated blood film reporting and malaria diagnosis. At last, we handle a broad range of clinical microbiology applications, such as the reduction of diagnostic workload by laboratory automation, the detection and identification of clinically relevant microorganisms, and the detection of antimicrobial resistance.

show abstract

“…Pan et al [37] constructed a CNN model, and achieved 97% accuracy in the classification of 3 urine sediment categories, including RBCs, WBCs, and CAOXs. Kang et al [38], [39] combined Faster RCNN with SSD to classify 7 categories of urine sediment particles. Although these methods have achieved satisfying results, these methods still have disadvantages such as confusion of some different categories in recognition.…”

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

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

An End-to-End System for Automatic Urinary Particle Recognition with Convolutional Neural Network

Cited by 35 publications

References 13 publications

Deep learning approach to peripheral leukocyte recognition

Deep learning approach to peripheral leukocyte recognition

Recent evolutions of machine learning applications in clinical laboratory medicine

Research on Urine Sediment Images Recognition Based on Deep Learning

Contact Info

Product

Resources

About