A comparison of three preprocessing techniques for kidney stone segmentation in CT scan images

Thein, Nilar; Hamamoto, Kazuhiko; Nugroho, Hanung Adi; Adji, Teguh Bharata

doi:10.1109/bmeicon.2018.8609996

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, because of the nature of CT scanning in kidney stone case, the location of kidney stone is enclosed inside of bony skeleton and bed-mat is existed at the behind of bony skeleton and stone. Estimation two coordinate thresholding values have been applied for locationbased thresholding algorithm [30]. As a result of the pre-processing, bony skeleton and some bone fragments are removed from the image.…”

Section: Implementation Detailmentioning

confidence: 99%

See 1 more Smart Citation

Automated False Positive Reduction and Feature Extraction of Kidney Stone Object in 3D CT Images

Thein¹,

Adji²,

Hamamoto³

et al. 2019

IJIES

Self Cite

View full text Add to dashboard Cite

CT imaging is widely used for a variety of diagnostic and therapeutic purposes. It is a best effective and efficient tool in kidney stones diagnostic and treatment strategies whenever contactless measurements of quality are necessary to examine different types of stones. Accurate segmentation is a key process in CT diagnostic imaging. But, there are some challenges to distinguish among stones, stents or nephrostomy tubes, calcification and bone fragments in stone diagnostic CT imaging. This study proposed and experimentally investigated a scheme to reduce false positive for stone detection and to extract meaningful structural information for diagnosis of kidney stones. Firstly, the interested object (stone) is segmented by Otsu's thresholding method and morphological operation. Secondly, the parameters based on 3D morphological features are measured for stone detection. In false positive reduction, the unwanted disturbances (bone fragments, image noise, calcification and stents) are eliminated using novel volume-ratio based thresholding and SAV ratio based thresholding. Finally, it provided an output that identifies meaningful structural information (Surface-area-to-volume ratio, volume, location and density of kidney stone) for kidney stone diagnosis. Digitized transverse abdomen CT images from 35 patients with kidney stone cases were statistically analyzed and validated. The estimation of coordinate points in the stone region was measured independently by the expert radiologists to get the validated data for the analysis. The proposed algorithm was significantly reduced the false positives with 70% of overall accuracy. Moreover, it can present the meaningful information of the kidney stone. This may lead to more accurate stone management.

show abstract

Section: Implementation Detailmentioning

confidence: 99%

“…For performance evaluation, sensitivity was used in this study for a comparison of proposed algorithm. In [31], it is calculated using TP and FN rate as shown below:…”

Section: Performance Evaluationmentioning

confidence: 99%