Automatic gallbladder and gallstone regions segmentation in ultrasound image

Lian, Jing; Ma, Yide; Ma, Yurun; Shi, Bin; Liu, Jizhao; Yang, Zhen; Guo, Yanan

doi:10.1007/s11548-016-1515-z

Cited by 33 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(ii) 99Te, ETC scans requiring special equipment is difficult to popularize in most primary hospitals [43];…”

Section: Cholecystolithotripsy For Patients With Symptomatic Chronic mentioning

confidence: 99%

Advances in Gallbladder-Preserving Surgery for Gallbladder Diseases

Gs¹,

Zhao²,

Huang³

et al. 2019

Clin Res Open Access

View full text Add to dashboard Cite

Research on gallbladder diseases, whether in basic pathogenesis or clinical treatment, has been continuing and developing. Currently, gallbladderpreserving lithotripsy has attracted considerable attention in the treatment of cholecystolithiasis in China. In recent years, Endoscopic Minimally Invasive Gallbladder-Preserving Surgery (CGPS) has become more and more mature. However, the recurrence rate of gallstones after CGPS has been an urgent question that requires careful investigation. This article reviews the progress in postoperative recurrence of gallbladder diseases treated with gall bladder preservation surgery.

show abstract

“…(ii) 99Te, ETC scans requiring special equipment is difficult to popularize in most primary hospitals [43];…”

Section: Cholecystolithotripsy For Patients With Symptomatic Chronic mentioning

confidence: 99%

Advances in Gallbladder-Preserving Surgery for Gallbladder Diseases

Gs¹,

Zhao²,

Huang³

et al. 2019

Clin Res Open Access

View full text Add to dashboard Cite

show abstract

“…Furthermore, optimization of this technique was achieved by constructing high-resolution broadband transducers with 3D and 4D options for organ imaging. This diagnostic arsenal was further enriched with endoscopic, laparoscopic and contrast-enhanced ultrasound (CEUS), as well as elastography and automatic organ segmentation, which was achieved using a special algorithm (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11) . Ultrasonography has long been a method allowing for precise cytological diagnosis of lesions by means of transabdominal and endoscopic ultrasound-guided fine needle aspiration biopsy (12)(13)(14) .…”

Section: Introductionmentioning

confidence: 99%

Optimization of diagnostic ultrasonography of the gallbladder based on own experience and literature

2020

View full text Add to dashboard Cite

Although transabdominal imaging of the gallbladder has become a gold standard, new light should be shed on some aspects, which will prove useful in everyday practice. Therefore, based on our own experience and the available literature, we would like to draw attention to those elements of gallbladder ultrasound imaging which may increase its diagnostic efficacy. The paper draws attention to the difficulty in assessing certain anatomical structures, such as the inferior wall, the bottom and the region of the neck of the gallbladder, and offers ways to improve their imaging. We also emphasized the negative effects of duodenal and transverse colon (along with their contents) adhesion to the bottom of the gallbladder on the correct diagnosis. Due to the importance of size in the management strategy for detected gallbladder polyps, we suggest their measurement on an image enlarged with the zoom function. This technique also allows for an accurate assessment of the shape and echostructure of these lesions. An enlarged image of a polyp makes it possible to trace its behavior in time. We also remind that the hepatic wall of the gallbladder is the only site allowing for a reliable wall thickness measurement. We also pointed to the importance of changing patient's position when assessing the mobility and the nature of lesions. Altering patient's position during examination may help detect anomalies in the form of a floating gallbladder, which may promote its torsion. Finally, pathologies whose diagnosis may be facilitated by color-coded blood flow imaging are also presented. The issues discussed in this paper are only a fraction of problems faced by an ultrasound operator in the field of gallbladder diagnostic imaging. However, the proposed ultrasound approaches should help solve some of these problems in everyday practice.

show abstract

“…In 2013, ultrasound image segmentation with a level set model was proposed [25], and then it was improved by using the parameter-adaptive pulse-coupled neural network (PA-PCNN) [16] and using the normalized cut (NCUT) segmentation technique [1]. However, using ultrasound imaging to penetrate the human body will produce a large number of interferences.…”

Section: Introductionmentioning

confidence: 99%

U-Next: A Novel Convolution Neural Network With an Aggregation U-Net Architecture for Gallstone Segmentation in CT Images

et al. 2019

View full text Add to dashboard Cite

The incidence of cholelithiasis is more than 10% in the natural population. It is a common and frequently occurring disease worldwide. The lesions are predominantly sand-like and are difficult to distinguish in medical images. Although ultrasound is often the first-line technique for diagnosing cholelithiasis, CT plays an important role in diagnosing complications related to gallstones. To the best of our knowledge, no effective method has been proposed for segmenting CT images of gallstones. To address this difficulty, we have proposed a novel deep learning segmentation model, U-NeXt, which can automatically provide the importance of different shapes and sizes of target structures in images. a) We proposed attention up-sampling blocks for up-sampling. b) We also proposed a spatial pyramid pooling of skip connections, which is called SkipSPP. A series of convolution layers are connected by jumping connections to generate multi-scale features. c) We employed a dense connection to many details of the model to extract more features. In addition, we contributed a new data set for gallstone segmentation, which is co-labelled by three chief physicians from the hepatobiliary department and the medical imaging department of Shandong Province Third Hospital, China. The data set included 5,350 images from 726 patients. Compared with the previous best CT image segmentation method for gallstones, the intersection over union (IoU) improved by 24%, and compared with the medical image segmentation baseline model, the IoU improved by 7%, with a satisfactory segmentation effect. We extended U-NeXt to the nuclei segmentation task, showing that the model has good generalizability. INDEX TERMS Image segmentation, artificial intelligence, neural networks, medical diagnosis.

show abstract

Automatic gallbladder and gallstone regions segmentation in ultrasound image

Abstract: The proposed method is potential to assist physicians for diagnosing the gallbladder disease rapidly and effectively.

Cited by 33 publications

References 34 publications

Advances in Gallbladder-Preserving Surgery for Gallbladder Diseases

Advances in Gallbladder-Preserving Surgery for Gallbladder Diseases

Optimization of diagnostic ultrasonography of the gallbladder based on own experience and literature

U-Next: A Novel Convolution Neural Network With an Aggregation U-Net Architecture for Gallstone Segmentation in CT Images

Contact Info

Product

Resources

About