EFFICIENT 3D PROSTATE SURFACE DETECTION FOR ULTRASOUND GUIDED ROBOTIC BIOPSY

2006 ◽  
Vol 03 (04) ◽  
pp. 439-461 ◽  
Author(s):  
FAN SHAO ◽  
KECK VOON LING ◽  
LOUIS PHEE ◽  
WAN SING NG ◽  
DI XIAO
Keyword(s):  
Current System ◽  
Transrectal Ultrasound ◽  
Speckle Noise ◽  
Practical Method ◽  
Ultrasound Images ◽  
Ultrasound Guided ◽  
Low Contrast ◽  
Surface Detection ◽  
Domain Specific Knowledge ◽  
Weak Boundaries

Prostate surface detection from ultrasound images plays a key role in our recently developed ultrasound guided robotic biopsy system. However, due to the low contrast, speckle noise and shadowing in ultrasound images, this still remains a difficult task. In the current system, a 3D prostate surface is reconstructed from a sequence of 2D outlines, which are performed manually. This is arduous and the results depend heavily on the user's expertise. This paper presents a new practical method, called Evolving Bubbles, based on the level set method to semi-automatically detect the prostate surface from transrectal ultrasound (TRUS) images. To produce good results, a few initial bubbles are simply specified by the user from five particular slices based on the prostate shape. When the initial bubbles evolve along their normal directions, they expand, shrink, merge and split, and finally are attracted to the desired prostate surface. Meanwhile, to remedy the boundary leaking problem caused by gaps or weak boundaries, domain specific knowledge of the prostate and statistical information are incorporated into the Evolving Bubbles. We apply the bubbles model to eight 3D and four stacks of 2D TRUS images and the results show its effectiveness.

AUTOMATIC 3D PROSTATE SURFACE DETECTION FROM TRUS WITH LEVEL SETS

2004 ◽  
Vol 04 (03) ◽  
pp. 385-403 ◽  
Author(s):  
FAN SHAO ◽  
KECK VOON LING ◽  
WAN SING NG
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Level Sets ◽  
Transrectal Ultrasound ◽  
User Interaction ◽  
Speckle Noise ◽  
Boundary Detection ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Weak Boundaries

Prostate boundary detection from ultrasound images plays an important role in prostate disease diagnoses and treatments. However, due to the low contrast, speckle noise and shadowing in ultrasound images, this still remains a difficult task. Currently, prostate boundary detection is performed manually, which is arduous and heavily user dependent. A possible solution is to improve the efficiency by automating the boundary detection process with minimal manual involvement. This paper presents a new approach based on the level set method to automatically detect the prostate surface from 3D transrectal ultrasound images. The user interaction in the initialization procedure is relieved by automatically putting the centroid of the initial zero level sets close to the image center. Region information, instead of the image gradient, is integrated into the level set method to remedy the "boundary leaking" problem caused by gaps or weak boundaries. Moreover, to increase the accuracy and robustness, knowledge-based features, such as expected shape (kidney-like) and ultrasound appearance of the prostate (looking from within the gland, the intensities are transitions from dark to light), are also incorporated into the model. The proposed method is applied to eight 3D TRUS images and the results have shown its effectiveness.

scholarly journals BGM-Net: Boundary-Guided Multiscale Network for Breast Lesion Segmentation in Ultrasound

2021 ◽  
Vol 8 ◽  
Author(s):  
Yunzhu Wu ◽  
Ruoxin Zhang ◽  
Lei Zhu ◽  
Weiming Wang ◽  
Shengwen Wang ◽  
...  
Keyword(s):  
Breast Lesion ◽  
Speckle Noise ◽  
Breast Ultrasound ◽  
Ultrasound Images ◽  
Lesion Segmentation ◽  
Low Contrast ◽  
Feature Enhancement ◽  
Boundary Map ◽  
Weak Boundaries ◽  
Feature Pyramid

Automatic and accurate segmentation of breast lesion regions from ultrasonography is an essential step for ultrasound-guided diagnosis and treatment. However, developing a desirable segmentation method is very difficult due to strong imaging artifacts e.g., speckle noise, low contrast and intensity inhomogeneity, in breast ultrasound images. To solve this problem, this paper proposes a novel boundary-guided multiscale network (BGM-Net) to boost the performance of breast lesion segmentation from ultrasound images based on the feature pyramid network (FPN). First, we develop a boundary-guided feature enhancement (BGFE) module to enhance the feature map for each FPN layer by learning a boundary map of breast lesion regions. The BGFE module improves the boundary detection capability of the FPN framework so that weak boundaries in ambiguous regions can be correctly identified. Second, we design a multiscale scheme to leverage the information from different image scales in order to tackle ultrasound artifacts. Specifically, we downsample each testing image into a coarse counterpart, and both the testing image and its coarse counterpart are input into BGM-Net to predict a fine and a coarse segmentation maps, respectively. The segmentation result is then produced by fusing the fine and the coarse segmentation maps so that breast lesion regions are accurately segmented from ultrasound images and false detections are effectively removed attributing to boundary feature enhancement and multiscale image information. We validate the performance of the proposed approach on two challenging breast ultrasound datasets, and experimental results demonstrate that our approach outperforms state-of-the-art methods.

scholarly journals A Fast, Fully Automated Prostate Boundary Segmentation Using Probabilistic Approaches In Ultrasound Images

2021 ◽  
Author(s):  
Rasa Vafaie
Keyword(s):  
Em Algorithm ◽  
Signal To Noise Ratio ◽  
Transrectal Ultrasound ◽  
Speckle Noise ◽  
Computational Time ◽  
Dice Similarity Coefficient ◽  
Ultrasound Images ◽  
Segmentation Method ◽  
Initial Model ◽  
Hybrid Segmentation

Segmentation of prostate boundaries in transrectal ultrasound (TRUS) images plays a great role in prostate cancer diagnosis. Due to the low signal to noise ratio and existence of the speckle noise in TRUS images, prostate image segmentation has proven to be an extremely difficult task. In this thesis report, a fast fully automated hybrid segmentation method based on probabilistic approaches is presented. First, the position of the initial model is automatically estimated using prostate boundary representative patterns. Next, the Expectation Maximization (EM) algorithm and Markov Random Field (MRF) theory are utilized in the deformation strategy to optimally fit the initial model on the prostate boundaries. A less computationally EM algorithm and a new surface smoothing technique are proposed to decrease the segmentation time. Successful experimental results with the average Dice Similarity Coefficient (DSC) value 93.9±2.7% and computational time around 9 seconds validate the algorithm.

Modified Distance Regularized Level Set Segmentation Based Analysis for Kidney Stone Detection

2015 ◽  
Vol 2 (2) ◽  
pp. 24-41 ◽  
Author(s):  
K. Viswanath ◽  
R. Gunasundari
Keyword(s):  
Energy Level ◽  
Level Set ◽  
High Speed ◽  
Gabor Filter ◽  
Energy Levels ◽  
Speckle Noise ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Level Set Function ◽  
Level Set Segmentation

The abnormalities of the kidney can be identified by ultrasound imaging. The kidney may have structural abnormalities like kidney swelling, change in its position and appearance. Kidney abnormality may also arise due to the formation of stones, cysts, cancerous cells, congenital anomalies, blockage of urine etc. For surgical operations it is very important to identify the exact and accurate location of stone in the kidney. The ultrasound images are of low contrast and contain speckle noise. This makes the detection of kidney abnormalities rather challenging task. Thus preprocessing of ultrasound images is carried out to remove speckle noise. In preprocessing, first image restoration is done to reduce speckle noise then it is applied to Gabor filter for smoothening. Next the resultant image is enhanced using histogram equalization. The preprocessed ultrasound image is segmented using distance regularized level set segmentation (DR-LSS), since it yields better results. It uses a two-step splitting methods to iteratively solve the DR-LSS equation, first step is iterating LSS equation, and then solving the Sign distance equation. The second step is to regularize the level set function which is the obtained from first step for better stability. The DR is included for LSS for eliminating of anti-leakages on image boundary. The DR-LSS does not require any expensive re-initialization and it is very high speed of operation. The RD-LSS results are compared with distance regularized level set evolution DRLSE1, DRLSE2 and DRLSE3. Extracted region of the kidney after segmentation is applied to Symlets (Sym12), Biorthogonal (bio3.7, bio3.9 & bio4.4) and Daubechies (Db12) lifting scheme wavelet subbands to extract energy levels. These energy level gives an indication about presence of stone in that particular location which significantly vary from that of normal energy level. These energy levels are trained by Multilayer Perceptron (MLP) and Back Propagation (BP) ANN to identify the type of stone with an accuracy of 98.6%.

scholarly journals Phase- and GVF-Based Level Set Segmentation of Ultrasonic Breast Tumors

2012 ◽  
Vol 2012 ◽  
pp. 1-22 ◽  
Author(s):  
Liang Gao ◽  
Xiaoyun Liu ◽  
Wufan Chen
Keyword(s):  
Level Set ◽  
Breast Tumor ◽  
Active Contour Model ◽  
Speckle Noise ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Good Convergence ◽  
Capture Range ◽  
Edge Based ◽  
Concave Boundaries

Automatically extracting breast tumor boundaries in ultrasound images is a difficult task due to the speckle noise, the low image contrast, the variance in shapes, and the local changes of image intensity. In this paper, an improved edge-based active contour model in a variational level set formulation is proposed for semi-automatically capturing ultrasonic breast tumor boundaries. First, we apply the phase asymmetry approach to enhance the edges, and then we define a new edge stopping function, which can increase the robustness to the intensity inhomogeneities. To extend the capture range of the method and provide good convergence to boundary concavities, we use the phase information to obtain an improved edge map, which can be used to calculate the gradient vector flow (GVF). Combining the edge stopping term and the improved GVF in the level set framework, the proposed method can robustly cope with noise, and it can extract the low contrast and/or concave boundaries well. Experiments on breast ultrasound images show that the proposed method outperforms the state-of-art methods.

Speckle Noise Diffusion in Knee Articular Cartilage Ultrasound Images

2020 ◽  
Vol 16 (6) ◽  
pp. 739-751
Author(s):  
Muhammad Ali Shoaib ◽  
Md Belayet Hossain ◽  
Yan Chai Hum ◽  
Joon Huang Chuah ◽  
Maheza Irna Mohd Salim ◽  
...  
Keyword(s):  
Articular Cartilage ◽  
Contrast Ratio ◽  
Speckle Noise ◽  
Absolute Error ◽  
Cartilage Injury ◽  
Speckle Reduction ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Reduction Techniques ◽  
Articular Cartilage Injury

Background: Ultrasound (US) imaging can be a convenient and reliable substitute for magnetic resonance imaging in the investigation or screening of articular cartilage injury. However, US images suffer from two main impediments, i.e., low contrast ratio and presence of speckle noise. Aims: A variation of anisotropic diffusion is proposed that can reduce speckle noise without compromising the image quality of the edges and other important details. Methods: For this technique, four gradient thresholds were adopted instead of one. A new diffusivity function that preserves the edge of the resultant image is also proposed. To automatically terminate the iterative procedures, the Mean Absolute Error as its stopping criterion was implemented. Results: Numerical results obtained by simulations unanimously indicate that the proposed method outperforms conventional speckle reduction techniques. Nevertheless, this preliminary study has been conducted based on a small number of asymptomatic subjects. Conclusion: Future work must investigate the feasibility of this method in a large cohort and its clinical validity through testing subjects with a symptomatic cartilage injury.

Improved Adaptive Wavelet Thresholding for Effective Speckle Noise Reduction in Low Contrast Medical Images

2019 ◽  
Vol 28 (10) ◽  
pp. 1950176 ◽  
Author(s):  
P. Sreelatha ◽  
M. Ezhilarasi
Keyword(s):  
Contrast Enhancement ◽  
Speckle Noise ◽  
Noise Removal ◽  
Ultrasound Images ◽  
Medical Ultrasound ◽  
Gamma Correction ◽  
Significant Information ◽  
Adaptive Wavelet ◽  
Low Contrast ◽  
Image Contrast Enhancement

Informative images endure from poor contrast and noise during image acquisition. Significant information retrieval necessitates image contrast enhancement and removal of noise as a prerequisite before any further processing can be done. Dominant applications with low contrast images affected by speckle noise are medical ultrasound images. The objective of this work is to improve the effectiveness of the preprocessing stage in medical ultrasound images by enhancing the image while retaining its structural characteristics. For image enhancement, this work proposes to develop an automatic contrast enhancement technique using cumulative histogram equalization and gamma correction based on the image. For noise removal, this work proposes an algorithm Gamma Correction with Exponentially Adaptive Threshold (GCEAT) which suggests the use of GC for contrast enhancement along with a new wavelet-based adaptive soft thresholding technique for noise removal. The proposed GCEAT-based image de-noising is validated with other enhancement and noise removal techniques. Experimental results with low contrast synthetic and actual ultrasound images show that the suggested proposed system performs better than existing contrast enhancement techniques. Encouraging results were obtained with medical ultrasound images in terms of Peak-Signal to Noise Ratio (PSNR), Mean Square Error (MSE), Structural Similarity Index Measure (SSIM) and Average Intensity (AI).

scholarly journals Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation

2021 ◽  
Vol 11 (21) ◽  
pp. 10180
Author(s):  
Sunetra Banerjee ◽  
Juan Lyu ◽  
Zixun Huang ◽  
Hung Fat Frank Leung ◽  
Timothy Tin-Yan Lee ◽  
...  
Keyword(s):  
Network Architecture ◽  
Medical Condition ◽  
Detection System ◽  
Speckle Noise ◽  
3D Ultrasound ◽  
Input Image ◽  
Ultrasound Images ◽  
Feature Identification ◽  
Screening Process ◽  
Low Contrast

Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually employed modalities include X-ray and MRI, which employ ionising radiation and are expensive. Hence, a non-radiating 3D ultrasound imaging technique has been developed as a safe and economic alternative. However, ultrasound produces low-contrast images that are full of speckle noise, and skilled intervention is necessary for their processing. Given the prevalent occurrence of scoliosis and the limitations of scalability of human expert interventions, an automatic, fast, and low-computation assessment technique is being developed for mass scoliosis diagnosis. In this paper, a novel hybridized light-weight convolutional neural network architecture is presented for automatic lateral bony feature identification, which can help to develop a fully-fledged automatic scoliosis detection system. The proposed architecture, Light-convolution Dense Selection U-Net (LDS U-Net), can accurately segment ultrasound spine lateral bony features, from noisy images, thanks to its capabilities of smartly selecting only the useful information and extracting rich deep layer features from the input image. The proposed model is tested using a dataset of 109 spine ultrasound images. The segmentation result of the proposed network is compared with basic U-Net, Attention U-Net, and MultiResUNet using various popular segmentation indices. The results show that LDS U-Net provides a better segmentation performance compared to the other models. Additionally, LDS U-Net requires a smaller number of parameters and less memory, making it suitable for a large-batch screening process of scoliosis without a high computational requirement.

Modified Distance Regularized Level Set Segmentation Based Analysis for Kidney Stone Detection

2017 ◽  
pp. 693-710
Author(s):  
K. Viswanath ◽  
R. Gunasundari
Keyword(s):  
Energy Level ◽  
Level Set ◽  
High Speed ◽  
Gabor Filter ◽  
Energy Levels ◽  
Back Propagation ◽  
Speckle Noise ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Level Set Segmentation

The abnormalities of the kidney can be identified by ultrasound imaging. The kidney may have structural abnormalities like kidney swelling, change in its position and appearance. Kidney abnormality may also arise due to the formation of stones, cysts, cancerous cells, congenital anomalies, blockage of urine etc. For surgical operations it is very important to identify the exact and accurate location of stone in the kidney. The ultrasound images are of low contrast and contain speckle noise. This makes the detection of kidney abnormalities rather challenging task. Thus preprocessing of ultrasound images is carried out to remove speckle noise. In preprocessing, first image restoration is done to reduce speckle noise then it is applied to Gabor filter for smoothening. Next the resultant image is enhanced using histogram equalization. The preprocessed ultrasound image is segmented using distance regularized level set segmentation (DR-LSS), since it yields better results. It uses a two-step splitting methods to iteratively solve the DR-LSS equation, first step is iterating LSS equation, and then solving the Sign distance equation. The second step is to regularize the level set function which is the obtained from first step for better stability. The DR is included for LSS for eliminating of anti-leakages on image boundary. The DR-LSS does not require any expensive re-initialization and it is very high speed of operation. The RD-LSS results are compared with distance regularized level set evolution DRLSE1, DRLSE2 and DRLSE3. Extracted region of the kidney after segmentation is applied to Symlets (Sym12), Biorthogonal (bio3.7, bio3.9 & bio4.4) and Daubechies (Db12) lifting scheme wavelet subbands to extract energy levels. These energy level gives an indication about presence of stone in that particular location which significantly vary from that of normal energy level. These energy levels are trained by Multilayer Perceptron (MLP) and Back Propagation (BP) ANN to identify the type of stone with an accuracy of 98.6%.

scholarly journals A Fast, Fully Automated Prostate Boundary Segmentation Using Probabilistic Approaches In Ultrasound Images

2021 ◽  
Author(s):  
Rasa Vafaie
Keyword(s):  
Em Algorithm ◽  
Signal To Noise Ratio ◽  
Transrectal Ultrasound ◽  
Speckle Noise ◽  
Computational Time ◽  
Dice Similarity Coefficient ◽  
Ultrasound Images ◽  
Segmentation Method ◽  
Initial Model ◽  
Hybrid Segmentation

Segmentation of prostate boundaries in transrectal ultrasound (TRUS) images plays a great role in prostate cancer diagnosis. Due to the low signal to noise ratio and existence of the speckle noise in TRUS images, prostate image segmentation has proven to be an extremely difficult task. In this thesis report, a fast fully automated hybrid segmentation method based on probabilistic approaches is presented. First, the position of the initial model is automatically estimated using prostate boundary representative patterns. Next, the Expectation Maximization (EM) algorithm and Markov Random Field (MRF) theory are utilized in the deformation strategy to optimally fit the initial model on the prostate boundaries. A less computationally EM algorithm and a new surface smoothing technique are proposed to decrease the segmentation time. Successful experimental results with the average Dice Similarity Coefficient (DSC) value 93.9±2.7% and computational time around 9 seconds validate the algorithm.

Sign in / Sign up

Export Citation Format

Share Document