Elysium Technologies Private Limitedelysiumtechnologies.com/wp-content/uploads/2015/08/2015_BioMed… · supervised segmentation methods. The proposed algorithm achieves a vessel

Elysium Technologies Private Limited Singapore | Madurai | Chennai | Trichy | Ramnad|

Erode | Tirunelveli| Dindigul|Sivakasi

http://www.elysiumtechnologies.com, [email protected]

http://www.elysiumtechnologies.com/


mailto:[email protected]





NT-037 A Low-Complexity Congestion Control and Scheduling Algorithm for Multihop Wireless















Automatic detection of the blood vessels in retinal images is a challenging task. In this paper a survey

has been made to help biomedical engineers and medical physicists. Here we have taken three different

methods for blood vessels segmentation, method (a) a novel method to segment the retinal blood vessel

is used, which overcome the variations in contrast in large and thin blood vessels. Method (b) a method

uses 2-D Gabor wavelet to enhance the vascular pattern and method(c) a method used is Star

Networked Pixel Tracking Algorithm which is used to eradicate a noise aligned in a vessel format.

These methods to segment the blood vessels so that we can easily diagnose and do treatment of several

eye disorders.

ETPL

BM - 001 A Survey on Blood Vessel Detection Methodologies in Retinal Images

We present a reversible data hiding technique for digital medical images. The idea is to embed the

header of the image or other data in the image itself, pursuing tamper-proofing capabilities and

inseparability. In particular, the proposed data hiding technique using Least Significant Bits (LSBs)

hides information into the Region of Interest (ROI) and preserves lost information in the Region of

Non Interest (RONI) for reversibility purposes. ROI pixels are accessed consecutively or in accordance

to a Just Noticeable Distortion (JND) model, while RONI pixels are accessed in a consecutive or

pseudo-random order. In the experiments with MRI and X-Ray images, we prove excellent fidelity and

100% reversibility of the ROI.

ETPL

BM - 002

Reversible blind data hiding for verifying integrity and authenticating MRI and

X-Ray images








The standard fuzzy C-means (FCM) algorithm does not fully utilize the spatial information for image

segmentation and is sensitive to noise especially in the presence of intensity inhomogeneity in magnetic

resonance imaging (MRI) images. The underlying reason is that a single fuzzy membership function

in FCM algorithm cannot properly represent pattern associations to all clusters. In this paper, we

present a spatial fuzzy C-means (SpFCM) algorithm for the segmentation of MRI images. The

algorithm utilizes spatial information from the neighbourhood of each pixel under consideration and is

realized by defining a probability function. A new membership function is introduced using this spatial

information to generate local membership values for each pixel. Finally, new clustering centers and

weighted joint membership functions are presented based on the local and global membership

functions. The resulting SpFCM algorithm solves the problem of sensitivity to noise and intensity

inhomogeneity in MRI data and thereby improves the segmentation results. The experimental results

on several simulated and real-patient MRI brain images show that the SpFCM algorithm has superior

performance on image segmentation when compared to some FCM-based algorithms.

ETPL

BM - 003

A spatial fuzzy C-means algorithm with application to MRI image segmentation








Robustness is one of the most important characteristics of computer-aided diagnosis systems designed

for dermoscopy images. However, it is difficult to ensure this characteristic if the systems operate with

multisource images acquired under different setups. Changes in the illumination and acquisition

devices alter the color of images and often reduce the performance of the systems. Thus, it is important

to normalize the colors of dermoscopy images before training and testing any system. In this paper, we

investigate four color constancy algorithms: Gray World, max-RGB, Shades of Gray, and General

Gray World. Our results show that color constancy improves the classification of multisource images,

increasing the sensitivity of a bag-of-features system from 71.0% to 79.7% and the specificity from

55.2% to 76% using only 1-D RGB histograms as features.

ETPL

BD - 004

Improving Dermoscopy Image Classification Using Color Constancy

Optic disc (OD) localization and segmentation are important in developing systems for automated

diagnosis of various serious ophthalmic pathologies. This paper presents a new, fast and robust

methodology for fully automatic localization and segmentation of the optic disc in fundus images. This

methodology locates the OD with a morphological approach based on the combination of vessel

convergence and intensity. The boundary of the OD is extracted by using distance regularized

narrowband level set evolution (DRLSE). This algorithm has been validated on three public databases.

The location procedure has a high success rate of 99.52% in the cases averagely and the segmentation

method improves the sensitivity and specificity to 99.92% and 96.49% respectively. The results

confirm the superiority of the proposed method over the conventional ways.

ETPL

BM - 005

Automatic localization and segmentation of optic disc in fundus image using

morphology and level set








Detection of brain tumor is one of the emerging topics of research in biomedical image processing.

Accurate detection is critical, especially when the tumor morphological changes remain subtle,

irregular and difficult to assess by clinical examination. This paper illustrates the ability of watershed

segmentation to separate the abnormal tissue from the normal surrounding tissue to get a real

identification of involved and noninvolved area that help the surgeon to distinguish the involved area

precisely. At the end of the process tumor is extracted from the MR image and its exact position and

shape are determined and various parameters like perimeter, eccentricity, entropy and centroid have

been calculated.

ETPL

BM - 006

Watershed segmentation brain tumor detection

Breast density measurement is an important aspect in breast cancer diagnosis as dense tissue has been

related to the risk of breast cancer development. The purpose of this study is to develop a method to

automatically compute breast density in breast MRI. The framework is a combination of image

processing techniques to segment breast and fibroglandular tissue. Intra- and interpatient signal

intensity variability is initially corrected. The breast is segmented by automatically detecting body-

breast and air-breast surfaces. Subsequently, fibroglandular tissue is segmented in the breast area using

expectation-maximization. A dataset of 50 cases with manual segmentations was used for evaluation.

Dice similarity coefficient (DSC), total overlap, false negative fraction (FNF), and false positive

fraction (FPF) are used to report similarity between automatic and manual segmentations. For breast

segmentation, the proposed approach obtained DSC, total overlap, FNF, and FPF values of 0.94, 0.96,

0.04, and 0.07, respectively. For fibroglandular tissue segmentation, we obtained DSC, total overlap,

FNF, and FPF values of 0.80, 0.85, 0.15, and 0.22, respectively. The method is relevant for researchers

investigating breast density as a risk factor for breast cancer and all the described steps can be also

applied in computer aided diagnosis systems.

ETPL

BM - 007

Breast Segmentation and Density Estimation in Breast MRI: A Fully Automatic

Framework








This paper presents a novel three-stage blood vessel segmentation algorithm using fundus photographs.

In the first stage, the green plane of a fundus image is preprocessed to extract a binary image after high-

pass filtering, and another binary image from the morphologically reconstructed enhanced image for

the vessel regions. Next, the regions common to both the binary images are extracted as the major

vessels. In the second stage, all remaining pixels in the two binary images are classified using a

Gaussian mixture model (GMM) classifier using a set of eight features that are extracted based on pixel

neighborhood and first and second-order gradient images. In the third postprocessing stage, the major

portions of the blood vessels are combined with the classified vessel pixels. The proposed algorithm is

less dependent on training data, requires less segmentation time and achieves consistent vessel

segmentation accuracy on normal images as well as images with pathology when compared to existing

supervised segmentation methods. The proposed algorithm achieves a vessel segmentation accuracy

of 95.2%, 95.15%, and 95.3% in an average of 3.1, 6.7, and 11.7 s on three public datasets DRIVE,

STARE, and CHASE_DB1, respectively.

ETPL

BM - 008

Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and

Sub image Classification








Automatic segmentation of brain tissues from MRI is of great importance for clinical application and

scientific research. Recent advancements in supervoxel-level analysis enable robust segmentation of

brain tissues by exploring the inherent information among multiple features extracted on the

supervoxels. Within this prevalent framework, the difficulties still remain in clustering uncertainties

imposed by the heterogeneity of tissues and the redundancy of the MRI features. To cope with the

aforementioned two challenges, we propose a robust discriminative segmentation method from the

view of information theoretic learning. The prominent goal of the method is to simultaneously select

the informative feature and to reduce the uncertainties of supervoxel assignment for discriminative

brain tissue segmentation. Experiments on two brain MRI datasets verified the effectiveness and

efficiency of the proposed approach.

ETPL

BM - 009

Discriminative Clustering and Feature Selection for Brain MRI Segmentation








This paper proposes a new computer-aided method for the skin lesion classification applicable to both

melanocytic skin lesions (MSLs) and nonmelanocytic skin lesions (NoMSLs). The computer-aided

skin lesion classification has drawn attention as an aid for detection of skin cancers. Several researchers

have developed methods to distinguish between melanoma and nevus, which are both categorized as

MSL. However, most of these studies did not focus on NoMSLs such as basal cell carcinoma (BCC),

the most common skin cancer and seborrheic keratosis (SK) despite their high incidence rates. It is

preferable to deal with these NoMSLs as well as MSLs especially for the potential users who are not

enough capable of diagnosing pigmented skin lesions on their own such as dermatologists in training

and physicians with different expertise. We developed a new method to distinguish among melanomas,

nevi, BCCs, and SKs. Our method calculates 828 candidate features grouped into three categories:

color, subregion, and texture. We introduced two types of classification models: a layered model that

uses a task decomposition strategy and flat models to serve as performance baselines. We tested our

methods on 964 dermoscopy images: 105 melanomas, 692 nevi, 69 BCCs, and 98 SKs. The layered

model outperformed the flat models, achieving detection rates of 90.48%, 82.51%, 82.61%, and

80.61% for melanomas, nevi, BCCs, and SKs, respectively. We also identified specific features

effective for the classification task including irregularity of color distribution. The results show promise

for enhancing the capability of the computer-aided skin lesion classification.

ETPL

BM - 010

Four-Class Classification of Skin Lesions With Task Decomposition Strategy








For the dermoscopy image, uneven illumination will influence segmentation accuracy and lead to

wrong aided diagnosis result. In this paper, a no reference uneven illumination assessment metric is

proposed for dermoscopy images. Firstly, the distorted image is decomposed to illumination and

reflectance components through variational framework for Retinex (VFR). Then, the illumination

component is extracted by basis function fitting. Lastly, average gradient of the illumination

component (AGIC) is calculated as the uneven illumination metric. A series of experiments show that,

the proposed illumination extraction method is insensitive to the image content, and the proposed

metric delivers an accurate illumination assessment result.

ETPL

BM - 011

No Reference Uneven Illumination Assessment for Dermoscopy Images

Human foot plays vital role in our body movement. The peak pressure measurement of plantar surface

of human foot is very important for diagnosis of diseases and in research field for biomedical engineers.

Depending on footprint image parameters like A intercept, B intercept, Footprint Index(FPI) and

Footprint Geometry Index(FGI), Human foot can be classified in Flat Foot, Normal Foot and High arch

Foot. Hence using this result further diagnosis and treatment is possible for that individual patient gives

in an efficient way. These results are helpful for gait analysis and in sports biomechanics.

ETPL

BM - 012

Human footprint classification using image parameters








This paper proposes a new computer-aided method for the skin lesion classification applicable to both

melanocytic skin lesions (MSLs) and nonmelanocytic skin lesions (NoMSLs). The computer-aided

skin lesion classification has drawn attention as an aid for detection of skin cancers. Several researchers

have developed methods to distinguish between melanoma and nevus, which are both categorized as

MSL. However, most of these studies did not focus on NoMSLs such as basal cell carcinoma (BCC),

the most common skin cancer and seborrheic keratosis (SK) despite their high incidence rates. It is

preferable to deal with these NoMSLs as well as MSLs especially for the potential users who are not

enough capable of diagnosing pigmented skin lesions on their own such as dermatologists in training

and physicians with different expertise. We developed a new method to distinguish among melanomas,

nevi, BCCs, and SKs. Our method calculates 828 candidate features grouped into three categories:

color, subregion, and texture. We introduced two types of classification models: a layered model that

uses a task decomposition strategy and flat models to serve as performance baselines. We tested our

methods on 964 dermoscopy images: 105 melanomas, 692 nevi, 69 BCCs, and 98 SKs. The layered

model outperformed the flat models, achieving detection rates of 90.48%, 82.51%, 82.61%, and

80.61% for melanomas, nevi, BCCs, and SKs, respectively. We also identified specific features

effective for the classification task including irregularity of color distribution. The results show promise

for enhancing the capability of the computer-aided skin lesion classification.

ETPL

BM - 013

Topological Modeling and Classification of Mammographic Microcalcification

Clusters








Compressed sensing (CS) has been applied to magnetic resonance imaging for the acceleration of data

collection. However, existing CS techniques usually produce images with residual artifacts,

particularly at high reduction factors. In this paper, we propose a novel, two-stage reconstruction

scheme, which takes advantage of the properties of k-space data and under-sampling patterns that are

useful in CS. In this algorithm, the under-sampled k-space data is segmented into low-frequency and

high-frequency domains. Then, in stage one, using dense measurements, the low-frequency region of

k-space data is faithfully reconstructed. The fully reconstituted low-frequency k-space data from the

first stage is then combined with the high-frequency k-space data to complete the second stage

reconstruction of the whole of k-space. With this two-stage approach, each reconstruction inherently

incorporates a lower data under-sampling rate and more homogeneous signal magnitudes than

conventional approaches. Because the restricted isometric property is easier to satisfy, the

reconstruction consequently produces lower residual errors at each step. Compared with a conventional

CS reconstruction, for the cases of cardiac cine, brain and angiogram imaging, the proposed method

achieves a more accurate reconstruction with an improvement of 2-4 dB in peak signal-to-noise ratio

respectively, using reduction factors of up to 6.

ETPL

BM - 014

Compressed Sensing MRI via Two-stage Reconstruction








Automated and general medical image segmentation can be challenging because the foreground and

the background may have complicated and overlapping density distributions in medical imaging.

Conventional region-based level set algorithms often assume piecewise constant or piecewise smooth

for segments, which are implausible for general medical image segmentation. Furthermore, low

contrast and noise make identification of the boundaries between foreground and background difficult

for edge-based level set algorithms. Thus, to address these problems, we suggest a supervised

variational level set segmentation model to harness the statistical region energy functional with a

weighted probability approximation. Our approach models the region density distributions by using

the mixture-of-mixtures Gaussian model to better approximate real intensity distributions and

distinguish statistical intensity differences between foreground and background. The region-based

statistical model in our algorithm can intuitively provide better performance on noisy images. We

constructed a weighted probability map on graphs to incorporate spatial indications from user input

with a contextual constraint based on the minimization of contextual graphs energy functional. We

measured the performance of our approach on ten noisy synthetic images and 58 medical datasets with

heterogeneous intensities and ill-defined boundaries and compared our technique to the Chan-Vese

region-based level set model, the geodesic active contour model with distance regularization, and the

random walker model. Our method consistently achieved the highest Dice similarity coefficient when

compared to the other methods.

ETPL

BM - 015

Supervised Variational Model with Statistical Inference and Its Application in

Medical Image Segmentation








This paper presents an automated method for counting red blood cells present in a blood sample. The

proposed method addresses the problems of holes present in blood cells and overlapping characteristics

of the red blood cells. The procedure is quite simple and straightforward, which utilizes mathematical

morphological operations of erosion and dilation for performing different steps. It first thresholds a

gray scale image to obtain the binary image using the Otsu thresholding method, and then, performs

the hole filling process on the red blood cells if they have holes. Then, the process moves on to the job

of counting the red blood cells. For this, each red blood cell is extracted and its shape analysis is

performed to decide whether it is circular, non-circular, overlapping or just partially present in the

sample. If a cell is only partially present in the image, then it is discarded. In case of overlapping, the

number of cells in the overlapped area is determined. Several experimental results have been presented

to establish the effectiveness of the method. One of the important findings is that the proposed method

gives accurate count of red blood cells of the blood sample, and classifies each cell into one of the four

categories mentioned above.

ETPL

BM - 016

An automated method for counting and characterizing red blood cells using

mathematical morphology








Medical ultrasound imaging has transformed the disease identification in the human body in the last

few decades. The major setback for ultrasound medical images is speckle noise. Speckle noise is

created in ultrasound images due to numerous reflections of ultrasound signals from hard tissues of

human body. Speckle noise corrupts the medical ultrasound images dropping the detectable quality of

the image. An endeavor is made to recover the image quality of ultrasound medical images by using

block based hard and soft thresholding of wavelet coefficients. Medical ultrasound image is

transformed to wavelet domain using debauchee's mother wavelet. Divide the approximate and detailed

coefficients into uniform blocks of size 8×8, 16×16, 32×32 and 64×64. Hard and soft thresholding on

these blocks of approximate and detailed coefficients are applied. Inverse transformation to original

spatial domain produces a noise reduced ultrasound image. Experiments were conducted on medical

ultrasound images obtained from diagnostic centers in Vijayawada, India. Quality of improved images

in measured using peak signal to noise ratio (PSNR), image quality index (IQI), structural similarity

index (SSEVI).

ETPL

BM - 017

Block based thresholding in wavelet domain for denoising ultrasound medical

images

In this paper algorithm is proposed for detection of vessels present in a fundus image of an eye. Blood

vessels extraction and removal are used to detect the other artifacts like lesions, the fovea and optic

nerve. The proposed algorithm used the combination of different morphological operators which make

this method less complex and also computationally efficient. Two different channels of an image green

and L respectively are utilized to get the final vessel structure. This method also gives the region of

interest for macula which may make macula detection easy. The proposed algorithm is tested on

DRIVE data set of fundus image of an eye. The result gives good detection of vessel structure and the

proposed method is computationally efficient.

ETPL

BM - 018

Extraction of retinal vasculature by using morphology in fundus images








Wireless capsule endoscopy (WCE) is able to investigate the entire gastrointestinal tract including the

small bowel. To reduce the reviewing time of captured images by gastroenterologists and increasing

the accuracy rate for automatic detection of abnormalities, it is beneficial to remove regions which

have less or no clinical information of small bowel texture (i.e., uninformative regions). In this research

study, a multi-stage method including Chan-Vese, color range ratio, adaptive gamma correction

method (AGCM), canny color edge detection operator, and morphological processing is proposed to

detect these uninformative regions. The results support the effectiveness of the proposed method. In

conclusion, the proposed method is a simple method to implement and performed well in removing the

uninformative regions of small bowel images.

ETPL

BM - 019

Detection of uninformative regions in wireless capsule endoscopy images

Brain tumours are considered to be serious kind of disease in Medical field. Brain Tumours are reason

of the abnormal and uncontrolled division and growth of cells in the brain region itself. If this

uncontrolled growth becomes more than 60% then the patient is unable to recover. So, it is must to

have the fast and accurate detection of the brain tumour. Different algorithms are provided for the

tumour detection. The step for tumour detection starts with the acquisition of MRI scan image of

tumour. MRI image have the gray and white matter and the region affected by tumour is of high

intensity. This paper describes comparative study of various methods for tumour detection. Tumour

detection by Edge Detection gives the exact location of tumour and image segmentation plays an

important role in medical imaging. So, Segmentation can work efficiently for detecting and extracting

the tumour from MRI image of the patient.

ETPL

BM - 020

Performance analysis of various methods of tumour detection








Thank You!





Documents

Elysium Technologies Private Limitedelysiumtechnologies.com/wp-content/uploads/2015/08/2015_BioMed… · supervised segmentation methods. The proposed algorithm achieves a vessel