The paper proposed by Nay Chi Lynn in the year 2017 presents a methodological approach for the classification of pigmented skin lesions in dermoscopic images.Melanoma, one type of skin cancer is considered the most dangerous form of skin cancer occurred in humans. However it is curable if the person detects early. These cancers are caused by undesirable damage to DNA by skin cells (usually caused by ultraviolet light from the sun or solarium), when skin cells multiply rapidly, causing mutations (genetic defects), forming malignant tumors.
It is important to develop a technology for computerized image analysis because to minimize the diagnostic error caused by the quantitative analysis of tumors, highly complexity of visual interpretation and subjectivity.
Firstly, the image of the skin to remove unwanted hair and noise, and then the segmentation process is performed to extract the affected area. For detecting the melanoma skin cancer, the meanshift algorithm that segments the lesion from the entire image is used in this study. Feature extraction is then performed by underlying ABCD dermatology rules. After extracting the features from the lesion, feature selection algorithm has been used to get optimized features in order to feed for classification stage.
127 our experts are availableright now
Those selected optimized features are classified using kNN, decision tree and SVM.classifiers. This diagnosis research work includes both segmentation with MeanShift algorithm and classification using KNN decision tree, SVM with the highest accuracy of 78.2% which shows promising results.
The paper proposed by Aye Min in the year 2017,presents the method of image enhancement and tumor segmentation of brain. In medical field, segmentation of brain regions and detection of brain tumor are very challenging tasks because of its complex structure. Magnetic resonance imaging (MRI) provides the detailed information about brain anatomy. Proper brain tumor segmentation using MR brain images helps in identifying exact size and shape of Brain tumor, this intern helps in diagnosis and treatment of brain tumor.
Manual segmentation of tumors requires a long period of time, even for a qualified specialist. Fully automated segmentation and quantitative analysis of tumors, therefore, are highly beneficial maintenance. However, it is also very difficult due to the large variety of anatomical structures and low contrast of current imaging techniques that create the distinction between normal and tumor regions. Its objective is to create a trustworthy procedure detection of tumors of a multimodal MRI record based on a controlled machine study the methods using a data set containing MICCAI Brats images with ground truth, provided by human experts.
The paper is used to investigate deep learning for DME recognition on OCT images— Diabetic Macular Edema (DME) is a common eye disease that causes irreversible vision loss for diabetic patients, if left untreated. Thus, early diagnosis of DME could help in early treatment and prevent blindness. This paper aims to create a framework based on deep learning for DME recognition on Spectral Domain Optical Coherence Tomography (SD-OCT) images through transfer learning.
First, images are pre- processed: denoised using Block-Matching and 3-Dimension filtering (BM3D) and cropped through image boundary extraction. Later, features are extracted using CNN of AlexNet and finally images are classified using SVM classifier. The development of OCT which provides high resolution of retinal images for DME detection plus the adaptation of deep learning has proven to improve image classification with high performance of more than 90%.
Tongue image segmentation Thresholding, Clustering and Morphological operation Automatic computer-aided. Tongue diagnosis system gives more accuracy than conventional tongue diagnosis. Nerve segmentation Canny algorithm To find the nerve very easily because it includes segmentation of nerves in ultrasound image.
MRI image enhancement and tumor segmentation for Brain Adaptive k-means clustering and morphological operation Proper Brain tumor segmentation using MR Brain image helps in identifying exact size and shape of Brain tumor. Blood vessels segmentation Local Thresholding Blood vessel detection algorithm is to early detecting the diabetes in advanced stages by comparison of its states of retinal blood vessels. Measurement of Fetal Head Structures Thresholding Estimation the gestational age of fetus, predict expected deli very date, assess the fetal size and monitor growth.
Segmentation and classification of skin cancer Melanoma Mean shift algorithm, classification of cancer using KNN Decision tree, SVM To minimize the diagnostic error caused by the complexity of visual interpretation and subjectivity.
Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. Many methods are existing and still developing the new methods for the segmentation to overcome the shortcomings of the existing methods. Here various segmentation techniques are implemented using MRI images ,UltraSound images, Computed Tomography(CT) and Optical Coherent Tomography(OCT)
Images .Outcomes are depend on some input parameter like, threshold for the thresholding, number of cluster centers, and seed point for the region growing. Edge detection depends on discontinuity of gray level and on intensity variation on the gray scale images. Above explained methods give almost identical outcomes, when the inputs are accurate.
