• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.239-248
• /
• 2010

Leukocyte in blood smear image provides significant information to doctors for diagnosis of patient health status. Therefore, it is necessary step to separate leukocyte from blood smear image among various blood cells for early disease prediction. In this paper, we present a saliency map and stepwise region merging based leukocyte segmentation method. Since leukocyte region has salient color and texture, we create a saliency map using these feature map. Saliency map is used for sub-image separation. Then, clustering is performed on each sub-image using mean-shift. After mean-shift is applied, stepwise region-merging is applied to particle clusters to obtain final leukocyte nucleus. The experimental results show that our system can indeed improve segmentation performance compared to previous researches with average accuracy rate of 71%.

• Journal of Biomedical Engineering Research
• /
• v.40 no.5
• /
• pp.179-188
• /
• 2019

In ultrasound telemedicine, it is important to reduce the size of the data by compressing the ultrasound image when sending it. Ultrasound images can be divided into image context and other information consisting of patient ID, date, and several letters. Between them, ultrasound context is very important information for diagnosis and should be securely preserved as much as possible. In several previous papers, ultrasound compression methods were proposed to compress ultrasound context and other information into different compression parameters. This ultrasound compression method minimized the loss of ultrasound context while greatly compressing other information. This paper proposed the method of automatic segmentation of ultrasound context to overcome the limitation of the previously described ultrasound compression method. This algorithm was designed to robust for various ultrasound device and to enable real-time operation to maintain the benefits of ultrasound imaging machine. The operation time of extracting ultrasound context through the proposed segmentation method was measured, and it took 311.11 ms. In order to optimize the algorithm, the ultrasound context was segmented with down sampled input image. When the resolution of the input image was reduced by half, the computational time was 126.84 ms. When the resolution was reduced by one-third, it took 45.83 ms to segment the ultrasound context. As a result, we verified through experiments that the proposed method works in real time.

• Journal of Biomedical Engineering Research
• /
• v.24 no.4
• /
• pp.259-266
• /
• 2003

Non-rigid registration between different modality images with shape deformation can be used to diagnosis and study for inter-patient image registration, longitudinal intra-patient registration, and registration between a patient image and an atlas image. This paper proposes a hierarchical registration method using bodily tissue based segmentation for registration between color images and CT images of the Visible Human leg areas. The cross-sectional color images and the axial CT images are segmented into three distinctive bodily tissue regions, respectively: fat, muscle, and bone. Each region is separately registered hierarchically. Bounding boxes containing bodily tissue regions in different modalities are initially registered. Then, boundaries of the regions are globally registered within range of searching space. Local boundary segments of the regions are further registered for non-rigid registration of the sampled boundary points. Non-rigid registration parameters for the un-sampled points are interpolated linearly. Such hierarchical approach enables the method to register images efficiently. Moreover, registration of visibly distinct bodily tissue regions provides accurate and robust result in region boundaries and inside the regions.

• Journal of Biomedical Engineering Research
• /
• v.13 no.1
• /
• pp.19-24
• /
• 1992

Lineacgrams are diagnostic films taken using X-ray from the linear accelerator with the patient in the treatment position to assure that the treatment is being delivered in accordance with the treatment prescription. But the image quality of the lineacgram is so bad because of the high X-ray energy. This paper presents a new algorithm that enhances the image of lineacgram. Thls algorithm calculates optimal threshold value which is used for segmentation of lineacgram using co-occurrence matrix and enhances the image Inside and outside treatment area preserving treatments boundary.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.176-181
• /
• 2023

During cancer treatment, the patient's response to drugs appears differently at the cellular level. In this paper, an image-based cell phenotypic feature quantification and key feature selection method are presented to predict the response of patient-derived cancer cells to a specific drug. In order to analyze the viability characteristics of cancer cells, high-definition microscope images in which cell nuclei are fluorescently stained are used, and individual-level cell analysis is performed. To this end, first, image stitching is performed for analysis of the same environment in units of the well plates, and uneven brightness due to the effects of illumination is adjusted based on the histogram. In order to automatically segment only the cell nucleus region, which is the region of interest, from the improved image, a superpixel-based segmentation technique is applied using the fluorescence expression level and morphological information. After extracting 242 types of features from the image through the segmented cell region information, only the features related to cell viability are selected through the ReliefF algorithm. The proposed method can be applied to cell image-based phenotypic screening to determine a patient's response to a drug.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.45-51
• /
• 2005

This paper emphasizes on the accomplishment of compensated proton density image and T2 weighted image taken from the shrinkage surface of the Brain. From the images, the Brain's surface shrinkage in the normal image and the surface shrinkage in the abnormal image can be observed. After the separation of white matter, gray matter, and CSF, this algorithm calculates the volume of each of them automatically. Results are subdivided into particular ages and saved in the database to be analyzed and to be processed statistically. Therefore, by using this algorithm the normal and abnormal stages can be detected in the early stages to diagnose. This result easily discernment Alzheimer patient and is useful for Alzheimer diagnostic and early detection.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.11
• /
• pp.2051-2057
• /
• 2007

In Oriental medicine, the status of a tongue is the important indicator to diagnose one's health like physiological and clinicopathological changes of inner parts of the body. The method of tongue diagnosis is not only convenient but also non-invasive and widely used in Oriental medicine. However, tongue diagnosis is affected by examination circumstances a lot like a light source, patient's posture and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue is inevitable but difficult since the colors of a tongue, lips and skin in a mouth are similar. The proposed method includes preprocessing, graph-based over-segmentation, detecting positions with a local minimum over shading, detecting edge with color difference and estimating edge geometry from the probable structure of a tongue, where preprocessing performs down-sampling to reduce computation time, histogram equalization and edge enhancement. A tongue was segmented from a face image with a tongue from a digital tongue diagnosis system by the proposed method. According to three oriental medical doctors' evaluation, it produced the segmented region to include effective information and exclude a non-tongue region. It can be used to make an objective and standardized diagnosis.

• Journal of International Society for Simulation Surgery
• /
• v.3 no.1
• /
• pp.1-8
• /
• 2016

In the field of Radiology, the Computer Aided Diagnosis is the technology which gives valuable information for surgical purpose. For its importance, several computer vison methods are processed to obtain useful information of images acquired from the imaging devices such as X-ray, Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These methods, called pattern recognition, extract features from images and feed them to some machine learning algorithm to find out meaningful patterns. Then the learned machine is then used for exploring patterns from unseen images. The radiologist can therefore easily find the information used for surgical planning or diagnosis of a patient through the Computer Aided Diagnosis. In this paper, we present a review on three widely-used methods applied to Computer Aided Diagnosis. The first one is the image processing methods which enhance meaningful information such as edge and remove the noise. Based on the improved image quality, we explain the second method called segmentation which separates the image into a set of regions. The separated regions such as bone, tissue, organs are then delivered to machine learning algorithms to extract representative information. We expect that this paper gives readers basic knowledges of the Computer Aided Diagnosis and intuition about computer vision methods applied in this area.

• Korea Journal of Hospital Management
• /
• v.17 no.2
• /
• pp.21-33
• /
• 2012

Purpose : This study aims to suggest application of patients DB to hospital marketing by performing market segmentation and selecting target market. Consequently help to establish suited strategy of marketing. Method : 14,072 patients hospitalized in a University Medical Center were recruited into this study. In order to classify the customer groups, cluster analysis was used with RFM(Recency, Frequency, Monetary) model, and 1-way ANOVA verified the differences among groups. And then, sociodemographical status, healthcare utilization and diagnosis(ICD-10) of each group were compared to draw a marketing strategy. Results : Four groups were classified through clustering analysis, and'high use and high profit' and'low use and high profit' groups were selected as a target market. The features of target market were as follows, the female proportion was high; used a private room; hospitalized through the emergency room; had operation; length of stay was long; had many comorbidity and cooperative treatment. There was difference in each feature of target market: as for the'high use and high profit' group, many patients were diagnosed with 'certain infectious and parasitic diseases'; and as for the'low use and high profit'group, the proportion of patients who purchased'industrial accident compensation insurance'and'auto insurance'was relatively high; many patients were diagnosed with'Injury, poisoning and certain other consequences of external causes'. Conclusion : It is needed to establish'positioning' strategy by monitoring and communicating with'high use and high profit' group. And for the case of'low use and high profit' group, it is necessary to make a follow-up management and lead them to have a medical check-up.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.24-34
• /
• 2019

In this research, a practical deep learning framework to differentiate the lesions and nodules in breast acquired with ultrasound imaging has been proposed. 7408 ultrasound breast images of 5151 patient cases were collected. All cases were biopsy proven and lesions were semi-automatically segmented. To compensate for the shift caused in the segmentation, the boundaries of each lesion were drawn using Fully Convolutional Networks(FCN) segmentation method based on the radiologist's specified point. The data set consists of 4254 benign and 3154 malignant lesions. In 7408 ultrasound breast images, the number of training images is 6579, and the number of test images is 829. The margin between the boundary of each lesion and the boundary of the image itself varied for training image augmentation. The training images were augmented by varying the margin between the boundary of each lesion and the boundary of the image itself. The images were processed through histogram equalization, image cropping, and margin augmentation. The networks trained on the data with augmentation and the data without augmentation all had AUC over 0.95. The network exhibited about 90% accuracy, 0.86 sensitivity and 0.95 specificity. Although the proposed framework still requires to point to the location of the target ROI with the help of radiologists, the result of the suggested framework showed promising results. It supports human radiologist to give successful performance and helps to create a fluent diagnostic workflow that meets the fundamental purpose of CADx.