TP Rate Research Articles

New Method to Assist Discrimination of Liver Diseases by Spherical SOM with Mahalanobis Distance

Spherical SOM, an improved version of a kind of neutral network SOM, has successfully been applied to data analysis in a variety of fields achieving effective results. However, distance measure of commercial spherical SOM is limited to the Euclidean distance and it is not suitable enough to the analysis of biased data such as blood test results. The Mahalanobis distance is said to be effective for the analysis of such medical data. Therefore it is expected that better results should be obtained if spherical SOM with Mahalanobis distance is applied to the analysis of medical data. In this paper, we take blood test items as multi-dimensional vectors and convert the input data into Mahalanobis distance with the aim of developing an automated diagnosis system by spherical SOM with Mahalanobis distance as pseudo input data. Conversion of the input data into Mahalanobis distance ensures correct evaluations of the biased data of blood test results at the same time allowing automated diagnosis based on doctors’ intuitions and experiences. We have grouped subjects of diagnosis whose features were not well discriminated by conventional Mahalanobis distance and have administered detailed discrimination by the group and obtained better discrimination rates. While in the conventional studies TP rates for the following five categories, no liverrelated problem, hepatoma (liver cancer), acute hepatitis, chronic hepatitis and liver cirrhosis, were 100%, 70%, 100%, 80% and 60% respectively, they were 96%, 80%, 71%, 86% and 91% respectively with the proposed method. Significant results were obtained overall except for acute hepatitis.

Completely Automated Segmentation Approach for Breast Ultrasound Images Using Multiple-Domain Features

Lesion segmentation is a challenging task for computer aided diagnosis systems. In this article, we propose a novel and fully automated segmentation approach for breast ultrasound (BUS) images. The major contributions of this work are: an efficient region-of-interest (ROI) generation method is developed and new features to characterize lesion boundaries are proposed. After a ROI is located automatically, two newly proposed lesion features (phase in max-energy orientation and radial distance), combined with a traditional intensity-and-texture feature, are utilized to detect the lesion by a trained artificial neural network. The proposed features are tested on a database of 120 images and the experimental results prove their strong distinguishing ability. Compared with other breast ultrasound segmentation methods, the proposed method improves the TP rate from 84.9% to 92.8%, similarity rate from 79.0% to 83.1% and reduces the FP rate from 14.1% to 12.0%, using the same database. In addition, sensitivity analysis demonstrates the robustness of the proposed method.

Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images

Pulmonary nodules may indicate the early stage of lung cancer, and the progress of lung cancer causes associated changes in the shape and number of pulmonary blood vessels. The automatic segmentation of pulmonary nodules and blood vessels is desirable for chest computer-aided diagnosis (CAD) systems. Since pulmonary nodules and blood vessels are often attached to each other, conventional nodule detection methods usually produce many false positives (FPs) in the blood vessel regions, and blood vessel segmentation methods may incorrectly segment the nodules that are attached to the blood vessels. A method to simultaneously and separately segment the pulmonary nodules and blood vessels was developed and tested. A line structure enhancement (LSE) filter and a blob-like structure enhancement (BSE) filter were used to augment initial selection of vessel regions and nodule candidates, respectively. A front surface propagation (FSP) procedure was employed for precise segmentation of blood vessels and nodules. By employing a speed function that becomes fast at the initial vessel regions and slow at the nodule candidates to propagate the front surface, the front surface can be propagated to cover the blood vessel region with suppressed nodules. Hence, the resultant region covered by the front surface indicates pulmonary blood vessels. The lung nodule regions were finally obtained by removing the nodule candidates that are covered by the front surface. A test data set was assembled including 20 standard-dose chest CT images obtained from a local database and 20 low-dose chest CT images obtained from lung image database consortium (LIDC). The average extraction rate of the pulmonary blood vessels was about 93%. The average TP rate of nodule detection was 95% with 9.8 FPs/case in standard-dose CT image, and 91.5% with 10.5 FPs/case in low-dose CT image, respectively. Pulmonary blood vessels and nodules segmentation method based on local intensity structure analysis and front surface propagation were developed. The method was shown to be feasible for nodule detection and vessel extraction in chest CAD.

Study on Opposite Folded Plate Anaerobic Reactor in Treatment of Low Concentration Sewage

With the demands of quantity and quality for water are increasing rapidly and a lot of wastewater treatment processes are difficult to be used abroad. Therefore, how to enhance the efficiency and to reduce consumption is the key to solve these problems. For purpose of enhancing mass transfer in the system, the reactor was modified with the structure characteristic of opposite folded plate. and the system with the characteristic of multi-phase anaerobe of compartments longitudinally down reactor and two-double phase of sludge- biomembrane in every compartment. The results was when the HRT≥6h and the sludge retention time (SRT) was controlled 120 days, the pilot-scale opposite folded plate hybrid anaerobic reactor (OFPHAR) was Two-phase Anaerobic system. The trial results indicated that the optimal HRT was 6h at (25±2) °C, and the corresponding removal rates of COD, TP and TN removal rates were 78.58%, 35.15%, 39.17% respectively.

Computer-aided diagnosis for early-stage breast cancer by using Wavelet Transform

A high-sensitivity computer-aided diagnosis algorithm which can detect and quantify micro-calcifications for early-stage breast cancer is proposed in this research. The algorithm can be divided into two phases: image reconstruction and recognition on micro-calcification regions. For Phase I, the suspicious micro-calcification regions are separated from the normal tissues by wavelet layers and Renyi's information theory. The Morphology-Dilation and Majority Voting Rule are employed to reconstruct the scattered regions of suspicious micro-calcification. For Phase II, total 49 descriptors which mainly include shape inertia, compactness, eccentricity and grey-level co-occurrence matrix are introduced to define the characteristics of the suspicious micro-calcification clusters. In order to reduce the computation load, Principal Component Analysis (PCA) is used to transform these descriptors to a compact but efficient vector expression by linear combination method. The performance of proposed diagnosis algorithm is verified by intensive experiments upon realistic clinic patients. The efficacy of Back-propagation Neural Network classifier exhibits its superiority in terms of high true positive rate (TP rate) and low false positive rate (FP rate), in comparison to Bayes classifier.

The Conduct and Reporting of Meta-Analyses of Studies of Diagnostic Tests, and a Consideration of ROC Curves: Answers to the January 2010 Journal Club Questions

The Conduct and Reporting of Meta-Analyses of Studies of Diagnostic Tests, and a Consideration of ROC Curves: Answers to the January 2010 Journal Club Questions

Performance of pilot-scale vertical flow constructed wetlands treating simulated municipal wastewater: effect of various design parameters

Abstract Ten pilot-scale, cylindrical, vertical flow constructed wetland units, of diameter 0.82 m and height 1.5 m, were designed, constructed, and operated treating a simulated municipal wastewater in parallel experiments. The operation scheme was 2 days feeding and 6 days resting. The 10 wetland units had various porous media materials (i.e., carbonate material, material from river bed, zeolite, and bauxite), two vegetation types (i.e., common reeds and cattails), and three total thicknesses of the porous media (i.e., 50, 80, and 90 cm). Water quality samples were collected at the inlet and the outlet of each unit, and were analyzed in the laboratory for BOD5, COD, TKN, ammonia nitrogen, nitrate, nitrite, TP, and ortho-phosphate. This article presents the results obtained after operation of these systems for one full year. Organic matter removal proved to be very good in all 10 units, since it reached on the average 71.1% and 66.9% for BOD5 and COD, respectively. Nitrogen removal was also satisfactory (47.1% for TKN and 42.2% for NH4+—N). TP and ortho-phosphate retention rates reached about 36.9% and 37.9%, respectively.

낙동강 유역에 대한 일별 유달부하량 산정모델개발 II. 모델식의 활용

As analyzed the estimated values of the daily delivery loads from thirteen major side streams such as Naesung-river, Keumho-river, Hwang-river, Nam-river during five years (from 1999 to 2003), the daily BOD inflow into the main stream of Nakdong river in 2003 shows the highest quantity as 31.1 ton and the daily BOD inflows in 1999, 2000, 2001, and 2002 are 26.7 ton, 22.5 ton, 21.0 ton, 25.8 ton, respectively. The daily TN in-flow into the main stream of Nakdong river in 2003 shows also the highest quantity as 64.9 ton and the daily TN inflows in 1999, 2000, 2001, and 2002 are 55.19 ton, 46.27 ton, 39.5 ton, 53.38 ton, respectively. The daily TP inflow into the main stream of Nakdong river in 2003 shows the highest quantity as 2.70 ton likewise and the daily TP inflows in 1999, 2000, 2001, and 2002 are 2.17 ton, 1.87 ton, 1.60 ton, 2.10 ton, respectively The rate of BOD loads from each side main stream into the main stream of Nakdong river shows that the BOD loads of Keumho-river are the highest as the values range from 32.8 % (2002) <TEX>${\sim}$</TEX> 35.1 % (2003) and the BOD loads of Nam-river, Naesung-river, Hwang-river are high in the order named. The rate of TN loads to the main stream is also similar to the trend of BOD loads. The contribution of the TN loads of Geumho-river to the contamination of the main stream is also the highest having a range from 27.0 % (2002) to 28.8 % (1999) among the main side streams and the TN loads of Naesung-river, Nam-river, and Heachun-river are high in the order named. The rate of TP loads is quite different from the trend of BOD and TN loads. The TP rate of Keumho-river, however, is still the highest as ranging 58.6 % (2002) to 61.7 % (2003) and the river has the biggest portion (over 50%) of the entire pollution to the main stream of Nakdong river.

Identification of insect damaged wheat kernels using transmittance images

We used transmittance images and different learning algorithms to classify insect damaged and un-damaged wheat kernels. Using the histogram of the pixels of the wheat images as the feature, and the linear model as the learning algorithm, we achieved a false positive rate (1-specificity) of 0.2 at the true positive rate (sensitivity) of 0.8 and an area under the ROC curve (AUC) of 0.86. Combining the linear model and a radial basis function network in a committee resulted in a FP rate of 0.1 at the TP rate of 0.8 and an AUC of 0.92.