Hong Ming Tsai

An automatic diagnostic system for CT liver image classification

Computed tomography (CT) images have been widely used for liver disease diagnosis. Designing and developing computer-assisted image processing techniques to help doctors improve their diagnosis has received considerable interests over the past years. In this paper, a CT liver image diagnostic classification system is presented which will automatically find, extract the CT liver boundary and further classify liver diseases. The system comprises a detect-before-extract (DBE) system which automatically finds the liver boundary and a neural network liver classifier which uses specially designed feature descriptors to distinguish normal liver, two types of liver tumors, hepatoma and hemageoma. The DBE system applies the concept of the normalized fractional Brownian motion model to find an initial liver boundary and then uses a deformable contour model to precisely delineate the liver boundary. The neural network is included to classify liver tumors into hepatoma and hemageoma. It is implemented by a modified probabilistic neural network (PNN) [MPNN] in conjunction with feature descriptors which are generated by fractal feature information and the gray-level co-occurrence matrix. The proposed system was evaluated by 30 liver cases and shown to be efficient and very effective.

Identifying multiple abdominal organs from CT image series using a multimodule contextual neural network and spatial fuzzy rules

Identifying abdominal organs is one of the essential steps in visualizing organ structure to assist in teaching, clinical training, diagnosis, and medical image retrieval. However, due to partial volume effects, gray-level similarities of adjacent organs, contrast media affect, and the relatively high variations of organ position and shape, automatically identifying abdominal organs has always been a high challenging task. To conquer these difficulties, this paper proposes combining a multimodule contextual neural network and spatial fuzzy rules and fuzzy descriptors for automatically identifying abdominal organs from a series of CT image slices. The multimodule contextual neural network segments each image slice through a divide-and-conquer concept, embedded within multiple neural network modules, where the results obtained from each module are forwarded to other modules for integration, in which contextual constraints are enforced. With this approach, the difficulties arising from partial volume effects, gray-level similarities of adjacent organs, and contrast media affect can be reduced to the extreme. To address the issue of high variations in organ position and shape, spatial fuzzy rules and fuzzy descriptors are adopted, along with a contour modification scheme implementing consecutive organ region overlap constraints. This approach has been tested on 40 sets of abdominal CT images, where each set consists of about 40 image slices. We have found that 99% of the organ regions in the test images are correctly identified as its belonging organs, implying the high promise of the proposed method.

Evaluation of predictive value of CLIP, Okuda, TNM and JIS staging systems for hepatocellular carcinoma patients undergoing surgery.

Background:  An accurate staging system is required to assess hepatocellular carcinoma (HCC) patients in order to benefit from hepatic resection before surgery. Cancer of the Liver Italian Program (CLIP) score was considered to be better than the Okuda staging system to predict survival. Japan Integrated Staging Score (JIS score) includes tumor, nodes, metastases (TNM) stage and Child–Pugh grade as a new staging system for HCC. The purpose of the present paper was to compare the CLIP, Okuda, TNM and JIS staging systems for HCC patients undergoing surgery.

Carpal tunnel syndrome assessed with diffusion tensor imaging: Comparison with electrophysiological studies of patients and healthy volunteers

The main goal of this study was to investigate the applicability of parameters derived from diffusion tension imaging (DTI) in diagnosing carpal tunnel syndrome (CTS). Forty subjects were recruited, of which 19 were normal controls and 21 belonged to the CTS group. DTI of median nerves evaluated at 4 levels of the wrist (distal radius, pisiform bone, middle portion of the carpal tunnel, and hamate bone) and conventional MRI of the wrist was performed in normal and CTS subjects in two finger postures (extension and flexion). Fractional anisotropy (FA) and apparent diffusion coefficient (ADC) were derived from DTI, and parameters related to abnormal hyperintensity of the median nerve were derived from conventional MRI. Electrophysiological tests, including nerve conduction velocity and F wave were also performed for comparison. The results of FA and ADC measurements did not depend on the measuring location and finger posture. Mean FA was decreased while mean ADC was increased by CTS. FA and ADC at the middle portion of the carpal tunnel was 0.47±0.05 and 1.37±0.12 (×10(-3) mm2/s) for the control group and 0.42±0.04 and 1.50±0.15 (×10(-3) mm2/s) for the CTS group, respectively. The linear correlations of FA and ADC versus electrophysiological indicators of CTS were significant (R2 ranged from 0.09 to 0.36), indicating FA and ADC from DTI had significant correlation with the existence and severity of CTS.

The role of transcatheter arterial embolization for patients with unresectable hepatocellular carcinoma: a nationwide, multicentre study evaluated by cancer stage

Background:  Transcatheter arterial embolization is a major palliative treatment for unresectable hepatocellular carcinoma, but the survival benefit of transcatheter arterial embolization is controversial.

The role of transcatheter arterial embolization in patients with resectable hepatocellular carcinoma: a nation-wide, multicenter study

Abstract: Purpose: The role of transcatheter arterial embolization (TAE) for patients with resectable hepatocellular carcinoma (HCC) is controversial. Analyzing a cohort of nation‐wide data can delineate the beneficial effect of TAE for those patients.

Meckel's diverticulum associated with ileal volvulus in a neonate.

Abstract.A symptomatic Meckels diverticulum (MD) may manifest as an intestinal obstruction secondary to a volvulus. We describe a case of a meconium-impacted MD associated with inflammatory adhesions to adjacent viscera that presented as an intestinal obstruction in a 4-h-old infant secondary to an ileal volvulus with resultant infarction of the diverticulum and ileal segment.

Discrimination of Liver Diseases from CT Images Based on Gabor Filters

In this paper, a liver disease diagnosis based on Gabor filters is proposed. Three kinds of liver diseases are identified: cyst, hepatoma and cavernous hemangioma. The diagnosis scheme includes two steps: features extraction and classification. The features derived from Gabor filters are obtained from the ROIs among the normal and abnormal CT images. In the classification step the SVM classifier is used to discriminate the different liver disease types. Finally the receiver operating characteristic curve is employed to evaluate the performance of the diagnosis system. The effectiveness of the proposed method is demonstrated through experimental results on CT images including 76 liver cysts, 30 hepatomas, and 40 cavernous hemangiomas. From the results, we can observe that the discrimination rate of cyst is higher than the other diseases, and the classification accuracy decreases slightly between cavernous hemangiomas and hepatomas. However, a normal region can be discriminated from all of these diseases entirely

Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation

Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66% and 87.73% in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86% and 100% by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes.

A retrospective study of pulmonary infarction in patients with systemic lupus erythematosus from southern Taiwan

Since large-scale reports of pulmonary infarction in systemic lupus erythematosus (SLE) are limited, a retrospective study was performed for this manifestation in 773 hospitalized patients in southern Taiwan from 1999 to 2009. Pulmonary infarction was defined as the presence of pulmonary embolism, persistent pulmonary infiltrates, and characteristic clinical symptoms. Demographic, clinical, laboratory, and radiological images data were analyzed. There were 12 patients with pulmonary embolism and 9 of them had antiphospholipid syndrome (APS). Six patients (19 to 53 years, average 38.2 ± 12.6) with 9 episodes of lung infarction were identified. All cases were APS and four episodes had coincidental venous thromboembolism. There were four episodes of bilateral infarction and seven episodes of larger central pulmonary artery embolism. Heparin therapy was routinely prescribed and thrombolytic agents were added in two episodes. Successful recovery was noted in all patients. In conclusion, there was a 0.8% incidence of pulmonary infarction in patients with SLE, all with the risk factor of APS. Differentiation between pulmonary infarction and pneumonia in lupus patients should be made; they have similar chest radiography with lung consolidation but require a different clinical approach in management. Although this report is a retrospective study with relatively small numbers of lupus patients with lung infarcts, our observation might provide beneficial information on the clinical features and radiological presentations during the disease evolution of pulmonary infarction in SLE with APS.