ABSTRACT
In order to overcome the difficulty in lung parenchymal segmentation due to the factors such as lung disease and bronchial interference, a segmentation algorithm for three-dimensional lung parenchymal is presented based on the integration of surfacelet transform and pulse coupled neural network (PCNN). First, the three-dimensional computed tomography of lungs is decomposed into surfacelet transform domain to obtain multi-scale and multi-directional sub-band information. The edge features are then enhanced by filtering sub-band coefficients using local modified Laplacian operator. Second, surfacelet inverse transform is implemented and the reconstructed image is fed back to the input of PCNN. Finally, iteration process of the PCNN is carried out to obtain final segmentation result. The proposed algorithm is validated on the samples of public dataset. The experimental results demonstrate that the proposed algorithm has superior performance over that of the three-dimensional surfacelet transform edge detection algorithm, the three-dimensional region growing algorithm, and the three-dimensional U-NET algorithm. It can effectively suppress the interference coming from lung lesions and bronchial, and obtain a complete structure of lung parenchyma.
Subject(s)
Algorithms , Neural Networks, Computer , Tomography, X-Ray ComputedABSTRACT
Mild encephalitis/encephalopathy with reversible splenial lesion has special clinical-imaging features. According to the extent of lesion involvement, it can be divided into type Ⅰ and type Ⅱ. Clinically, type Ⅰ is more common, and type Ⅱ is rare. A rare case of recurrent type Ⅱ mild encephalitis/encephalopathy with reversible splenial lesion is reported. The patient presented with typical type Ⅱ mild encephalitis/encephalopathy with reversible splenial lesion for the first time, involving the corpus callosum and the deep white matter, and the lesions disappeared after a short-term reexamination. Two years later, the lesions recurred, and the scope of the lesions was similar to that of the first time, and the lesions disappeared after a short-term reexamination. The clinical and imaging findings are analyzed in combination with relevant literatures review in order to deepen the understanding of the disease and improve the level of diagnosis and treatment.
ABSTRACT
Objective To analyze the computed tomography (CT)characteristics of splenic lymphangioma and the association be-tween CT findings and pathological results.Methods The CT characteristics and pathological findings of 9 patients with splenic lym-phangioma were retrospectively analyzed.Results There were 8 cavernous lymphangioma and 1 cystic lymphangioma.Of the 9 ca-ses,it revealed that the percentage of blood vessel elements ranging from 5% to 50% via microscope.CT found 2 cases were with single lymphangioma,3 with multiple lesions,exhibiting as round or round-like mass;4 cases were found with diffuse lymphangio-ma and different size of cystic masses distributed across spleen.Five of the 9 cases who were with single or multiple lymphangioma showed circular and thin line-like cyst wall,while the remaining 4 cases showed latticed cyst wall in CT characteristics.The content in the cysts were with uneven density in all the 9 cases with CT value ranging from 10 to 40 HU,3 of which combined with sand-like calcification.Enhancement scanning found two characteristics:(a)cyst wall and separation were mildly enhanced,especially in the delayed phase;(b)the content in the cyst presents anomalous small patchy and mild enhancement.The enhancement of the content in the cyst did not change as the increasing of blood vessel composition.Conclusion CT examination will help the diagnosis of splenic lymphangioma and is of significance in informing clinical treatment.