RESUMEN
Contrast-enhanced computed tomography (CE-CT) images are used extensively for the diagnosis of liver cancer in clinical practice. Compared with the non-contrast CT (NC-CT) images (CT scans without injection), the CE-CT images are obtained after injecting the contrast, which will increase physical burden of patients. To handle the limitation, we proposed an improved conditional generative adversarial network (improved cGAN) to generate CE-CT images from non-contrast CT images. In the improved cGAN, we incorporate a pyramid pooling module and an elaborate feature fusion module to the generator to improve the capability of encoder in capturing multi-scale semantic features and prevent the dilution of information in the process of decoding. We evaluate the performance of our proposed method on a contrast-enhanced CT dataset including three phases of CT images, (i.e., non-contrast image, CE-CT images in arterial and portal venous phases). Experimental results suggest that the proposed method is superior to existing GAN-based models in quantitative and qualitative results.
Asunto(s)
Arterias , Tomografía Computarizada por Rayos X , Humanos , Tomografía Computarizada por Rayos X/métodosRESUMEN
Accurate recognition of cervical cancer cells is of great significance to clinical diagnosis, but these existing algorithms are designed by low-level manual feature, and their performance improvements are limited an improved algorithm based on residual neural network is proposed to improve the accuracy of diagnosis. Firstly, momentum parameters are introduced into the training model; secondly, by changing the number of training samples, the recognition rate of the algorithm can be improved. Therefore, aiming at the task of object recognition under resource constrained condition, we optimize the design method of the network structure such as convolution operation, model parameter compression and enhancement of feature expression depth, and design and implement the lightweight network model structure for embedded platform. Our proposed deep network model can reduce the parameters of the model and the resources needed for operation under the condition of guaranteeing the precision. The experimental results show that the lightweight deep model has better performance than that of the existing comparison models, and it can achieve the model accuracy of 94.1% under the condition that the model with fewer parameters on cervical cells data set.
Asunto(s)
Algoritmos , Diagnóstico por Computador/instrumentación , Detección Precoz del Cáncer/métodos , Neoplasias del Cuello Uterino/diagnóstico , Femenino , Humanos , Redes Neurales de la ComputaciónRESUMEN
To solve the problem of location and segmentation of intervertebral discs in spinal MRI images, a method of intervertebral disc segmentation and degeneration classification diagnosis based on wavelet image denoising and independent component analysis-active appearance model (ICA-AAM) was proposed. Firstly, the spinal MRI image is decomposed by wavelet transform, and the noise is filtered by soft threshold method. Then, aiming at the inadequacy of PCA method in AAM in describing data details, ICA is used instead of PCA to model shape and texture models, and an improved AAM segmentation model is formed. Finally, the intervertebral discs in MRI images are segmented by AAM model, and the degeneration classification of intervertebral discs is diagnosed according to the gray level characteristics of the segmented region. The experimental results show that the method can accurately locate and segment the intervertebral disc region and make classification diagnosis.