Background: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods: We present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN (Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet (Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN (Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. Results: Experiments show that our method is the best in terms of efficiency and accuracy (91.78%) compared to other methods. Conclusions: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.
Meningioma is the second most commonly encountered tumor type in the brain. There are three grades of meningioma by the standards of the World Health Organization. Preoperative grade prediction of meningioma is extraordinarily important for clinical treatment planning and prognosis evaluation. In this paper, we present a new deep learning model for assisting automatic prediction of meningioma grades to reduce the recurrence of meningioma. Our model is based on an improved LeNet-5 model of convolutional neural network (CNN) and does not require the extraction of the diseased tissue, which can greatly enhance the efficiency. To address the issue of insufficient and unbalanced clinical data of meningioma images, we use an oversampling technique which allows us to considerably improve the accuracy of classification. Experiments on large clinical datasets show that our model can achieve quite high accuracy (i.e., as high as 83.33%) for the classification of meningioma images.
24 December 2018 in Computational and Mathematical Methods in Medicine
In this paper, we propose a novel algorithm for medical image segmentation, which combines the density peaks clustering (DPC) with the fruit fly optimization algorithm, and it has the following advantages. Firstly, it avoids the problem of DPC that needs to artificially select parameters (such as the number of clusters) in its decision graph and thus can automatically determine their values. Secondly, our algorithm uses random step size, instead of the fixed step size as in the fruit fly optimization algorithm, which helps avoid falling into local optima. Thirdly, our algorithm selects the cut-off distance and the cluster centers using the image entropy value and can better capture the structures of the image. Experiments on benchmark dataset and proprietary dataset show that our algorithm can adaptively segment medical images with faster convergence and better robustness.
4 April 2022 in Computational and Mathematical Methods in Medicine
Brain tumors are the deadliest and most difficult to treat of all forms of cancer. Preoperative classification of brain tumors is conducive to the development of corresponding treatment plan. Take pituitary tumors as an example. Precisely judging the image data of pituitary tumor texture before surgery can provide a basis for the selection of surgical plan and prognosis. However, the existing methods require manual intervention, and the efficiency and accuracy are not high. In this paper, we proposed an automatic brain tumor texture diagnosis method for uneven sequence image data. First, for the small sample of pituitary tumor MRI image data, the T1 and T2 sequence data are uneven or missing; we used the CycleGAN model to perform data conversion between different domains to obtain a completely sampled MRI spatial sequence. Then, we used texture analysis+pseudo-label learning to label pituitary tumor data of some unknown labels. After that, we used the improved U-Net model based on CBAM to optimize feature extraction for pituitary tumor image data. Finally, we used the CRNN model to classify the degree of pituitary tumor texture based on the advantages of sequence data. The entire process only needs to provide labels for the entire sequence data, and the efficiency is greatly improved, with an accuracy rate of 94.23%.
Preoperative classification of brain tumors is critical to developing personalized treatment plans, however existing classification methods rely on manual intervention and often have problems with efficiency and accuracy, which may lead to misdiagnosis or delayed diagnosis in clinical practice and affect the therapeutic effect. We propose a fully automated approach to brain tumor magnetic resonance imaging (MRI) classification, consisted by a feature extractor based on the improved U-Net and a classifier based on convolutional recurrent neural network (CRNN). The encoder of the feature extractor based on dense block, is used to enhance feature propagation and reduce the number of parameters. The decoder uses residual block to reduce the weight of some features for improving the effect of MRI spatial sequence reconstruction, and avoid gradient disappearance. Skip connections between the encoder and the decoder effectively merge low-level features and high-level features. The extract feature sequence is input into the CRNN-based classifier for final classification. We assessed the performance of our method for grading glioma, glioma isocitrate dehydrogenase1 (IDH1) mutation status classification and pituitary tumor texture classification on two datasets, glioma or pituitary tumors collected in a local affiliated hospital and glioma imaging data from TCIA. Compared with commonly models and new models, our model achieves higher accuracy, with an accuracy of 90.72%, classified glioma IDH1 mutation status with an accuracy of 94.35%, and classified pituitary tumor texture with an accuracy of 94.64%.