Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues

Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image data is often expensive and time-consuming. In this study, we propose a co-optimization learning network (COL-Net) for Magnetic Resonance Imaging (MRI) segmentation of ischemic penumbra tissues. COL-Net base on the limited labeled samples and consists of an unsupervised reconstruction network (R), a supervised segmentation network (S), and a transfer block (T). The reconstruction network extracts the robust features from reconstructing pseudo unlabeled samples, which is the auxiliary branch of the segmentation network. The segmentation network is used to segment the target lesions under the limited labeled samples and the auxiliary of the reconstruction network. The transfer block is used to co-optimization the feature maps between the bottlenecks of the reconstruction network and segmentation network. We propose a mix loss function to optimize COL-Net. COL-Net is verified on the public ischemic penumbra segmentation challenge (SPES) with two dozen labeled samples. Results demonstrate that COL-Net has high predictive accuracy and generalization with the Dice coefficient of 0.79. The extended experiment also shows COL-Net outperforms most supervised segmentation methods. COL-Net is a meaningful attempt to alleviate the limited labeled sample problem in medical image segmentation.

Breast cancer X-ray image staging: based on efficient net with multi-scale fusion and cbam attention

With ever-progressing development period, image classification algorithms based on deep learning have shown good performance on some large datasets. In the development of classification algorithms, many proposals related to attention mechanism have greatly improved the accuracy of the model, and at the same time increased the interpretability of the network structure. However, on medical image data, the performance of the classification algorithm is not as expected, and the reason is that the fine-grained image data differs little among all classes, resulting that the knowledge domain is also hard to learn for models. We (1) proposed the Efficientnet model based on the cbam attention mechanism, and added a multi-scale fusion method; (2) applied the model to the breast cancer medical image data set, and completed the breast cancer classification task with high accuracy (Phase I, Phase II, Phase III, etc.); (3) Compared with other existing image classification algorithms, our method has the highest accuracy, thus the researchers conclude that EfficientNet with CBAM and multi-scale fusion will improve the classification performance. This result is helpful for deeper research on medical image processing and breast cancer staging.

Detection of Pediatric Femur Configuration on X-ray Images

In this paper, we present a fully automatic solution for denoting bone configuration on two-dimensional images. A dataset of 300 X-ray images of children’s knee joints was collected. The strict experimental protocol established in this study increased the difficulty of post-processing. Therefore, we tackled the problem of obtaining reliable information from medical image data of insufficient quality. We proposed a set of features that unambiguously denoted configuration of the bone on the image, namely the femur. It was crucial to define the features that were independent of age, since age variability of subjects was high. Subsequently, we defined image keypoints directly corresponding to those features. Their positions were used to determine the coordinate system denoting femur configuration. A complex keypoint detector was proposed, composed of two different estimator architectures: gradient-based and based on the convolutional neural network. The positions of the keypoints were used to determine the configuration of the femur on each image frame. The overall performance of both estimators working in parallel was evaluated using X-ray images from the publicly available LERA dataset.

Research on Application of Ultrasound Medical Imaging Technology in Big Data Mining of Regional Medical Imaging

Ultrasound medical imaging technology is one of the main methods of medical non-invasive diagnosis, and it is the focus of research in the medical field at home and abroad. Medical images have a large amount of data and contain a wealth of image feature information and rules, which need to be studied and understood. Therefore, the research of data mining technique for reading medical images has become a very important field in the interdisciplinary research of medical and computer science. The high resolution of medical images, the mass of data, and the complexity of image feature expressions make the research of data mining technology in medical images of great academic value and broad application prospects. At present, research on data mining for medical images has just started, and there are still many problems in the direct application of existing data mining methods. Researching and exploring the theoretical and practical problems of medical image data mining, such as data mining methods and algorithms suitable for medical image, which has significant and crucial value, and it is of great importance to help physicians in clinical diagnosis of medical images. This article introduces the background, definition and basic process of data mining technology, the characteristics of medical imaging data and the key techniques of medical image data mining. In view of the data mining research of human abdominal medical images is a completely new field, human abdominal imaging is the most complicated part of medical images. Solving the problem of abdominal imaging is of great value to the entire medical image. For regional medical image big data mining, we can use ultrasound images of the human abdomen. The clustering feature extraction algorithm and its implementation based on the approximate density structure of medical images proposed in this article, and innovative research results such as classification rule mining methods, are used to mine medical image data research, automatic diagnosis of clinical medical images, and early diagnosis of clinical medicine are of great significance.