Wei Guo

In medical image segmentation, conventional state-space-model-based Mamba networks suffer from long-range forgetting due to locally dependent scanning mechanisms, which compromises prediction consistency and segmentation accuracy when processing long sequences. To enhance long-range dependency modeling, this study proposes a Hierarchical Memory Mamba-UNet (H2M-UNet) integrating a novel Hierarchical Memory 2D (HM2D) scanning mechanism. HM2D introduces a four-branch parallel scanning strategy with differentiated functional roles to achieve multi-scale feature co-optimization. Specifically, a global scanning path is designed for low-resolution features obtained from down-sampling to strengthen long-range dependency modeling, a local refinement path is deployed on high-resolution skip-connection features to capture fine details, and the conventional dual-path scanning is retained for original-resolution features to preserve basic representations. Extensive experiments on the Synapse multi-organ and ACDC cardiac segmentation datasets validate the effectiveness of the proposed method. On Synapse, H2M-UNet achieves an average Dice of 81.79% and HD95 of 14.00, outperforming nnUNet, Swin-UNet, and UD-Mamba by 1.76%–4.00% in Dice and reducing HD95 by 3.88–20.14. On ACDC, it attains an average Dice of 91.33% and HD95 of 1.12, improving Dice by 0.12%–0.70% and de-creasing HD95 by 0.05–0.46 compared with baseline models. These results demonstrate that integrating the HM2D mechanism effectively mitigates long-range forgetting and enhances fine-grained feature preservation, leading to superior segmentation accuracy and boundary consistency in complex medical imaging scenarios. Our code is available at: https://github.com/fangxiao-yu/HMMamba.

Objective: The aim of the study is to investigate the values of intratumoral and peritumoral regions based on mammography and magnetic resonance imaging for the prediction of Ki-67 and human epidermal growth factor (HER-2) status in breast cancer (BC). Methods: Two hundred BC patients were consecutively enrolled between January 2017 and March 2021 and divided into training (n = 133) and validation (n = 67) groups. All the patients underwent breast mammography and magnetic resonance imaging screening. Features were derived from intratumoral and peritumoral regions of the tumor and selected using the least absolute shrinkage and selection operator regression to build radiomic signatures (RSs). Receiver operating characteristic curve analysis and the DeLong test were performed to assess and compare each RS. Results: For each modality, the combined RSs integrating features from intratumoral and peritumoral regions always showed better prediction performance for predicting Ki-67 and HER-2 status compared with the RSs derived from intratumoral or peritumoral regions separately. The multimodality and multiregional combined RSs achieved the best prediction performance for predicting the Ki-67 and HER-2 status with an area under the receiver operating characteristic curve of 0.888 and 0.868 in the training cohort and 0.800 and 0.848 in the validation cohort, respectively. Conclusions: Peritumoral areas provide complementary information to intratumoral regions of BC. The developed multimodality and multiregional combined RSs have good potential for noninvasive evaluation of Ki-67 and HER-2 status in BC.

Accurate liver segmentation is essential for radiation therapy planning of hepatocellular carcinoma and absorbed dose calculation. However, liver segmentation is a challenging task due to the anatomical variability in both shape and size and the low contrast between liver and its surrounding organs. Thus we propose a convolutional neural network (CNN) for automated liver segmentation. In our method, fractional differential enhancement is firstly applied for preprocessing. Subsequently, an initial liver segmentation is obtained by using a CNN. Finally, accurate liver segmentation is achieved by the evolution of an active contour model. Experimental results show that the proposed method outperforms existing methods. One hundred fifty CT scans are evaluated for the experiment. For liver segmentation, Dice of 95.8%, true positive rate of 95.1%, positive predictive value of 93.2%, and volume difference of 7% are calculated. In addition, the values of these evaluation measures show that the proposed method is able to provide a precise and robust segmentation estimate, which can also assist the manual liver segmentation task.

The existing CNN-based segmentation methods use the object regions alone as the labels to train their networks, and the potentially useful boundaries annotated by radiologists are not used directly during the training. Thus, we proposed a framework of double U-Nets to integrate object regions and boundaries for more accurate segmentation. The proposed network consisted of a down-sampling path followed by two symmetric up-sampling paths. The down-sampling path learned the low-level features of regions and boundaries, and two up-sampling paths learned the high-level features of regions and boundaries, respectively. The outputs from the down-sampling path were concatenated with the corresponding ones from two up-sampling paths by skip connections. The outputs of double U-Nets were the predicted probability images of object regions and boundaries, and they were integrated to calculate the dice loss with the corresponding labels. The proposed double U-Nets were evaluated on two datasets: 247 radiographs for the segmentation of lungs, hearts, and clavicles, and 284 radiographs for the segmentation of pelvises. Compared with the baseline U-Net, our double U-Nets improved the mean dices and reduced the 90% Hausdorff distances for the “difficult” objects (lower lungs, clavicles, and pelvises), and the integration of “difficult” object regions and boundaries can improve the segmentation results compared with the use of object regions alone. However, for the “easy” objects (entire lungs and hearts) or “very difficult” objects (pelvises in lateral and implanted images), the integration did not improve the segmentation performance.

In today’s cyber world, worms pose a great threat to the global network infrastructure. In this paper, we propose a worm detection system based on deep learning. It includes two main modules: one worm detection module based on a convolutional neural network (CNN) and one automatic worm signature generation module based on a deep neural network (DNN). In the CNN-based worm detection module, we propose three kinds of data preprocessing methods: frequency processing, frequency weighted processing, and difference processing, and use CNN to train the model for worm detection. In the DNN-based worm signature generation module, there are two phrase:DNN is firstly utilized for training the model with worm payloads and their corresponding signatures as input in the training phrase. After worm payloads are fed into the trained DNN model in the test phrase, worm signatures are generated by our proposed Signature Beam Search algorithm. In the experiment, we firstly analyzed the impact of different data preprocessing methods and the number of convolution-pooling layers in the CNN model on the worm detection performance. Then we analyzed the effects of different signatures in the DNN algorithm on the automatic generation of worm signatures. Experiments show that the generated signatures have a good detection performance.

With the rapid development of the Internet era, the number of malware has reached an unprecedented peak, and therefore malware is threatening global network security seriously. In this paper, we propose an Android malware detection approach based on SIMGRU, which belongs to the static detection approach. The similarity of clustering is widely used in static analysis of android malware, so we introduce the similarity to improve Gated Recurrent Unit (GRU), and obtain three different structures of SimGRU: InputSimGRU, HiddenSimGRU, and InputHiddenSimGRU. The InputHiddenSimGRU is the combination of InputSimGRU and HiddenSimGRU. The experiment shows that InputSimGRU, HiddenSimGRU, and InputHiddenSimGRU outperform the conventional GRU model and other methods.