Acute appendicitis (AA) is one of the most prevalent surgical acute abdominal condition diseases. The recognition and segmentation of the inflamed appendix are important for AA diagnosis. However, it is a challenging task to find and segment the inflamed appendix from computed tomography (CT) images due to the varying sizes and shapes of different appendices and blurred borders with nearby tissues. To the best of our knowledge, the general expert segmentation model suffers due to the characterization of the inflamed appendix. Thus, we propose a deformable convolutional encoder-decoder network (DCED) for better recognition and segmentation of the inflamed appendix. The network consists of an encoder, a bottleneck, and a decoder. The encoder is composed of several convolutional neural network (CNN) layers to capture the local structural information. The bottleneck based on a vision transformer (ViT) focuses on the region of interest (ROI) using the global attention mechanism. The encoder and bottleneck modules effectively combine the local and global information of input data to locate the inflamed appendix. The decoder based on a deformable convolutional network (DCN) learns the varied boundary information, which helps to improve the accuracy of boundary segmentation. Extensive experimental results on a real-world AA dataset show that the proposed method yields the best average Dice similarity coefficient (DSC) of 71.29% and average Hausdorff Distance 95% (HD95) of 12.38 mm in comparison to state-of-the-art segmentation methods.

The accuracy of initial attitude calculated from initial alignment has an important influence on the performance of SINS/USBL integrated navigation system. Currently, two main problems need to be overcome for SINS to complete the in-motion coarse alignment assisted by USBL system. 1) As SINS cannot obtain accurate initial attitude during the initial alignment phase, so USBL system can only provide the relative position in acoustic frame, but not the precise absolute position in navigation frame. 2) The outliers contained in the USBL raw data will seriously affect the performance of coarse alignment. In this paper, an in-motion coarse alignment method for SINS/USBL using the relative position of USBL is creatively proposed. Firstly, after constructing the apparent displacement vector from the relative position provided by USBL system and the output of IMU, an in-motion vector observation model is constructed. Secondly, the proposed method can suppress the influence of outliers in USBL raw data based on the advantages of displacement vector. Finally, the experimental results of the simulation and field tests show that the proposed method can not only complete the in-motion coarse alignment with favorable performance, but also effectively suppress the influence of the outliers in USBL data on the coarse alignment.Note to Practitioners—This paper was motivated by the problem of rapid in-motion coarse alignment for the SINS/USBL integrated navigation system in an underwater environment. Due to the failure of GNSS signals in underwater environments, the existing in-motion coarse alignment algorithms assisted by GNSS position/velocity are no longer applicable. In this paper, an in-motion coarse alignment method assisted by USBL relative position is proposed for SINS in underwater environments. In this article, we compare and analyze the differences between the principle of USBL positioning and GNSS positioning. Based on the characteristics of USBL positioning principle, the displacement vectors are extracted from the relative position of USBL for coarse alignment in this paper. The designed method can effectively suppress the impact of noise and outliers in USBL data on coarse alignment performance. The results of the simulation and field tests indicate that the method investigated in this paper is feasible in practical engineering.

In this work, we propose a radiomics-guided neural network, XRadNet, for breast cancer molecular subtype prediction. XRadNet is a two-head neural network, with one for predicting molecular subtypes and the other for approximating radiomic features. In addition, a training scheme with radiomics guidance is proposed to improve performance. First, we conduct a series of experiments to test the radiomic feature learning capacity of different neural networks, which determines the backbone of XRadNet. Moreover, significant radiomic features are also determined according to radiomics and prior knowledge. XRadNet is subsequently pretrained in a self-supervised manner. The pretraining uses synthetic samples to train the backbone and radiomic feature regression head. This mitigates the impact of an insufficient number of samples. Finally, XRadNet is fine-tuned with a downstream real-world dataset by enabling all heads. Furthermore, a logistic regression is built with radiomic features and learned features, which provides a new way to interpreting the trained model with concepts familiar to radiologists. The experimental results show that XRadNet effectively predicts the four molecular subtypes of breast cancer. These results also demonstrate that the proposed training scheme yields better or competitive performance than those models pretrained on ImageNet or medical datasets.

When analyzing CT images of patients with suspected appendicitis, radiologists need to observe and examine consecutive 2D CT slices. Computer-assisted detection of the appendix in 2D CT slices significantly improve the diagnostic efficiency of radiologists. However, existing 2D medical image object detection methods primarily focus on spatial features within a single CT slice, which overlook spatial relationships between consecutive slices. We propose an Appendix Object Correction Network (AOCN) to refine predictions of universal object detectors. Although AOCN is a 2D network, it effectively leverages spatial relationships across consecutive CT slices. AOCN requires only a few training epochs to improve the accuracy of bounding boxes significantly, which offers advantages such as high scalability, low cost, and reduced training time. It consists of a global case feature learning module for extracting global feature map from the CT case and an object feature relation module for modeling the relationships between objects across slices. Experimental results demonstrate the effectiveness and efficiency of AOCN in correcting the output bounding boxes of several mainstream object detection networks, with a 6% to 14% improvement in Recall while requiring only a few training epochs.

Breast cancer is a heterogeneous disease, where molecular subtypes of breast cancer are closely related to the treatment and prognosis. Therefore, the goal of this work is to differentiate between luminal and non-luminal subtypes of breast cancer. The hierarchical radiomics network (HRadNet) is proposed for breast cancer molecular subtypes prediction based on dynamic contrast-enhanced magnetic resonance imaging. HRadNet fuses multilayer features with the metadata of images to take advantage of conventional radiomics methods and general convolutional neural networks. A two-stage training mechanism is adopted to improve the generalization capability of the network for multicenter breast cancer data. The ablation study shows the effectiveness of each component of HRadNet. Furthermore, the influence of features from different layers and metadata fusion are also analyzed. It reveals that selecting certain layers of features for a specified domain can make further performance improvements. Experimental results on three data sets from different devices demonstrate the effectiveness of the proposed network. HRadNet also has good performance when transferring to other domains without fine-tuning.

Multimodal image fusion plays an essential role in medical image analysis and application, where computed tomography (CT), magnetic resonance (MR), single-photon emission computed tomography (SPECT), and positron emission tomography (PET) are commonly-used modalities, especially for brain disease diagnoses. Most existing fusion methods do not consider the characteristics of medical images, and they adopt similar strategies and assessment standards to natural image fusion. While distinctive medical semantic information (MS-Info) is hidden in different modalities, the ultimate clinical assessment of the fusion results is ignored. Our MsgFusion first builds a relationship between the key MS-Info of the MR/CT/PET/SPECT images and image features to guide the CNN feature extractions using two branches and the design of the image fusion framework. For MR images, we combine the spatial domain feature and frequency domain feature (SF) to develop one branch. For PET/SPECT/CT images, we integrate the gray color space feature and adapt the HSV color space feature (GV) to develop another branch. A classification-based hierarchical fusion strategy is also proposed to reconstruct the fusion images to persist and enhance the salient MS-Info reflecting anatomical structure and functional metabolism. Fusion experiments are carried out on many pairs of MR-PET/SPECT and MR-CT images. According to seven classical objective quality assessments and one new subjective clinical quality assessment from 30 clinical doctors, the fusion results of the proposed MsgFusion are superior to those of the existing representative methods.

Acute appendicitis (AA) is one of the most prevalent surgical acute abdominal condition diseases. The treatment management of A A is highly dependent on the CT image diagnosis. However, the in-flamed appendix exhibits blurred boundaries with nearby tissue, varying shapes, and sizes. These properties require high robustness and generalization capability of inflamed appendix segmentation networks. In this paper, we propose a CNN-Transformer-based encoder-decoder segmentation network (LSSED) equipped with localized stochastic sensitivity (LSS) loss function and residual dilated paths (RD-Paths) to solve above problems. The proposed method effectively learns robust features of the input data by reducing the LSS of unseen samples. In addition, the RD-Paths capture multiscale feature information and reduce the semantic gap between the encoder and decoder, which improves the accuracy of the segmentation. Empirical studies on a real-world AA dataset show that our method yields the best performance in terms of average Dice similarity coefficient (DSC) and Hausdorff Distance of 95% (HD95) compared to several state-of-the-art segmentation networks.