In computed tomography (CT), metal artifacts pose a persistent challenge to achieving high-quality imaging. Despite advancements in metal artifact reduction (MAR) techniques, many existing approaches have not fully leveraged the intrinsic a priori knowledge related to metal artifacts, improved model interpretability, or addressed the complex texture of CT images effectively. To address these limitations, we propose a novel and interpretable framework, the wavelet-inspired oriented adaptive dictionary network (WOADNet). WOADNet builds on sparse coding with orientational information in the wavelet domain. By exploring the discriminative features of artifacts and anatomical tissues, we adopt a high-precision filter parameterization strategy that incorporates multiangle rotations. Furthermore, we integrate a reweighted sparse constraint framework into the convolutional dictionary learning process and employ a cross-space, multiscale attention mechanism to construct an adaptive convolutional dictionary unit for the artifact feature encoder. This innovative design allows for flexible adjustment of weights and convolutional representations, resulting in significant image quality improvements. The experimental results using synthetic and clinical datasets demonstrate that WOADNet outperforms both traditional and state-of-the-art MAR methods in terms of suppressing artifacts.

Automatic medical image segmentation plays a crucial role in clinical diagnosis and treatment. However, it is still a challenging task due to the complex interior characteristics ( e.g. , inconsistent intensity, low contrast, texture heterogeneity) and ambiguous external boundary structures. In this paper, we introduce a novel geometric structure learning mechanism (GSLM) to overcome the limitations of existing segmentation models that lack learning ”focus, path, and difficulty.” The geometric structure in this mechanism is jointly characterized by the skeleton-like structure extracted by the mask distance transform (MDT) and the boundary structure extracted by the mask distance inverse transform (MDIT). Among them, the skeleton-like and boundary pay attention to the trend of interior characteristics consistency and external structure continuity, respectively. With this idea, we design GSAL, a novel end-to-end geometric structure adversarial learning for robust medical image segmentation. GSAL has four components: a geometric structure generator, which yields the geometric structure to learn the most discriminative features that preserve interior characteristics consistency and external boundary structure continuity, skeleton-like and boundary structure discriminators , which enhance and correct the characterization of internal and external geometry to mutually promote the capture of global contextual dependencies, and a geometric structure fusion sub-network, which fuses the two complementary and refined skeleton-like and boundary structures to generate the high-quality segmentation results. The proposed approach has been successfully applied to three different challenging medical image segmentation tasks , including polyp segmentation , COVID-19 lung infection segmentation, and lung nodule segmentation. Extensive experimental results demonstrate that the proposed GSAL achieves favorably against most state-of-the-art methods under different evaluation metrics . The code is available at: https://github.com/DLWK/GSAL .

Semantic segmentation tasks often have multiple output hypotheses for a single input image. Particularly in medical images, these ambiguities arise from unclear object boundaries or differences in physicians' annotation. Learning the distribution of annotations and automatically giving multiple plausible predictions is useful to assist physicians in their decision-making. In this paper, we propose a semantic segmentation framework, PixelSeg, for modelling aleatoric uncertainty in segmentation maps and generating multiple plausible hypotheses. Unlike existing works, PixelSeg accomplishes the semantic segmentation task by sampling the segmentation maps pixel by pixel, which is achieved by the PixelCNN layers used to capture the conditional distribution between pixels. We propose (1) a hierarchical architecture to model high-resolution segmentation maps more flexibly, (2) a fast autoregressive sampling algorithm to improve sampling efficiency by 96.2, and (3) a resampling module to further improve predictions' quality and diversity. In addition, we demonstrate the great advantages of PixelSeg in the novel area of interactive uncertainty segmentation, which is beyond the capabilities of existing models. Extensive experiments and state-of-the-art results on the LIDC-IDRI and BraTS 2017 datasets demonstrate the effectiveness of our proposed model.

Medical image segmentation tasks often have more than one plausible annotation for a given input image due to its inherent ambiguity. Generating multiple plausible predictions for a single image is of interest for medical critical applications. Many methods estimate the distribution of the annotation space by developing probabilistic models to generate multiple hypotheses. However, these methods aim to improve the diversity of predictions at the expense of the more important accuracy. In this paper, we propose a novel probabilistic segmentation model, called Joint Probabilistic U-net, which successfully achieves flexible control over the two abstract conceptions of diversity and accuracy. Specifically, we (i) model the joint distribution of images and annotations to learn a latent space, which is used to decouple diversity and accuracy, and (ii) transform the Gaussian distribution in the latent space to a complex distribution to improve model's expressiveness. In addition, we explore two strategies for preventing the latent space collapse, which are effective in improving the model's performance on datasets with limited annotation. We demonstrate the effectiveness of the proposed model on two medical image datasets, i.e. LIDC-IDRI and ISBI 2016, and achieved state-of-the-art results on several metrics.

Pulmonary nodule detection and segmentation are the necessary successively steps in lung cancer screening with low-dose computed tomography (CT) scans. However, the state-of-the-art models focus on solving tasks separately, thereby ignore the correlation between each task. Besides, most nodule detectors adopt anchor-based method falling to achieve good performance in low FPs per scan. To overcome those barriers, we present a novel multi-task 3D convolutional network (DeepNodule) for simultaneous nodule detection and segmentation in a shared-and-fined manner. Meanwhile, we utilize the center-point of the predicted segmentation masks to refine the bounding box coordinate and get a more precise nodule location. Furthermore, we design a 3D Gated Channel Transformation convolutional attention block for learning nodule features better. Experiments conducted on LUNA16 dataset demonstrates that DeepNodule obtains competitive performance, with the sensitivity of nodule candidate detection achieving 92.0%, and the accuracy of nodule segmentation reaching 80.04%.

Accurate identification and early diagnosis of malignant lung nodules are crucial for improving the survival rate of patients with lung cancer. Deep learning methods have recently been proven success in computer-aided diagnostic tasks. However, to the best of our knowledge, the features of tissues and vessels will disturb the model resulting in inaccurate classification of the nodules. To reduce the interference and capture crucial contextual information from different channels in a more efficient way, we introduce a Hyper-Attention Mechanism(HAM) that can be easily integrated into convolutional neural networks(CNNs). Moreover, without incorporating prior-domain knowledge, traditional methods lack interpretability, which is difficult to understand and utilize them in the clinic by radiologists. Based on this, we propose a novel Knowledge-Guided model to predict malignant pulmonary nodules from chest CT data, which inject external medical knowledge into CNNs to guide the training process. We evaluate the proposed model on the LIDC-IDRI dataset and demonstrate its effectiveness by achieving comparable state-of-the-art performance.

Accurate segmentation for lung nodules in lung computed tomography (CT) scans plays a key role in the early diagnosis of lung cancer. Many existing methods, especially U-Net, have made significant progress in lung nodule segmentation. However, due to the complex shapes of lung nodules and the similarity of visual characteristics between nodules and lung tissues, an accurate segmentation with low false positives of lung nodules is still a challenging problem. Considering the fact that both boundary and texture information of lung nodules are important for obtaining an accurate segmentation result, we propose a novel Mask and Texture-driven Generative Adversarial Network (MTGAN) with a joint multi-scale L1 loss for lung nodule segmentation, which takes full advantages of U-Net and adversarial training. The proposed MTGAN leverages adversarial learning strategy guided by the boundary and texture information of lung nodules to generate more accurate segmentation results with lesser false positives. We validate our model with the LIDC-IDRI dataset, and experimental results show that our method achieves excellent segmentation results for a variety of lung nodules, especially for juxtapleural nodules and low-dense nodules. Without any bells and whistles, the proposed MTGAN achieves significant segmentation performance with the Dice similarity coefficient (DSC) of 85.24% on the LIDC-IDRI dataset.

This paper aims to automatically diagnose thoracic diseases in Chest X-ray(CXR) images using deep neural net-works(DNN). However, the existing approaches generally use the global CXR images as input for training purposes. This strategy is low-efficiency, coarse, and might introduce many unnecessary noises. We believe that the deep learning, which is inherently an algebraic computation system, is not the most efficient way to acquire highly sophisticated human knowledge, for example those thoracic diseases are typically limited within the lung regions and interdependence between lesion location. In this paper, we address the above problem by proposing to explore how external medical knowledge can be injected into DNN to guide its training process. We design four feature extraction modules to construct a knowledge-guided deep zoom neural network(KGZNet), which can gradually make full use of the most medical discriminative feature information(from coarse to fine) of global, lung regions, and lesion regions. Specifically, we first learn global branch using global images. Second, learn the lung region branch using lung region images, which are identified and cropped by the Lung Region Generator(LRG-1). Then, guided by the attention heat map generated from the lung region branch learning, we inference a mask to crop a medical discriminative lesion region from the lung region images by the Lesion Region Generator(LRG-2). The lesion region images are used for training a lesion branch. Lastly, the obtained medical discriminative features knowledge are fused by the feature fusion model for disease classification. We have evaluated the proposed method on the NIH ChestX-ray 14 dataset and achieves the average AUC of 0.878, and the experiment results demonstrate the superiority and effectiveness of the proposed method, compared to other state-of-the-art methods.