Computer-aided diagnosis of skin diseases is an important tool. Various algorithms have been applied to achieve segmentation and classification results. However, the difficulty for dermatologists and patients to visualize the prediction process of neural networks has limited the perceived reliability of such systems. In addition, traditional methods need to be trained using negative samples in order to predict the presence or absence of a lesion, but medical data is often in short supply. In this paper, we propose a multiple High-order Spatial Attention interaction model (MHA-UNet) for use in a highly explainable skin lesion segmentation task. MHA-UNet is able to obtain the presence or absence of a lesion by explainable reasoning without the need for training on negative samples. We used a total of five public skin datasets and one private dataset to confirm its effectiveness. For classifying the presence of lesions, we obtained positive and negative detection rates of 81.0% and 83.2% on the PH2and Kaggle95 datasets under the condition that no negative samples were involved in training. For segmentation experiments, comparison experiments of the proposed method with 15 medical segmentation models demonstrate the state-of-the-art performance of our model. The code is available from https://github.com/wurenkai/MHA-UNet.

Intracranial germ cell tumors are rare tumors that mainly affect children and adolescents. Radiotherapy is the cornerstone of interdisciplinary treatment methods. Radiation of the whole ventricle system and the local tumor can reduce the complications in the late stage of radiotherapy while ensuring the curative effect. However, manually delineating the ventricular system is labor-intensive and time-consuming for physicians. The diverse ventricle shape and the hydrocephalus-induced ventricle dilation increase the difficulty of automatic segmentation algorithms. Therefore, this study proposed a fully automatic segmentation framework. Firstly, we designed a novel unsupervised learning-based label mapper, which is used to handle the ventricle shape variations and obtain the preliminary segmentation result. Then, to boost the segmentation performance of the framework, we improved the region growth algorithm and combined the fully connected conditional random field to optimize the preliminary results from both regional and voxel scales. In the case of only one set of annotated data is required, the average time cost is 153.01 s, and the average target segmentation accuracy can reach 84.69%. Furthermore, we verified the algorithm in practical clinical applications. The results demonstrate that our proposed method is beneficial for physicians to delineate radiotherapy targets, which is feasible and clinically practical, and may fill the gap of automatic delineation methods for the ventricular target of intracranial germ celltumors.

The visual quality of ultrasound (US) images is crucial for clinical diagnosis and treatment. The main source of image quality degradation is the inherent speckle noise generated during US image acquisition. Current deep learning-based methods cannot preserve the maximum boundary contrast when removing noise and speckle. In this paper, we address the issue by proposing a novel wavelet-based generative adversarial network (GAN) for real-time high-quality US image reconstruction, viz. WGAN-DUS. First, we propose a batch normalization module (BNM) to balance the importance of each sub-band image and fuse sub-band features simultaneously. Then, a wavelet reconstruction module (WRM) integrated with a cascade of wavelet residual channel attention block (WRCAB) is proposed to extract distinctive sub-band features used to reconstruct denoised images. A gradual tuning strategy is proposed to fine-tune our generator for better despeckling performance. We further propose a wavelet-based discriminator and a comprehensive loss function to effectively suppress speckle noise and preserve the image features. Besides, we have designed an algorithm to estimate the noise levels during despeckling of real US images. The performance of our network was then evaluated on natural, synthetic, simulated and clinical US images and compared against various despeckling methods. To verify the feasibility of WGAN-DUS, we further extend our work to uterine fibroid segmentation with the denoised US image of the proposed approach. Experimental result demonstrates that our proposed method is feasible and can be generalized to clinical applications for despeckling of US images in real-time without losing its fine details.

Augmented reality (AR) surgical navigation systems based on image overlay have been used in minimally invasive surgery. However, conventional systems still suffer from a limited viewing zone, a shortage of intuitive three-dimensional (3D) image guidance and cannot be moved freely. To fuse the 3-D overlay image with the patient in situ, it is essential to track the overlay device while it is moving. A direct line-of-sight should be maintained between the optical markers and the tracker camera. In this study, we propose a moving-tolerant AR surgical navigation system using autostereoscopic image overlay, which can avoid the use of the optical tracking system during the intraoperative period. The system captures binocular image sequences of environmental change in the operation room to locate the overlay device, rather than tracking the device directly. Therefore, it is no longer required to maintain a direct line-of-sight between the tracker and the tracked devices. The movable range of the system is also not limited by the scope of the tracker camera. Computer simulation experiments demonstrate the reliability of the proposed moving-tolerant AR surgical navigation system. We also fabricate a computer-generated integral photography-based 3-D overlay AR system to validate the feasibility of the proposed moving-tolerant approach. Qualitative and quantitative experiments demonstrate that the proposed system can always fuse the 3-D image with the patient, thus, increasing the feasibility and reliability of traditional 3-D overlay image AR surgical navigation systems.