Search

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and generate dynamic convolutional layers at the end of the decoder to extract the interested target. Although successful, it ignores the correlations among tasks and meanwhile is too late to make the model 'aware' of the ongoing task. To address both issues, we propose a prompt-driven Universal Segmentation model (UniSeg) for multi-task medical image segmentation using diverse modalities and domains. We first devise a learnable universal prompt to describe the correlations among all tasks and then convert this prompt and image features into a task-specific prompt, which is fed to the decoder as a part of its input. Thus, we make the model 'aware' of the ongoing task early and boost the task-specific training of the whole decoder. Our results indicate that the proposed UniSeg outperforms other universal models and single-task models on 11 upstream tasks. Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation. Code and model are available at https://github.com/yeerwen/UniSeg., 13 pages, 4 figures

Although recent years have witnessed the great success of convolutional neural networks (CNNs) in medical image segmentation, the domain shift issue caused by the highly variable image quality of medical images hinders the deployment of CNNs in real-world clinical applications. Domain generalization (DG) methods aim to address this issue by training a robust model on the source domain, which has a strong generalization ability. Previously, many DG methods based on feature-space domain randomization have been proposed, which, however, suffer from the limited and unordered search space of feature styles. In this paper, we propose a multi-source DG method called Treasure in Distribution (TriD), which constructs an unprecedented search space to obtain the model with strong robustness by randomly sampling from a uniform distribution. To learn the domain-invariant representations explicitly, we further devise a style-mixing strategy in our TriD, which mixes the feature styles by randomly mixing the augmented and original statistics along the channel wise and can be extended to other DG methods. Extensive experiments on two medical segmentation tasks with different modalities demonstrate that our TriD achieves superior generalization performance on unseen target-domain data. Code is available at https://github.com/Chen-Ziyang/TriD., Comment: 12 pages, 4 figures, 8 tables, early accepted by MICCAI 2023

Kidney structures segmentation is a crucial yet challenging task in the computer-aided diagnosis of surgery-based renal cancer. Although numerous deep learning models have achieved remarkable success in many medical image segmentation tasks, accurate segmentation of kidney structures on computed tomography angiography (CTA) images remains challenging, due to the variable sizes of kidney tumors and the ambiguous boundaries between kidney structures and their surroundings. In this paper, we propose a boundary-aware network (BA-Net) to segment kidneys, kidney tumors, arteries, and veins on CTA scans. This model contains a shared encoder, a boundary decoder, and a segmentation decoder. The multi-scale deep supervision strategy is adopted on both decoders, which can alleviate the issues caused by variable tumor sizes. The boundary probability maps produced by the boundary decoder at each scale are used as attention to enhance the segmentation feature maps. We evaluated the BA-Net on the Kidney PArsing (KiPA) Challenge dataset and achieved an average Dice score of 89.65$\%$ for kidney structure segmentation on CTA scans using 4-fold cross-validation. The results demonstrate the effectiveness of the BA-Net., Technical report. Solution to Kidney PArsing Challenge 2022 (KiPA22)

Herein, the oxazolidinone (OX) segments have been successfully introduced into carbon fiber-reinforced plastic (CFRP) composites via the bulk polymerization of the isocyanate and epoxy (EP) groups to significantly promote the mechanical properties. Through the bulk polymerization, the OX segments in epoxy resin (OX epoxy resin) have been formed, verified via the Fourier transform infrared (FT-IR) spectroscopy. Afterward, in order to obtain the cured OX epoxies, the as-prepared OX epoxy resin has been mixed with the pure EP resin for further curing. Thermogravimetric analysis (TGA) and dynamic mechanical thermal analysis (DMTA) have shown that the cured OX epoxies have exhibited improved thermal resistance and higher Tg than the cured neat epoxies. After introducing OX segments, the flexural strength, flexural modulus, and impact strength of the cured OX epoxies have been promoted by 30.1%, 12.1%, and 82.9%, respectively. Moreover, the mechanical properties of CFRP composites, fabricated from OX epoxy resin and T1100 carbon fibers, have been improved as well and in particular, the flexural strength, flexural modulus, impact strength, interlaminar shear strength, and compressive strength after the impact of the composites have been improved by 25.9%, 8.4%, 23.6%, 35.5%, and 23.8%, respectively. Furthermore, the impact damage of the composite laminates has been analyzed via Ultrasonic C-scan.