Ping Liu

Automated segmentation of abdominal organs and tumors in medical images is a challenging yet essential task in medical image analysis. Deep learning has shown excellent performance in many medical image segmentation tasks, but most prior efforts were fragmented, addressing individual organ and tumor segmentation tasks with specialized networks. To tackle the challenges of abdominal organ and tumor segmentation using partially labeled datasets, we introduce Re-parameterizing Mixture-of-Diverse-Experts (RepMode) to abdominal organ and tumor segmentation. Within the RepMode framework, the Mixture-of-Diverse-Experts (MoDE) block forms the foundation, learning generalized parameters applicable across all tasks. We seamlessly integrate the MoDE block into a U-shaped network with dynamic heads, addressing multi-scale challenges by dynamically combining experts with varying receptive fields for each organ and tumor. Our framework incorporates task encoding in both the encoder–decoder section and the segmentation head, enabling the network to adapt throughout the entire system based on task-related information. We evaluate our approach on the multi-organ and tumor segmentation (MOTS) dataset. Experiments show that DoDRepNet outperforms previous methods, including multi-head networks and single-network approaches, giving a highly competitive performance compared with the original single network with dynamic heads. DoDRepNet offers a promising approach to address the complexities of abdominal organ and tumor segmentation using partially labeled datasets, enhancing segmentation accuracy and robustness.

Brain tumor segmentation from medical images is a prerequisite to provide a quantitative and intuitive reference for clinical diagnosis and treatment. Manual segmentation depends on clinicians’ experience, and is laborious and time-consuming. To tackle these issues, we proposed an encoder-decoder neural network, i.e. deep supervised 3D Squeeze-and-Excitation V-Net (DSSE-V-Net) to segment brain tumors automatically. We modified V-Net by adding batch normalization and using bottom residual block to make the network deeper. Then we incorporated a squeeze & excitation(SE) module in the modified V-Net by adding the SE block in each stage of the encoder and decoder, respectively. We also integrated 3D deep supervision seamlessly into the network to accelerate convergence. We evaluated our model on the public BraTS 2017 dataset for brain tumor segmentation. Our model outperformed both 3D U-Net and modified V-Net, and obtained highly competitive performance compared with those methods winning in the BraTS 2017 challenge.

Background: We aimed at facilitating percutaneous radiofrequency ablation (RFA) for large tumors with accurate overlapping ablation planning and robot‐assisted needle insertion from a single incision port (SIP).Methods: We developed a personalized and quantitative RFA planning method to obtain multiple needle overlapping ablation planning through a single incision. A robot with a remote center of motion mechanism was designed to perform needle insertions through a SIP according to the planning.Results: Numerical and visual evaluation showed that the planning could yield nearly full coverage over large tumors and greatly reduce both ablation times and the ablations of normal tissues. Ex vivo and in vivo experiments showed that our robot‐assisted needle insertion system was capable of conducting the RFA procedure in large liver tumors from a SIP.Conclusions: Robot‐assisted RFA needle insertions from a SIP makes RFA treatment for large tumors more minimally invasive, predictable, and repeatable.