Semantic segmentation techniques are widely applied in various image analysis tasks. However, compared with natural images, medical image segmentation presents greater challenges. For instance, lesions often vary significantly in morphology, size, and structure, and are frequently accompanied by low contrast and blurred boundaries. To simultaneously preserve fine tissue structures when handling large-scale lesions and ensure the coherence of the divergent structures of vessels, tumors, and other organs while accurately segmenting adjacent cells, this paper proposes the concept of “Global Capture and Local Carving”. It introduces a model that integrates a hierarchical information fusion strategy, named CarveNet. CarveNet incorporates a carving mechanism at three levels: downsampling, feature transmission, and bottleneck processing. Structural Carving Pooling Module underpins the downsampling carving, deeply optimizing the information structure and morphology at different levels to maximize detail retention and minimize downsampling loss. Multi-window Carving ViT is employed for transmission carving, enhancing global information modeling while refining local feature representation. The bottleneck carving integrates a long-distance recurrent communication mechanism with grid-like spatial random shuffling to strengthen the robustness and diversity of feature extraction. Experiments conducted on eight medical image datasets demonstrate that CarveNet consistently delivers outstanding performance across all tasks, surpassing the second-best method in Dice coefficient by 1.136 %. This fully validates its effectiveness in terms of multi-lesion adaptability, accuracy, and generalization capability. The code is available at https://github.com/YF-W/CarveNet .

Over the past decades, Field-Programmable Gate Arrays (FPGAs) have become a choice for heterogeneous computing due to their flexibility, energy efficiency, and processing speed. OpenCL is used in FPGA heterogeneous computing for its high-level abstraction and cross-platform compatibility. Previous works have introduced optimization techniques in OpenCL for FPGAs to leverage FPGA-specific advantages. However, the multi-kernel pipeline technique, which can raise throughput and resource utilization, has not performed well. This article presents a CPU+FPGA heterogeneous platform with a novel execution model to optimize multi-kernel pipeline. Firstly, we extend OpenCL by introducing new APIs and additional functions to represent the execution model. Secondly, a hardware-software co-scheduling scheme is employed to manage execution. Thirdly, we design a holistic development flow and toolkit to facilitate the deployment of algorithms on the platform or the integration of RTL IP cores to the OpenCL environment. We validate the platform using a Range Doppler algorithm. The proposed development flow and integrated toolchain enhance the efficiency of integrating traditional RTL IP cores into the OpenCL environment. Experimental results demonstrate that, with a comparable processing speed (averaging 95%) to traditional RTL implementations, the platform successfully establishes the multi-kernel pipelines. Leveraging the multi-kernel pipeline, the platform achieves a significant improvement in multi-frame processing speed compared to traditional OpenCL.

Recently, transformers have shown strong performance in tasks such as computer vision and natural language processing. Notably, Swin Transformer has gained significant attention for its low computational complexity and impressive performance in computer vision tasks, due to its window attention mechanism and hierarchical architecture. However, these features also make hardware deployment more complicated. In this brief, we present an energy-efficient field-programmable gate array (FPGA) accelerator for Swin Transformer to support the hierarchical architecture and execute the window attention. First, we introduce a systolic array with alterable datapath (SAAD) to conduct the window attention. Second, we split the patch merging operation and design a data rearrangement module, which reduces the computing latency induced by the data rearrangement in Swin Transformer. Third, we present a parallelized dual-array dataflow to support different computing operations in Swin Transformer. We implement the accelerator on the Xilinx XCZU19EG platform. The proposed architecture achieves a throughput per digital signal processing (DSP) of 0.630 giga operations per second (GOPS)/DSP, which is$1.94\times $higher than existing works.

Abstract Semantic Segmentation has been widely used in a variety of clinical images, which greatly assists medical diagnosis and other work. To address the challenge of reduced semantic inference accuracy caused by feature weakening, a pioneering network called FTUNet (Feature-enhanced Transformer UNet) was introduced, leveraging the classical Encoder-Decoder architecture. Firstly, a dual-branch Encoder is proposed based on the U-shaped structure. In addition to employing convolution for feature extraction, a Layer Transformer structure (LTrans) is established to capture long-range dependencies and global context information. Then, an Inception structural module focusing on local features is proposed at the Bottleneck, which adopts the dilated convolution to amplify the receptive field to achieve deeper semantic mining based on the comprehensive information brought by the dual Encoder. Finally, in order to amplify feature differences, a lightweight attention mechanism of feature polarization is proposed at Skip Connection, which can strengthen or suppress feature channels by reallocating weights. The experiment is conducted on 3 different medical datasets. A comprehensive and detailed comparison was conducted with 6 non-U-shaped models, 5 U-shaped models, and 3 Transformer models in 8 categories of indicators. Meanwhile, 9 kinds of layer-by-layer ablation and 4 kinds of other embedding attempts are implemented to demonstrate the optimal structure of the current FTUNet.

The costly multiplications challenge the deployment of modern deep neural networks (DNNs) on resource-constrained devices. To promote hardware efficiency, prior works have built multiplication-free models. However, they are generally inferior to their multiplication-based counterparts in accuracy, calling for multiplication-reduced hybrid models to marry the benefits of both approaches. To achieve this goal, recent works, i.e., NASA and NASA+, have developedNeuralArchitectureSearch (NAS) andAcceleration frameworks to search for and accelerate such hybrid models via a tailored differentiable NAS (DNAS) engine and dedicated ASIC-based accelerators. In this paper, we delve deeper into the inherent advantages of FPGAs and present an enhanced approach called NASA-F, which focuses on FPGA-oriented search and acceleration for hybrid models. Specifically,on the algorithm level, we develop a tailored one-shot supernet-based NAS engine to streamline the search for hybrid models, eliminating the need for executing NAS for each deployment as well as additional training/finetuning steps.On the hardware level, we develop a chunk-based accelerator to fully leverage the diverse hardware resources available on FPGAs for the acceleration of heterogeneous layers in hybrid models, aiming to enhance both hardware utilization and throughput. Extensive experimental results consistently validate the superiority of our NASA-F framework, e.g., we can gain$\uparrow 0.67\%$top-1 accuracy over the prior work NASA on CIFAR100 even without additional training steps for searched models. Additionally, we can achieve up to$\uparrow 1.86\times $throughout and$\uparrow 2.16\times $FPS with$\uparrow 0.39$% top-1 accuracy over the state-of-the-art multiplication-based system on Tiny-ImageNet. Codes are available athttps://github.com/shihuihong214/NASA-F.

Based on the principle of user-centered design, the elderly user needs analysis is an indispensable part of the assistive product design. For this purpose, we designed a questionnaire on assistive products for the elderly and carried out an investigation in China. The questionnaire was aimed at over 60 years of the elder at home. Through the analysis of the questionnaire answers, we tried to understand the physiological function characteristics of the elderly, as well as the assistive product needs, usage intention, usage status, user experience, etc. of the elderly and proposed the application strategies in the design of the assistive products for elderly.

Aiming at the problem of the sick limb condition of the exoskeleton rehabilitation robot affects the smoothness and stability of the robot system during rehabilitation training, this paper proposed an impedance control model for the lower limb exoskeleton rehabilitation robot. The model realizes the flexibility of the robot system by adjusting the impedance control parameters in real time. To verify the validity of the model, we used SCONE software to realize forward dynamics simulation of walking gait. The classical PID impedance control system and fuzzy adaptive impedance control system are simulated respectively. The results show that the fuzzy adaptive control system is more effective to adapt to the changes of limb condition for the impedance control system of lower limb exoskeleton rehabilitation robot.