FAFuse: A Four-Axis Fusion framework of CNN and Transformer for medical image segmentation.

Medical image segmentation is crucial for accurate diagnosis and treatment in the medical field. In recent years, convolutional neural networks (CNNs) and Transformers have been frequently adopted as network architectures in medical image segmentation. The convolution operation is limited in modeling long-range dependencies because it can only extract local information through the limited receptive field. In comparison, Transformers demonstrate excellent capability in modeling long-range dependencies but are less effective in capturing local information. Hence, effectively modeling long-range dependencies while preserving local information is essential for accurate medical image segmentation. In this paper, we propose a four-axis fusion framework called FAFuse, which can exploit the advantages of CNN and Transformer. As the core component of our FAFuse, a Four-Axis Fusion module (FAF) is proposed to efficiently fuse global and local information. FAF combines Four-Axis attention (height, width, main diagonal, and counter diagonal axial attention), a multi-scale convolution, and a residual structure with a depth-separable convolution and a Hadamard product. Furthermore, we also introduce deep supervision to enhance gradient flow and improve overall performance. Our approach achieves state-of-the-art segmentation accuracy on three publicly available medical image segmentation datasets. The code is available at https://github.com/cczu-xiao/FAFuse.

Prostate cancer segmentation from MRI by a multistream fusion encoder.

BACKGROUND: Targeted prostate biopsy guided by multiparametric magnetic resonance imaging (mpMRI) detects more clinically significant lesions than conventional systemic biopsy. Lesion segmentation is required for planning MRI-targeted biopsies. The requirement for integrating image features available in T2-weighted and diffusion-weighted images poses a challenge in prostate lesion segmentation from mpMRI. PURPOSE: A flexible and efficient multistream fusion encoder is proposed in this work to facilitate the multiscale fusion of features from multiple imaging streams. A patch-based loss function is introduced to improve the accuracy in segmenting small lesions. METHODS: The proposed multistream encoder fuses features extracted in the three imaging streams at each layer of the network, thereby allowing improved feature maps to propagate downstream and benefit segmentation performance. The fusion is achieved through a spatial attention map generated by optimally weighting the contribution of the convolution outputs from each stream. This design provides flexibility for the network to highlight image modalities according to their relative influence on the segmentation performance. The encoder also performs multiscale integration by highlighting the input feature maps (low-level features) with the spatial attention maps generated from convolution outputs (high-level features). The Dice similarity coefficient (DSC), serving as a cost function, is less sensitive to incorrect segmentation for small lesions. We address this issue by introducing a patch-based loss function that provides an average of the DSCs obtained from local image patches. This local average DSC is equally sensitive to large and small lesions, as the patch-based DSCs associated with small and large lesions have equal weights in this average DSC. RESULTS: The framework was evaluated in 931 sets of images acquired in several clinical studies at two centers in Hong Kong and the United Kingdom. In particular, the training, validation, and test sets contain 615, 144, and 172 sets of images, respectively. The proposed framework outperformed single-stream networks and three recently proposed multistream networks, attaining F1 scores of 82.2 and 87.6% in the lesion and patient levels, respectively. The average inference time for an axial image was 11.8 ms. CONCLUSION: The accuracy and efficiency afforded by the proposed framework would accelerate the MRI interpretation workflow of MRI-targeted biopsy and focal therapies.

Rational design of molybdenum sulfide/tungsten oxide solar absorber with enhanced photocatalytic degradation toward dye wastewater purification.

Integrating advanced technologies into solar-driven water evaporation is gradually considered as a clean and sustainable way to acquire freshwater from saline or wastewater. In this study, thin molybdenum sulfide nanosheet arrays (MoS2 NSAs) modified by tungsten oxide nanoparticles (WO3) were designed. The as-prepared solar absorber could purify water and accomplish photocatalytic degradation of dyes that existed in bulk water via solar-driven water evaporation. Compared with bare MoS2 NSAs, the modification of WO3 enhanced the separation of electrons and holes within the solar absorber, resulting in the improvement of photocatalytic efficiency. The net evaporation rate of the solar absorber reached 0.97 kg m-2h-1 and the degradation rate constant of rhodamine B (RhB) reached 0.101 min-1 under 1 sun. This study successfully combined photothermal conversion and photocatalytic technologies and provided a new method for the treatment of dye wastewater with zero wastewater discharge.

Ultra low-cost and bio-sustainable carbonized green algae for wastewater purification in gold smelting industry.

As a promising solar energy conversion technology, solar water evaporation has been regarded as an energy-efficient approach to alleviate the freshwater shortage caused by industrial water pollution. In this paper, we developed a straightforward method with a solar-driven steam generator (SSG) based on the carbonized green algae (CGA) as a light-to-heat conversion material (LHCM) to deal with the industrial wastewater of gold smelting. CGA SSG exhibited excellent light absorption, hydrophilicity, and water evaporation rate (1.66 kg·m-2·h-1). It accomplished the non-selective removal of heavy metal ions (Cu2+, Pb2+, Zn2+, Hg2+) and CN- in the treatment of gold smelting wastewater, and the ion removal rate was 99%. Compared with traditional and complex wastewater treatment technologies, the solar-driven CGA SSG presented many advantages (low cost, simple preparation, and high performance) in water purification, which could be employed in backward areas to obtain clean water.