Search

Automatically segmenting polyps from colonoscopy videos is crucial for developing computer-assisted diagnostic systems for colorectal cancer. Existing automatic polyp segmentation methods often struggle to fulfill the real-time demands of clinical applications due to their substantial parameter count and computational load, especially those based on Transformer architectures. To tackle these challenges, a novel lightweight long-range context fusion network, named LightCF-Net, is proposed in this paper. This network attempts to model long-range spatial dependencies while maintaining real-time performance, to better distinguish polyps from background noise and thus improve segmentation accuracy. A novel Fusion Attention Encoder (FAEncoder) is designed in the proposed network, which integrates Large Kernel Attention (LKA) and channel attention mechanisms to extract deep representational features of polyps and unearth long-range dependencies. Furthermore, a newly designed Visual Attention Mamba module (VAM) is added to the skip connections, modeling long-range context dependencies in the encoder-extracted features and reducing background noise interference through the attention mechanism. Finally, a Pyramid Split Attention module (PSA) is used in the bottleneck layer to extract richer multi-scale contextual features. The proposed method was thoroughly evaluated on four renowned polyp segmentation datasets: Kvasir-SEG, CVC-ClinicDB, BKAI-IGH, and ETIS. Experimental findings demonstrate that the proposed method delivers higher segmentation accuracy in less time, consistently outperforming the most advanced lightweight polyp segmentation networks.

With the further development of neural networks, automatic segmentation techniques for melanoma are becoming increasingly mature, especially under the conditions of abundant hardware resources. This allows for the accuracy of segmentation to be improved by increasing the complexity and computational capacity of the model. However, a new problem arises when it comes to actual applications, as there may not be the high-end hardware available, especially in hospitals and among the general public, who may have limited computing resources. In response to this situation, this paper proposes a lightweight deep learning network that can achieve high segmentation accuracy with minimal resource consumption. We introduce a network called DTONet (double-tailed octave network), which was specifically designed for this purpose. Its computational parameter count is only 30,859, which is 1/256th of the mainstream UNet model. Despite its reduced complexity, DTONet demonstrates superior performance in terms of accuracy, with an IOU improvement over other similar models. To validate the generalization capability of this model, we conducted tests on the PH2 dataset, and the results still outperformed existing models. Therefore, the proposed DTONet network exhibits excellent generalization ability and is sufficiently outstanding.

The increasing global demand for skin disease diagnostics emphasizes the urgent need for advancements in AI-assisted diagnostic technologies for dermatoscopic images. In current practical medical systems, the primary challenge is balancing lightweight models with accurate image analysis to address constraints like limited storage and computational costs. While knowledge distillation methods hold immense potential in healthcare applications, related research on multi-class skin disease tasks is scarce. To bridge this gap, our study introduces an enhanced multi-source knowledge fusion distillation framework, termed DSP-KD, which improves knowledge transfer in a dual-stage progressive distillation approach to maximize mutual information between teacher and student representations. The experimental results highlight the superior performance of our distilled ShuffleNetV2 on both the ISIC2019 dataset and our private skin disorders dataset. Compared to other state-of-the-art distillation methods using diverse knowledge sources, the DSP-KD demonstrates remarkable effectiveness with a smaller computational burden.

Improving the efficiency of using energy and decreasing impacts on the environment will be an inevitable choice for future development. Based on this direction, three kinds of medium (modified anaerobic digestion wastewater, anaerobic digestion wastewater and a standard growth medium BG11) were used to culture microalgae towards achieving high-quality biodiesel products. The results showed that microalgae culturing with anaerobic digestate wastewater could increase lipid content (21.8%); however, the modified anaerobic digestion wastewater can boost the microalgal biomass production to 0.78 ± 0.01 g/L when compared with (0.35–0.54 g/L) the other two groups. Besides the first step lipid extraction, the elemental composition, thermogravimetric and pyrolysis products of the defatted microalgal residues were also analysed to delve into the utilisation potential of microalgae biomass. Defatted microalgae from modified wastewater by pyrolysis at 650 °C resulted in an increase in the total content of valuable products (39.47%) with no significant difference in the content of toxic compounds compared to other groups. Moreover, the results of the life cycle assessment showed that the environmental impact (388.9 mPET2000) was lower than that of raw wastewater (418.1 mPET2000) and standard medium (497.3 mPET2000)-cultivated groups. Consequently, the method of culturing microalgae in modified wastewater and pyrolyzing algal residues has a potential to increase renewable energy production and reduce environmental impact.