Adaptive loss-guided multi-stage residual ASPP for lesion segmentation and disease detection in cucumber under complex backgrounds.

BACKGROUND: In complex agricultural environments, the presence of shadows, leaf debris, and uneven illumination can hinder the performance of leaf segmentation models for cucumber disease detection. This is further exacerbated by the imbalance in pixel ratios between background and lesion areas, which affects the accuracy of lesion extraction. RESULTS: An original image segmentation framework, the LS-ASPP model, which utilizes a two-stage Atrous Spatial Pyramid Pooling (ASPP) approach combined with adaptive loss to address these challenges has been proposed. The Leaf-ASPP stage employs attention modules and residual structures to capture multi-scale semantic information and enhance edge perception, allowing for precise extraction of leaf contours from complex backgrounds. In the Spot-ASPP stage, we adjust the dilation rate of ASPP and introduce a Convolutional Attention Block Module (CABM) to accurately segment lesion areas. CONCLUSIONS: The LS-ASPP model demonstrates improved performance in semantic segmentation accuracy under complex conditions, providing a robust solution for precise cucumber lesion segmentation. By focusing on challenging pixels and adapting to the specific requirements of agricultural image analysis, our framework has the potential to enhance disease detection accuracy and facilitate timely and effective crop management decisions.

Multi-area collision-free path planning and efficient task scheduling optimization for autonomous agricultural robots.

Collision-free path planning and task scheduling optimization in multi-region operations of autonomous agricultural robots present a complex coupled problem. In addition to considering task access sequences and collision-free path planning, multiple factors such as task priorities, terrain complexity of farmland, and robot energy consumption must be comprehensively addressed. This study aims to explore a hierarchical decoupling approach to tackle the challenges of multi-region path planning. Firstly, we conduct path planning based on the A* algorithm to traverse paths for all tasks and obtain multi-region connected paths. Throughout this process, factors such as path length, turning points, and corner angles are thoroughly considered, and a cost matrix is constructed for subsequent optimization processes. Secondly, we reformulate the multi-region path planning problem into a discrete optimization problem and employ genetic algorithms to optimize the task sequence, thus identifying the optimal task execution order under energy constraints. We finally validate the feasibility of the multi-task planning algorithm proposed by conducting experiments in an open environment, a narrow environment and a large-scale environment. Experimental results demonstrate the method's capability to find feasible collision-free and cost-optimal task access paths in diverse and complex multi-region planning scenarios.

MSS-UNet: A Multi-Spatial-Shift MLP-based UNet for skin lesion segmentation.

Multilayer perceptron (MLP) networks have become a popular alternative to convolutional neural networks and transformers because of fewer parameters. However, existing MLP-based models improve performance by increasing model depth, which adds computational complexity when processing local features of images. To meet this challenge, we propose MSS-UNet, a lightweight convolutional neural network (CNN) and MLP model for the automated segmentation of skin lesions from dermoscopic images. Specifically, MSS-UNet first uses the convolutional module to extract local information, which is essential for precisely segmenting the skin lesion. We propose an efficient double-spatial-shift MLP module, named DSS-MLP, which enhances the vanilla MLP by enabling communication between different spatial locations through double spatial shifts. We also propose a module named MSSEA with multiple spatial shifts of different strides and lighter external attention to enlarge the local receptive field and capture the boundary continuity of skin lesions. We extensively evaluated the MSS-UNet on ISIC 2017, 2018, and PH2 skin lesion datasets. On three datasets, the method achieves IoU metrics of 85.01%±0.65, 83.65%±1.05, and 92.71%±1.03, with a parameter size and computational complexity of 0.33M and 15.98G, respectively, outperforming most state-of-the-art methods.The code is publicly available at https://github.com/AirZWH/MSS-UNet.

Semi-supervised medical image segmentation via cross-guidance and feature-level consistency dual regularization schemes.

BACKGROUND: Semi-supervised learning is becoming an effective solution for medical image segmentation because of the lack of a large amount of labeled data. PURPOSE: Consistency-based strategy is widely used in semi-supervised learning. However, it is still a challenging problem because of the coupling of CNN-based isomorphic models. In this study, we propose a new semi-supervised medical image segmentation network (DRS-Net) based on a dual-regularization scheme to address this challenge. METHODS: The proposed model consists of a CNN and a multidecoder hybrid Transformer, which adopts two regularization schemes to extract more generalized representations for unlabeled data. Considering the difference in learning paradigm, we introduce the cross-guidance between CNN and hybrid Transformer, which uses the pseudo label output from one model to supervise the other model better to excavate valid representations from unlabeled data. In addition, we use feature-level consistency regularization to effectively improve the feature extraction performance. We apply different perturbations to the feature maps output from the hybrid Transformer encoder and keep an invariance of the predictions to enhance the encoder's representations. RESULTS: We have extensively evaluated our approach on three typical medical image datasets, including CT slices from Spleen, MRI slices from the Heart, and FM Nuclei. We compare DRS-Net with state-of-the-art methods, and experiment results show that DRS-Net performs better on the Spleen dataset, where the dice similarity coefficient increased by about 3.5%. The experimental results on the Heart and Nuclei datasets show that DRS-Net also improves the segmentation effect of the two datasets. CONCLUSIONS: The proposed DRS-Net enhances the segmentation performance of the datasets with three different medical modalities, where the dual-regularization scheme extracts more generalized representations and solves the overfitting problem.