Litchi is often harvested by clamping and cutting the branches, which are small and can easily be damaged by the picking robot. Therefore, the detection of litchi branches is particularly significant. In this paper, an fully convolutional neural network-based semantic segmentation algorithm is proposed to semantically segment the litchi branches. First, the DeepLabV3+ semantic segmentation model is combined with the Xception depth separable convolution feature. Second, transfer learning and data enhancement are used to accelerate the convergence and improve the robustness of the model. Third, a coding and a decoding structure are adopted to reduce the number of network parameters. The decoding structure uses upsampling and the shallow features to fuse, and the same weight is assigned to ensure that the shallow feature semantics and the deep feature semantics are evenly distributed. Fourth, using atrous spatial pyramid pooling, we can better extract the semantic pixel position information without increasing the number of weight parameters. Finally, different sizes of hole convolution are used to ensure the prediction accuracy of small targets. Experiment results demonstrated that the DeepLabV3+ model using the Xception_65 feature extraction network obtained the best results, achieving a mean intersection over union (MIoU) of 0.765, which is 0.144 higher than the MIoU of 0.621 of the original DeepLabV3+ model. Meanwhile, the DeepLabV3+ model using the Xception_65 network has greater robustness, far exceeding the PSPNet_101 and ICNet in detection accuracy. The aforementioned results indicated that the proposed model produced better detection results. It can provide powerful technical support for the gripper picking robot to find fruit branches and provide a new solution for the problem of aim detection and recognition in agricultural automation.

Glioblastoma multiforme (GBM) is the most common primary malignancy of the central nervous system in adults. Macroscopically evident and symptomatic spinal metastases occur rarely. Autopsy series suggest that approximately 25% of patients with intracranial GBM have evidence of spinal subarachnoid seeding, although the exact incidence is not known as postmortem examination of the spine is not routinely performed.1–3 Herein, we present a rare case of symptomatic brain stem and entire spinal dissemination of GBM in a 36-year-old patient during postoperative adjuvant radiochemotherapy with temozolomide and cisplatin. Visual deterioration, intractable stomachache, and limb paralysis were the main clinical features. The results of cytological and immunohistochemical tests on the cerebrospinal fluid cells were highly suggestive of spinal leptomeningeal dissemination. After 1 month, the patient's overall condition deteriorated and succumbed to his disease. To the best of our knowledge, this is the first reported case of GBM dissemination presenting in this manner. Because GBM extracranial dissemination is rare, we also reviewed pertinent literature regarding this uncommon entity.Although metastases to spinal cord from GBM are uncommon, it is always important to have in mind when patients with a history of GBM present with symptoms that do not correlate with the primary disease pattern.