ABSTRACT
The multicut problem, also known as correlation clustering, is a classic combinatorial optimization problem that aims to optimize graph partitioning given only node (dis)similarities on edges. It serves as an elegant generalization for several graph partitioning problems and has found successful applications in various areas such as data mining and computer vision. However, the multicut problem with an exponentially large number of cycle constraints proves to be NP-hard, and existing solvers either suffer from exponential complexity or often give unsatisfactory solutions due to inflexible heuristics driven by hand-designed mechanisms. In this article, we propose a deep graph reinforcement learning method to solve the multicut problem within a combinatorial decision framework involving sequential edge contractions. The customized subgraph neural network adapts to the dynamically edge-contracted graph environment by extracting bilevel connected features from both contracted and original graphs. Our method can learn to infer feasible multicut solutions end-to-end toward optimization of the multicut objective in a data-driven manner. More specifically, by exploring the decision space adaptively, it implicitly gains heuristic knowledge from topological patterns of instances and thereby generates more targeted heuristics overcoming the short-sightedness inherent in the hand-designed ones. During testing, the learned heuristics iteratively contract graphs to construct high-quality solutions within polynomial time. Extensive experiments on synthetic and real-world multicut instances show the superiority of our method over existing combinatorial solvers, while also maintaining a certain level of out-of-distribution generalization ability.
ABSTRACT
Germline cells are critical for transmitting genetic information to subsequent generations in biological organisms. While their differentiation from somatic cells during embryonic development is well-documented in most animals, the regulatory mechanisms initiating plant germline cells are not well understood. To thoroughly investigate the complex morphological transformations of their ultrastructure over developmental time, nanoscale 3D reconstruction of entire plant tissues is necessary, achievable exclusively through electron microscopy imaging. This paper presents a full-process framework designed for reconstructing large-volume plant tissue from serial electron microscopy images. The framework ensures end-to-end direct output of reconstruction results, including topological networks and morphological analysis. The proposed 3D cell alignment, denoise, and instance segmentation pipeline (3DCADS) leverages deep learning to provide a cell instance segmentation workflow for electron microscopy image series, ensuring accurate and robust 3D cell reconstructions with high computational efficiency. The pipeline involves five stages: the registration of electron microscopy serial images; image enhancement and denoising; semantic segmentation using a Transformer-based neural network; instance segmentation through a supervoxel-based clustering algorithm; and an automated analysis and statistical assessment of the reconstruction results, with the mapping of topological connections. The 3DCADS model's precision was validated on a plant tissue ground-truth dataset, outperforming traditional baseline models and deep learning baselines in overall accuracy. The framework was applied to the reconstruction of early meiosis stages in the anthers of Arabidopsis thaliana, resulting in a topological connectivity network and analysis of morphological parameters and characteristics of cell distribution. The experiment underscores the 3DCADS model's potential for biological tissue identification and its significance in quantitative analysis of plant cell development, crucial for examining samples across different genetic phenotypes and mutations in plant development. Additionally, the paper discusses the regulatory mechanisms of Arabidopsis thaliana's germline cells and the development of stamen cells before meiosis, offering new insights into the transition from somatic to germline cell fate in plants.
Subject(s)
Imaging, Three-Dimensional , Imaging, Three-Dimensional/methods , Microscopy, Electron/methods , Arabidopsis/ultrastructure , Arabidopsis/growth & development , Arabidopsis/cytology , Algorithms , Plant Cells/ultrastructure , Image Processing, Computer-Assisted/methodsABSTRACT
Objective: To explore the prognostic risk factors of ESD curative resection of gastrointestinal-neuroendocrine neoplasms (GI-NENs). Methods: A total of 97 patients treated with ESD successfully in our hospital were selected, their surgical site, size, number of resection lesions, operation time, intraoperative complications (such as bleeding and perforation), and treatment status were recorded, and the number of hemostatic clamps used after the postoperative follow-up results and the independent risk factors for ESD complications were obtained through the comparison between the noncomplication group and the ESD complication group using regression analysis. Results: A total of 97 patients with gastrointestinal neuroendocrine tumors were treated with ESD. 61 were males, 36 were females, the ratio of male to female was 1.7 : 1, onset age was 20-78 years old, and median onset age was 50 years old. In 81 cases, tumors were located in the stomach, 10 in the duodenum, and 6 in the rectum. A total of 103 lesions were detected by endoscopy, including 1 case with 2 sites in the stomach, 5 cases with 2 sites in the rectum, and the rest were single. The tumor diameter was 0.3 â¼ 2.5 cm, and the median diameter was 0.6 cm; there were 25 sites with a diameter less than 5 cm. There were 57 places with 10 mm, 16 places with 10-15 mm, and 5 places with >15 mm. All ESD operations were performed in one piece, with a total resection rate of 100%; 89.6% (60/67) of postoperative pathology showed negative basal, and 90.3% (56/62) showed negative resection margin, with a complete resection rate of 88.9% (48/54). ESD's operation time is 6 â¼ 66 min, and the median time is 18 min. During the operation, 5 cases had small amount of bleeding, 3 cases were perforated, 2 cases of delayed postoperative bleeding, 1 case of bleeding was caused by the patient's failure to follow the advice of the doctor to eat a large amount of solid food too early, and 1 case of delayed perforation (all recovered and discharged). ESD operation that bled, age, gender, and perforation location, pathological grade, pathological classification, tumor diameter, tumor surface, operation time, number of titanium clips, origin, echo uniformity, and echo level were statistically insignificant (P > 0.05). Postoperative bleeding was related to the operation time (P=0.017), but it was not an independent risk factor for postoperative bleeding (P=0.118; OR, 0.226; 95% CI, 0.035-1.461). 59 cases were followed up by endoscopy after the operation, and recurrence or no new tumors were found. Conclusion: ESD is an effective and safe treatment method for gastrointestinal neuroendocrine tumors with a diameter of 1-2 cm without invading the muscularis propria. The intraoperative complications seem to have little relationship with the patient; postoperative delayed bleeding is closely related to the ESD operation time but it is not an independent risk factor.
Subject(s)
Endoscopic Mucosal Resection , Gastrointestinal Neoplasms , Neuroendocrine Tumors , Adult , Aged , Endoscopic Mucosal Resection/adverse effects , Endoscopic Mucosal Resection/methods , Female , Gastrointestinal Neoplasms/surgery , Humans , Intraoperative Complications/etiology , Male , Middle Aged , Neuroendocrine Tumors/pathology , Neuroendocrine Tumors/surgery , Prognosis , Risk Factors , Treatment Outcome , Young AdultABSTRACT
The endoplasmic reticulum (ER) is a contiguous and complicated membrane network in eukaryotic cells, and membrane contact sites (MCSs) between the ER and other organelles perform vital cellular functions, including lipid homeostasis, metabolite exchange, calcium level regulation, and organelle division. Here, we establish a whole pipeline to reconstruct all ER, mitochondria, lipid droplets, lysosomes, peroxisomes, and nuclei by automated tape-collecting ultramicrotome scanning electron microscopy and deep learning techniques, which generates an unprecedented 3D model for mapping liver samples. Furthermore, the morphology of various organelles and the MCSs between the ER and other organelles are systematically analyzed. We found that the ER presents with predominantly flat cisternae and is knitted tightly all throughout the intracellular space and around other organelles. In addition, the ER has a smaller volume-to-membrane surface area ratio than other organelles, which suggests that the ER could be more suited for functions that require a large membrane surface area. Our data also indicate that ERâmitochondria contacts are particularly abundant, especially for branched mitochondria. Our study provides 3D reconstructions of various organelles in liver samples together with important fundamental information for biochemical and functional studies in the liver.
Subject(s)
Endoplasmic Reticulum/ultrastructure , Liver/cytology , Animals , Cell Nucleus/metabolism , Cell Nucleus/ultrastructure , Deep Learning , Endoplasmic Reticulum/metabolism , Imaging, Three-Dimensional , Lipid Droplets/metabolism , Lipid Droplets/ultrastructure , Liver/ultrastructure , Lysosomes/metabolism , Lysosomes/ultrastructure , Male , Mice , Microscopy, Electron, Scanning , Mitochondria/metabolism , Mitochondria/ultrastructure , Peroxisomes/metabolism , Peroxisomes/ultrastructureABSTRACT
Recently, with the rapid development of electron microscopy (EM) technology and the increasing demand of neuron circuit reconstruction, the scale of reconstruction data grows significantly. This brings many challenges, one of which is how to effectively manage large-scale data so that researchers can mine valuable information. For this purpose, we developed a data management module equipped with two parts, a storage and retrieval module on the server-side and an image cache module on the client-side. On the server-side, Hadoop and HBase are introduced to resolve massive data storage and retrieval. The pyramid model is adopted to store electron microscope images, which represent multiresolution data of the image. A block storage method is proposed to store volume segmentation results. We design a spatial location-based retrieval method for fast obtaining images and segments by layers rapidly, which achieves a constant time complexity. On the client-side, a three-level image cache module is designed to reduce latency when acquiring data. Through theoretical analysis and practical tests, our tool shows excellent real-time performance when handling large-scale data. Additionally, the server-side can be used as a backend of other similar software or a public database to manage shared datasets, showing strong scalability.