At present, China has entered a deeply aging society, and preparing for elderly care actively can respond to the aging population. This article reviews the theoretical basis, research status, evaluation tools, and influencing factors of elderly care preparation, aiming to provide reference for deepening the elderly care preparation work and achieving healthy aging.

Objective:To establish an artificial intelligence (AI)-assisted diagnostic system for lung cancer via deep transfer learning.Methods:The researchers collected 519 lung pathologic slides from 2016 to 2019, covering various lung tissues, including normal tissues, adenocarcinoma, squamous cell carcinoma and small cell carcinoma, from the Beijing Chest Hospital, the Capital Medical University. The slides were digitized by scanner, and 316 slides were used as training set and 203 as the internal test set. The researchers labeled all the training slides by pathologists and establish a semantic segmentation model based on DeepLab v3 with ResNet-50 to detect lung cancers at the pixel level. To perform transfer learning, the researchers utilized the gastric cancer detection model to initialize the deep neural network parameters. The lung cancer detection convolutional neural network was further trained by fine-tuning of the labeled data. The deep learning model was tested by 203 slides in the internal test set and 1 081 slides obtained from TCIA database, named as the external test set.Results:The model trained with transfer learning showed substantial accuracy advantage against the one trained from scratch for the internal test set [area under curve (AUC) 0.988 vs. 0.971, Kappa 0.852 vs. 0.832]. For the external test set, the transferred model achieved an AUC of 0.968 and Kappa of 0.828, indicating superior generalization ability. By studying the predictions made by the model, the researchers obtained deeper understandings of the deep learning model.Conclusions:The lung cancer histopathological diagnostic system achieves higher accuracy and superior generalization ability. With the development of histopathological AI, the transfer learning can effectively train diagnosis models and shorten the learning period, and improve the model performance.

OBJECTIVE: To optimize the method for embedding multiple undecalcified mouse tibias in plastic blocks, improve the efficiency and stability of plastic embedding and reduce the detachment rate of plastic slides. METHODS: Thirty undecalcified tibias from 15 B6 mice were used for plastic embedding after calcein labeling, fixation, dehydration and infiltration. The tibias were embedded in cylindrical plastic blocks with a diameter of 4 mm. For each bone, the 1/4 proximal tibia was cut off, and the remaining 3/4 was used for re-embedding. Five bones were embedded in a single block with each bone standing closely on the surface of a flat plate. The samples were randomized into control and experimental groups in all the processes of embedding, sectioning and staining. In the 3 groups with modified embedment, flowing CO was added into the embedding solution, embedding solution was applied to the section surface, and the slides were heated at 95 ℃ for 15 min. The polymerization time, slide detachment rate, bone formation and osteoblast parameters were analyzed. RESULTS: We prepared 6 plastic blocks, each containing 5 tibias, whose cross sections were on the same plane. The blocks were completely polymerized and suitable for sectioning. Flowing CO into the embedding solution reduced the polymerization time and increased the rate of complete polymerization. Application of the embedding solution on the section surface significantly reduced the detachment rate of the sections ( < 0.05) without affecting bone formation analysis ( > 0.05). Heating the slides significantly lowered the detachment rate of the sections ( < 0.05) without affecting osteoblast analysis ( > 0.05). CONCLUSIONS The optimized method allows effective embedding of multiple undecalcified mice tibias in the same block and can be an ideal method for histological analysis of undecalcified bones.
Animals ; Mice ; Plastics ; Staining and Labeling ; Tibia ; Tissue Embedding ; methods