Search

Abstract Background Breast cancer is the most common malignant tumor in the world. Intraoperative frozen section of sentinel lymph nodes is an important basis for determining whether axillary lymph node dissection is required for breast cancer surgery. We propose an RRCART model based on a deep-learning network to identify metastases in 2362 frozen sections and count the wrongly identified sections and the associated reasons. The purpose is to summarize the factors that affect the accuracy of the artificial intelligence model and propose corresponding solutions. Methods We took the pathological diagnosis of senior pathologists as the gold standard and identified errors. The pathologists and artificial intelligence engineers jointly read the images and heatmaps to determine the locations of the identified errors on sections, and the pathologists found the reasons (false reasons) for the errors. Through NVivo 12 Plus, qualitative analysis of word frequency analysis and nodal analysis was performed on the error reasons, and the top-down error reason framework of “artificial intelligence RRCART model to identify frozen sections of breast cancer lymph nodes” was constructed based on the importance of false reasons. Results There were 101 incorrectly identified sections in 2362 slides, including 42 false negatives and 59 false positives. Through NVivo 12 Plus software, the error causes were node-coded, and finally, 2 parent nodes (high-frequency error, low-frequency error) and 5 child nodes (section quality, normal lymph node structure, secondary reaction of lymph nodes, micrometastasis, and special growth pattern of tumor) were obtained; among them, the error of highest frequency was that caused by normal lymph node structure, with a total of 45 cases (44.55%), followed by micrometastasis, which occurred in 30 cases (29.70%). Conclusions The causes of identification errors in examination of sentinel lymph node frozen sections by artificial intelligence are, in descending order of influence, normal lymph node structure, micrometastases, section quality, special tumor growth patterns and secondary lymph node reactions. In this study, by constructing an artificial intelligence model to identify the error causes of frozen sections of lymph nodes in breast cancer and by analyzing the model in detail, we found that poor quality of slices was the preproblem of many identification errors, which can lead to other errors, such as unclear recognition of lymph node structure by computer. Therefore, we believe that the process of artificial intelligence pathological diagnosis should be optimized, and the quality control of the pathological sections included in the artificial intelligence reading should be carried out first to exclude the influence of poor section quality on the computer model. For cases of micrometastasis, we suggest that by differentiating slices into high- and low-confidence groups, low-confidence micrometastatic slices can be separated for manual identification. The normal lymph node structure can be improved by adding samples and training the model in a targeted manner.

Abscisic acid (ABA), hydrogen peroxide (H2O2) and ascorbate (AsA)–glutathione (GSH) cycle are widely known for their participation in various stresses. However, the relationship between ABA and H2O2 levels and the AsA–GSH cycle under drought stress in wheat has not been studied. In this study, a hydroponic experiment was conducted in wheat seedlings subjected to 15% polyethylene glycol (PEG) 6000–induced dehydration. Drought stress caused the rapid accumulation of endogenous ABA and H2O2 and significantly decreased the number of root tips compared with the control. The application of ABA significantly increased the number of root tips, whereas the application of H2O2 markedly reduced the number of root tips, compared with that under 15% PEG-6000. In addition, drought stress markedly increased the DHA, GSH and GSSG levels, but decreased the AsA levels, AsA/DHA and GSH/GSSG ratios compared with those in the control. The activities of the four enzymes in the AsA–GSH cycle were also markedly increased under drought stress, including glutathione reductase (GR), ascorbate peroxidase (APX), monodehydroascorbate reductase (MDHAR) and dehydroascorbate reductase (DHAR), compared with those in the control. However, the application of an ABA inhibitor significantly inhibited GR, DHAR and APX activities, whereas the application of an H2O2 inhibitor significantly inhibited DHAR and MDHAR activities. Furthermore, the application of ABA inhibitor significantly promoted the increases of H2O2 and the application of H2O2 inhibitor significantly blocked the increases of ABA, compared with those under 15% PEG-6000. Taken together, the results indicated that ABA and H2O2 probably interact under drought stress in wheat; and both of them can mediate drought stress by modulating the enzymes in AsA–GSH cycle, where ABA acts as the main regulator of GR, DHAR, and APX activities, and H2O2 acts as the main regulator of DHAR and MDHAR activities. [ABSTRACT FROM AUTHOR]