5-Fluorouracil(5-FU)has been widely used to treat gastrointestinal,head,neck,chest and ovarian malignant tu-mors since 1957. As an analogue of pyrimidine,5-FU plays anti-cancer roles by inhibiting thymioylate synthase and integrating its me-tabolites into DNA and RNA. Although 5-FU is one of the first-line therapeutic compounds for gastrointestinal malignant tumor as a sin-gle drug or in combination with other drugs,its effectiveness is hindered by its low efficiency,which may be due to chemotherapy re-sistance. 5-FU chemotherapy resistance may stem from enzyme abnormality,genetic abnormality and tumor microenvironment. In this paper,we make a review about 5-FU actions and the mechanisms underlying chemotherapy resistance.

Objective To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images. Methods A total of 1 001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1 007 images of pathological(non-stained)tongue coat-ing from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine with lung cancer,diabetes,and hypertension were collected.The tongue images were randomi-zed into the training,validation,and testing datasets in a 7:2:1 ratio.A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets.The training period was 90 epochs.The model's performance was evaluated by its accuracy,loss curve,recall,F1 score,confusion matrix,receiver operating characteristic(ROC)curve,and precision-recall(PR)curve in the tasks of predicting stained tongue coating images in the testing dataset.The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine(TCM). Results The training results showed that after 90 epochs,the model presented an excellent classification performance.The loss curve and accuracy were stable,showing no signs of overfitting.The model achieved an accuracy,recall,and F1 score of 92%,91%,and 92%,re-spectively.The confusion matrix revealed an accuracy of 92%for the model and 69%for TCM practitioners.The areas under the ROC and PR curves were 0.97 and 0.95,respectively. Conclusion The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners.This model has the potential to assist doctors in identifying false tongue coating and prevent-ing misdiagnosis.

[Objective] To summarize the diagnosis and treatment of Antopol Goldman lesion (AGL) in clinical practice. [Methods] Clinical data and diagnosis and treatment process of one AGL case treated in our hospital were retrospectively analyzed, and relevant literature was reviewed. [Results] The patient presented with painless gross hematuria and right-sided lower back pain.Imaging examination suggested swelling of the right kidney, blood accumulation in the right calyx, renal pelvis and lower ureter, blood clot in the bladder, and multiple small stones in the left kidney.After multidisciplinary consultation, close imaging follow-up, interventional and flexible ureterdscope examination, tumors of hematological diseases, renal hematuria, arteriovenous fistula and collection system were excluded.After conservative treatment, the patient gradually recovered.During the follow-up of 1 year, no hematuria or low back pain recurred. [Conclusion] There is no clear diagnostic standard for AGL.Diagnosis relies on imaging, interventional methods and ureteroscopy.It is necessary to exclude other diseases and adopt conservative treatment.