ABSTRACT
Objective:To build a small-sample ultra-widefield fundus images (UWFI) multi-disease classification artificial intelligence model, and initially explore the ability of artificial intelligence to classify UWFI multi-disease tasks.Methods:A retrospective study. From 2016 to 2021, 1 608 images from 1 123 patients who attended the Eye Center of the Renmin Hospital of Wuhan University and underwent UWFI examination were used for UWFI multi-disease classification artificial intelligence model construction. Among them, 320, 330, 319, 268, and 371 images were used for diabetic retinopathy (DR), retinal vein occlusion (RVO), pathological myopia (PM), retinal detachment (RD), and normal fundus images, respectively. 135 images from 106 patients at the Tianjin Medical University Eye Hospital were used as the external test set. EfficientNet-B7 was selected as the backbone network for classification analysis of the included UWFI images. The performance of the UWFI multi-task classification model was assessed using the receiver operating characteristic curve, area under the curve (AUC), sensitivity, specificity, and accuracy. All data were expressed using numerical values and 95% confidence intervals ( CI). The datasets were trained on the network models ResNet50 and ResNet101 and tested on an external test set to compare and observe the performance of EfficientNet with the 2 models mentioned above. Results:The overall classification accuracy of the UWFI multi-disease classification artificial intelligence model on the internal and external test sets was 92.57% (95% CI 91.13%-92.92%) and 88.89% (95% CI 88.11%-90.02%), respectively. These were 96.62% and 92.59% for normal fundus, 95.95% and 95.56% for DR, 96.62% and 98.52% for RVO, 98.65% and 97.04% for PM, and 97.30% and 94.07% for RD, respectively. The mean AUC on the internal and external test sets was 0.993 and 0.983, respectively, with 0.994 and 0.939 for normal fundus, 0.999 and 0.995 for DR, 0.985 and 1.000 for RVO, 0.991 and 0.993 for PM and 0.995 and 0.990 for RD, respectively. EfficientNet performed better than the ResNet50 and ResNet101 models on both the internal and external test sets. Conclusion:The preliminary UWFI multi-disease classification artificial intelligence model using small samples constructed in this study is able to achieve a high accuracy rate, and the model may have some value in assisting clinical screening and diagnosis.
ABSTRACT
BACKGROUND:It is wel-known that vitamin E holds antioxidant capacity, but whether other growth factors have the same effect on endplate chondrocytes has not yet been reported. OBJECTIVE:To observe the effect of different growth factors on the antioxidant ability of endplate chondrocytes in the intervertebral disc. METHODS:Endplate chondrocytes were primary cultured, and then divided into four groups, including blank control, serum deprivation, hydrogen peroxide stimulation and hydrogen peroxide stimulation combined with different growth factors groups. The 4th group was subdivided into insulin-like growth factor-1, basic fibroblast growth factor, transforming growth factorβ, forskolin and vitamin E groups. The expression levels of caspase-3, matrix metal oproteinase 13 and 3, inhibitor of metal oproteinase 1 as wel as thrombin 4 and 5 were detected by real-time PCR. Cel apoptosis was analyzed through apoptosis kit and flow cytometry. Cel synthesis and secretion were detected by western blot assay. The total antioxidant capacity and the hydrogen peroxide content were determined by kit, and then statistical y analyzed. RESULTS AND CONCLUSION:Different growth factors had significant differences in the endplate chondrocyte apoptosis, secretion and antioxidant capacity. To conclude, transforming growth factorβand forskolin do further damage to the cel s stimulated by hydrogen peroxide, while insulin-like growth factor-1 and vitamin E expose protective effect on the injured cel s.
ABSTRACT
BACKGROUND:Zinc-modified calcium silicate (CaSiO3) bioceramics coating on the titanium surface prepared in preliminary experiments has good chemical stability and antibacterial property. OBJECTIVE:To observe the effects of zinc-modified CaSiO3 bioceramics coating on osteointegration. METHODS:MC3T3-E1 cels were respectively cultured on the titanium with zinc-modified CaSiO3 bioceramics coating (experiment group), titanium with CaSiO3 bioceramics coating (control group) and pure titanium (blank control group). Then, cel adhesion, proliferation, calcification rate and the expression of type I colagen and osteocalcin were detected. The implant materials mentioned above were respectively inserted into the femurs of New Zealand white rabbits, and after 1.5 months, the osteoproliferation and osteointegration between the implants and the host were tested. RESULTS AND CONCLUSION:In vitro experiment: The number of adhesive cels at 12 hours after co-culture was significantly increased in the experimental group compared with the control group and blank control group (P < 0.05). At 14 days after co-culture, cel proliferation ability and ability of calcium nodule formation in the experiment group were significantly better than those in the other groups (P < 0.05). At 21 days after co-culture, there was no significant difference in the expression of type I colagen, but the expression of osteocalcin in the experiment group was higher than that in the control group and blank control group (P < 0.05).In vivo experiment: In the experiment group, a large amount of bone substances were detected, the coating materials directly contacted with the bone interface, new bone tissues and little fibrous tissues were observed at the interface. In contrast, there was a small amount of bone hyperplasia in the control group and almost no bone hyperplase in the blank control group. Moreover, a small part of the implant directly contacted with the bone interface and the most part was separated from bone trabeculae by fibrous tissues. These findings indicate that zinc-modified CaSiO3 bioceramics coating can enhance the ability of osteointegration between titanium implants and the host.