Nanostructure-based visual assay has been developed for determination of enzymatic activity, but most involve in poor visible color resolution and are not suitable for routine utilization. Herein, we designed a high-resolution colorimetric protocol based on gold/silver core/shell nanorod for visual readout of alkaline phosphatase (ALP) activity by using bare-eyes. The method relied on enzymatic reaction-assisted silver deposition on gold nanorod to generate significant color change, which was strongly dependent on ALP activity. Upon target ALP introduction into the substrate, the ascorbic acid 2-phosphate was hydrolyzed to form ascorbic acid, and then, the generated ascorbic acid reduced silver ion to metal silver and coated on the gold nanorod, thereby resulting in the blue shift of longitudinal localized surface plasmon resonance peak of gold nanorod accompanying a perceptible color change from red to orange to yellow to green to cyan to blue and to violet. Under optimal conditions, the designed method exhibited the wide linear range 5-100 mU mL(-1) ALP with a detection limit of 3.3 mU mL(-1). Moreover, it could be used for the semiquantitative detection of ALP from 20 to 500 mU mL(-1) by using the bare-eyes. The coefficients of variation for intra- and interassay were below 3.5% and 6.2%, respectively. Finally, this method was validated for the analysis of real-life serum samples, giving results matched well with those from the 4-nitrophenyl phosphate disodium salt hexahydrate (pNPP)-based standard method. In addition, the system could even be utilized in the enzyme-linked immunosorbent assay (ELISA) to detect IgG at picomol concentration. With the merits of simplification, low cost, user-friendliness, and sensitive readout, the gold nanorod-based colorimetric assay has the potential to be utilized by the public and opens a new horizon for bioassays.

Background Early diagnosis and management of perianal fistulizing Crohn’s disease (PFCD) is critical. But there is still lack of single reliable diagnostic modality to differentiate between early PFCD and cryptoglandular anal fistula (CAF). This study aimed to evaluate the feasibility and efficacy of deep convolutional neural networks (DCNNs) for distinguishing PFCD from CAF based on pelvic magnetic resonance imaging (MRI). Methods The MRIs from 400 patients primarily diagnosed with PFCD or CAF (two hundred respectively) were retrospectively collected as datasets and used in this study. All patients had no fistula associated surgical histories. The datasets were split into training (80%), validation (10%), and test(10%). Four different DCNNs, MobileNetV2, VGG11, ResNet18 and ResNet34, were trained to classify the patients with fistula MRIs as PFCD or as CAF. Both untrained and pretrained networks were used. Pretrained networks were obtained from the Pytorch Models, an open-access repository of pretrained models for use with Pytorch. The protocol was shown in Figure 1 and was approved by the institutional review board (2022ZSLYEC-421).On the test dataset, receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performances and were compared with the performances of radiologists. Comparisons between AUCs were made by using the Delong method. Accuracy, sensitivity, and specificity were determined from the optimal threshold by the Youden index. Figure1. Results Compared with CAF, the PFCD dataset contained more high fistulas (59.5% vs. 44.5%，P=0.003), more fistulas involved in the deep anterior space (15.5% vs. 3.0%，P<0.001), and less abscess formation (32.5% vs. 59.5%，P<0.001). Other fistula characteristics including ramification formation, supra- or infralevator extension, were not statistically different. The performances of the pretrained models were better than that of the untrained models (Figure 2). The AUC of 4 pretrained DCNN classifiers were MobileNetV2 [AUC: 0.943，95%CI（0.820~0.991）], VGG11 [AUC: 0.935, 95%CI（0.810~0.988）], ResNet 18 [AUC: 0.920, 95%CI（0.789~0.982）], ResNet 34[AUC: 0.929, 95%CI（0.801~0.986）] respectively. The performances of 4 pretrained DCNN classifiers were equivalent to that of senior radiologist, and were superior to that of junior radiologist (Figure 2, 3, 4). Figure 2. Figure 3. Figure4. Conclusion Deep learning with DCNN in classifying PFCD or CAF on perianal MRI is feasible. Transfer learning may further improve the performance of the DCNN model. A larger sample size dataset to train the former DCCNs is conducting in our constitution and the external validation will be added in the future.