Laparoscopic indocyanine green fluorescence imaging technique in rare type II cystic biliary atresia.

In recent years, it has been reported that indocyanine green can be used for intraoperative navigation in Kasai surgery. However, there are no reports of its application in surgery for rare type II cystic biliary atresia. We report a girl presented with jaundice and light-colored stools. Laboratory tests showed impaired liver function with elevated serum bilirubin and bile acid levels. The abdominal ultrasound and MRCP suggested a common hepatic duct cyst. A diagnosis of choledochal cyst was suspected and biliary atresia could not be excluded. Conservative treatment was unsatisfactory. Laparoscopic exploration with indocyanine green fluorescence was performed on the 38th day of her life, and intraoperative diagnosis of type II CBA was made because the common hepatic duct cyst and its downstream anatomical structures did not show fluorescence. The postoperative bilirubin and bile acid levels decreased significantly and she was discharged two weeks after surgery. This result suggests that indocyanine green can be safely used in laparoscopic surgery for type II CBA, which not only helps in the differential diagnosis of CBA and choledochal cyst, but also confirms bile flow in real time.

Lung nodule false positive reduction using a central attention convolutional neural network on imbalanced data.

Computer-aided detection systems for lung nodules play an important role in the early diagnosis and treatment process. False positive reduction is a significant component in pulmonary nodule detection. To address the visual similarities between nodules and false positives in CT images and the problem of two-class imbalanced learning, we propose a central attention convolutional neural network on imbalanced data (CACNNID) to distinguish nodules from a large number of false positive candidates. To solve the imbalanced data problem, we consider density distribution, data augmentation, noise reduction, and balanced sampling for making the network well-learned. During the network training, we design the model to pay high attention to the central information and minimize the influence of irrelevant edge information for extracting the discriminant features. The proposed model has been evaluated on the public dataset LUNA16 and achieved a mean sensitivity of 92.64%, specificity of 98.71%, accuracy of 98.69%, and AUC of 95.67%. The experimental results indicate that our model can achieve satisfactory performance in false positive reduction.

Indocyanine green fluorescence imaging localization-assisted thoracoscopy revision surgery after repair of esophageal atresia.

Revision surgery for the complications after repair of esophageal atresia is often complex because of previous surgeries and chest infections and thus requires surgical expertise. This study describes surgical experiences with the use of indocyanine green (ICG) fluorescence imaging localization-assisted thoracoscopy during revision surgery, including recurrent tracheoesophageal fistula (rTEF) (8 cases, one of which was esophageal-pulmonary fistula) and delayed esophageal closure (1 case). We performed fistula repair and esophageal reconstruction according to the indications of ICG. The application of this method avoids the excessive trauma caused by freeing the trachea and esophagus. Contrast imaging taken one week and one month after surgery indicated no spillover of the contrast agent from the esophagus, except in 1 case. Indocyanine green fluorescence imaging localization-assisted thoracoscopy is worth promoting for revision surgery after esophageal atresia repair.

Prognostic role of multiparameter MRI and radiomics in progression of advanced unresectable hepatocellular carcinoma following combined transcatheter arterial chemoembolization and lenvatinib therapy.

BACKGROUND: Current study aims to determine the prognostic value of Multiparameter MRI after combined Lenvatinib and TACE therapy in patients with advanced unresectable hepatocellular carcinoma (HCC). METHODS: A total of 61 HCC patients with pre-treatment Multiparameter MRI in Sun Yat-sen University Cancer Center from January 2019 to March 2021 were recruited in the current study. All patients received combined Lenvatinib and TACE treatment. Potential clinical and imaging risk factors for disease progression were analyzed using Cox regression model. Each patient extracts signs from the following 7 sequences: T1WI, T1WI arterial phase, T1WI portal phase, T1WI delay phase, T2WI, DWI (b = 800), ADC.1782 quantitative 3D radiomic features were extracted for each sequence, A random forest algorithm is used to select the first 20 features by feature importance. 7 logit regression-based prediction model was built for seven sequences based on the selected features and fivefold cross validation was used to evaluate the performance of each model. RESULTS: CR, PR, SD were reported in 14 (23.0%), 35 (57.4%) and 7 (11.5%) patients, respectively. In multivariate analysis, tumor number (hazard ratio, HR = 4.64, 95% CI 1.03-20.88), and arterial phase intensity enhancement (HR = 0.24, 95% CI 0.09-0.64; P = 0.004) emerged as independent risk factors for disease progression. In addition to clinical factors, the radiomics signature enhanced the accuracy of the clinical model in predicting disease progression, with an AUC of 0.71, a sensitivity of 0.99%, and a specificity of 0.95. CONCLUSION: Radiomic signatures derived from pretreatment MRIs could predict response to combined Lenvatinib and TACE therapy. Furthermore, it can increase the accuracy of a combined model for predicting disease progression. In order to improve clinical outcomes, clinicians may use this to select an optimal treatment strategy and develop a personalized monitoring protocol.

Dynamic Behavior of the Structural Phase Transition of Hydrogel Formation Induced by Temperature Ramp and Addition of Ibuprofen.

Understanding the dynamic behavior of hydrogel formation induced by a temperature ramp is essential for the design of gel-based injectable formulation as drug-delivery vehicles. In this study, the dynamic behavior of the hydrogel formation of Pluronic F108 aqueous solutions within different heating rates was explored in both macroscopic and microscopic views. It was discovered that when the heating rate is increased, the gelation temperature window (hard gel region) shrinks and the mechanical strength of the hydrogel decreases. A given system at different heating rates would lead to different crystalline structural evolutions. The time-resolved small-angle X-ray scattering (SAXS) experiments at a heating rate of 10 °C/min disclose that the crystalline structure of micelle packing in the hydrogel exhibits a series of transitions: hexagonal close-packed (HCP) to face-centered cubic (FCC) and body-centered cubic (BCC) structures coexisting and then to the BCC structure along with the increasing temperature. For the system at equilibrium, the BCC structure exclusively dominates the system. Furthermore, the addition of a hydrophobic model drug (ibuprofen) to the F108 aqueous solution promotes hard gel formation at even lower temperatures and concentrations of F108. The SAXS results for the system with ibuprofen at a heating rate of 10 °C/min demonstrate a mixture of FCC and BCC structures coexisting over the whole gelation window compared to the BCC structure that exclusively dominates the system at equilibrium. The addition of ibuprofen would alter the structural evolution to change the delivery path of the encapsulated drug, which is significantly related to the performance of drug release.

Automatic recognition of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNNs.

Ground-glass opacity (GGO) is a common CT imaging sign on high-resolution CT, which means the lesion is more likely to be malignant compared to common solid lung nodules. The automatic recognition of GGO CT imaging signs is of great importance for early diagnosis and possible cure of lung cancers. The present GGO recognition methods employ traditional low-level features and system performance improves slowly. Considering the high-performance of CNN model in computer vision field, we proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling is performed on multi-views and multi-receptive fields, which reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has the ability to obtain the optimal fine-tuning model. Multi-CNN models fusion strategy obtains better performance than any single trained model. We evaluated our method on the GGO nodule samples in publicly available LIDC-IDRI dataset of chest CT scans. The experimental results show that our method yields excellent results with 96.64% sensitivity, 71.43% specificity, and 0.83 F1 score. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images. Graphical abstract We proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has ability to obtain the optimal fine-tuning model. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images.