ZJZhuang Jin

Zhuang Jin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zhuang Jin has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Targeting Diagnosis of High‐Risk Papillary Thyroid Carcinoma Using Ultrasound Contrast Agent With the BRAFV600E Mutation

    by Fang Xie, Lin Yan, Yi‐Ming Li, Yu Lan, Jing Xiao, Ming‐Bo Zhang, Zhuang Jin, Ying Zhang, Xiao‐Qi Tian, Ya‐Qiong Zhu, et al.

    Objective High-risk papillary thyroid carcinoma (PTC) patients with BRAF mutation have lymph node and distant metastasis and poor prognosis. Therefore, this study aims to develop a targeted ultrasound contrast agent for the BRAF(V600E) mutation to screen high-risk PTC at early stage. Methods The targeted lipid nanobubbles carrying BRAF(V600E) antibody were prepared using thin film hydration-sonication and avidin-biotin binding methods. The physicochemical properties and stability of the targeted nanobubbles were detected by transmission electron microscopy, atomic force microscopy, and confocal laser scanning microscopy. The target binding abilities of the targeted nanobubbles in the PTC cells (B-CPAP) overexpressed mutant BRAF(V600E) were evaluated by immunofluorescence staining, quantitative real-time polymerase chain reaction, western blot, and fluorescence microscopy. After PTC tumor models overexpressed mutant BRAF(V600E) were established, the enhanced images of targeted lipid nanobubbles and untargeted lipid nanobubbles on PTC tumors in nude mice were observed using contrast-enhanced ultrasound imaging. Results The targeted lipid nanobubbles revealed uniform, round morphology, and good stability with a nanoscale size. Besides, BRAF(V600E) monoclonal antibody was observed to be combined on the surface of lipid nanobubbles. Furthermore, the targeted nanobubbles had a good targeting diagnosis ability in PTC cells with BRAF(V600E) overexpression. Moreover, the targeted nanobubbles had better ultrasound enhancement and peak intensity of the time-intensity curve (P < .001) in PTC tumors with BRAF(V600E) overexpression as compared to the untargeted lipid nanobubbles. Conclusion The targeted lipid nanobubbles carrying BRAF(V600E) antibody could be regarded as a potential targeted ultrasound contrast agent for the diagnosis of high-risk PTC.


  • Open Access

    A Novel Interpretable Computer-Aided Diagnosis System of Thyroid Nodules on Ultrasound Based on Clinical Experience

    by Shijie Zhang, Huarui Du, Zhuang Jin, Yaqiong Zhu, Ying Zhang, Fang Xie, Mingbo Zhang, Xiaoqi Tian, Jue Zhang, Yukun Luo

    Computer-aided diagnosis systems (CADs) present valuable second opinions to radiologists in diagnosis. Many studies on thyroid nodules have proposed various CADs to provide a binary result, benignity or malignancy, for doctors, ignoring interpretability of more ultrasonic features that could be more useful. We develop an interpretable CADs (iCADS) that utilizes deep-learning networks’ classification power and interpretability potential of clinical guidelines, like TIRADS, a well-established scale for thyroid nodules. iCADS incorporates a main neural-networks model and six neural-network based interpreters. The outputs of the six interpreters are compared with TIRADS guidelines and the matched result will form a report, more than a benignity or malignancy result, for radiologists. Clinical images of 16,946 thyroid nodules from 5,885 patients were used to train the proposed iCADS. An extra experimental data set containing 501 images were used to test the performance of the model. For better illustrating the assistant ability of iCADS, we also recruited ten junior radiologists to make diagnosis decisions with or without the help of different versions of iCADS. The experiments demonstrated that iCADS can largely improve junior radiologists diagnosis with the help of interpreter strategy. These experiments are also the very first attempt to evaluate the effect of interpretability of deep-learning based CADs in clinical practice. Comparison experiments with other deep-learning based CADs and traditional CADs indicated that the interpreter strategy can easily be combined to other intelligent CADs without the loss of performance. The framework of iCADS can also inspire more research on the development of CADs.


  • Integrating Clinical Knowledge in a Thyroid Nodule Classification Model Based on

    by Shijie Zhang, Jiabin Zhang, Hanjing Kong, Jian An, Yukun Luo, Jue Zhang, Huarui Du, Zhuang Jin, Yaqiong Zhu, Ying Zhang, et al.

    Deep neural network models are currently facing problems due the weak interpretability of predicted results. One solution would involve integrating the clinical knowledge and classifiers. In this study, we utilized mature clinical experiences from TI-RADS, and also trained a multi-label cost-sensitive classification network. The results show that the end-to-end classification model based on cost-sensitive loss function is a more effective way to integrate clinical knowledge into the deep neural network.


  • Design and Implementation of WA Face Recognition System based on Small WeChat Program

    by Zhuang Jin, Jun Wang, Shu Zhang

    Aiming at the disadvantages of traditional check-in time occupation and complicated personnel operation, this paper develops a system for WA face recognition with the help of small WeChat program. Based on the features of Wa people's faces, the system designs three modules: user authentication, face uploading and face recognition. Realizing it by small WeChat program development tools and Django framework, the background uses MySQL database as the base database. In order to achieve better recognition, the 1000 WA face pictures collected are mainly constructed, the data set is trained by convolution neural network, the ratio of training set to test set is 8:2, and the result of final test reaches 98%.


  • ChemInform Abstract: Replacement of BF4‐ by PF6‐ Makes Selectfluor Greener.

    by Zhuang Jin, Bo Xu, Stephen G. DiMagno, Gerald B. Hammond

    Changing the counterion in Selectfluor® from tetrafluoroborate to hexafluorophosphate significantly reduces catalyst loading in amide oxidation reactions.