Alert button
Picture for Juexiao Zhou

Juexiao Zhou

Alert button

Automated Bioinformatics Analysis via AutoBA

Sep 06, 2023
Juexiao Zhou, Bin Zhang, Xiuying Chen, Haoyang Li, Xiaopeng Xu, Siyuan Chen, Xin Gao

With the fast-growing and evolving omics data, the demand for streamlined and adaptable tools to handle the analysis continues to grow. In response to this need, we introduce Auto Bioinformatics Analysis (AutoBA), an autonomous AI agent based on a large language model designed explicitly for conventional omics data analysis. AutoBA simplifies the analytical process by requiring minimal user input while delivering detailed step-by-step plans for various bioinformatics tasks. Through rigorous validation by expert bioinformaticians, AutoBA's robustness and adaptability are affirmed across a diverse range of omics analysis cases, including whole genome sequencing (WGS), RNA sequencing (RNA-seq), single-cell RNA-seq, ChIP-seq, and spatial transcriptomics. AutoBA's unique capacity to self-design analysis processes based on input data variations further underscores its versatility. Compared with online bioinformatic services, AutoBA deploys the analysis locally, preserving data privacy. Moreover, different from the predefined pipeline, AutoBA has adaptability in sync with emerging bioinformatics tools. Overall, AutoBA represents a convenient tool, offering robustness and adaptability for complex omics data analysis.

Viaarxiv icon

Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost

Jun 19, 2023
Juexiao Zhou, Xiuying Chen, Xin Gao

Figure 1 for Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost
Figure 2 for Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost
Figure 3 for Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost
Figure 4 for Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost

Medical artificial general intelligence (AGI) is an emerging field that aims to develop systems specifically designed for medical applications that possess the ability to understand, learn, and apply knowledge across a wide range of tasks and domains. Large language models (LLMs) represent a significant step towards AGI. However, training cross-domain LLMs in the medical field poses significant challenges primarily attributed to the requirement of collecting data from diverse domains. This task becomes particularly difficult due to privacy restrictions and the scarcity of publicly available medical datasets. Here, we propose Medical AGI (MedAGI), a paradigm to unify domain-specific medical LLMs with the lowest cost, and suggest a possible path to achieve medical AGI. With an increasing number of domain-specific professional multimodal LLMs in the medical field being developed, MedAGI is designed to automatically select appropriate medical models by analyzing users' questions with our novel adaptive expert selection algorithm. It offers a unified approach to existing LLMs in the medical field, eliminating the need for retraining regardless of the introduction of new models. This characteristic renders it a future-proof solution in the dynamically advancing medical domain. To showcase the resilience of MedAGI, we conducted an evaluation across three distinct medical domains: dermatology diagnosis, X-ray diagnosis, and analysis of pathology pictures. The results demonstrated that MedAGI exhibited remarkable versatility and scalability, delivering exceptional performance across diverse domains. Our code is publicly available to facilitate further research at https://github.com/JoshuaChou2018/MedAGI.

Viaarxiv icon

SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model

Apr 21, 2023
Juexiao Zhou, Xin Gao

Figure 1 for SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model
Figure 2 for SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model
Figure 3 for SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model
Figure 4 for SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model

Skin and subcutaneous diseases are among the major causes of the nonfatal disease burden worldwide, affecting a significant proportion of the population. However, there are three major challenges in the field of dermatology diagnosis. Firstly, there is a shortage of dermatologists available to diagnose patients. Secondly, accurately diagnosing dermatological pictures can be challenging. Lastly, providing user-friendly diagnostic reports can be difficult. Recent advancements in the field of large language models (LLMs) have shown potential for clinical applications. However, current LLMs have difficulty processing images, and there are potential privacy concerns associated with using ChatGPT's API for uploading data. In this paper, we propose SkinGPT, which is the first dermatology diagnostic system that utilizes an advanced vision-based large language model. SkinGPT is the first system of its kind, incorporating a fine-tuned version of MiniGPT-4 with a vast collection of in-house skin disease images, accompanied by doctor's notes. With SkinGPT, users can upload their own skin photos for diagnosis, and the system can autonomously determine the characteristics and categories of skin conditions, perform analysis, and provide treatment recommendations. The ability to deploy it locally and protect user privacy makes SkinGPT an attractive option for patients seeking an accurate and reliable diagnosis of their skin conditions.

Viaarxiv icon

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

Feb 20, 2023
Juexiao Zhou, Longxi Zhou, Di Wang, Xiaopeng Xu, Haoyang Li, Yuetan Chu, Wenkai Han, Xin Gao

Heterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection simultaneously without the demand to modify the existing model structures or to share any private data. In this paper, we proposed PPPML-HMI, an open-source learning paradigm for personalized and privacy-preserving federated heterogeneous medical image analysis. To our best knowledge, personalization and privacy protection were achieved simultaneously for the first time under the federated scenario by integrating the PerFedAvg algorithm and designing our novel cyclic secure aggregation with the homomorphic encryption algorithm. To show the utility of PPPML-HMI, we applied it to a simulated classification task namely the classification of healthy people and patients from the RAD-ChestCT Dataset, and one real-world segmentation task namely the segmentation of lung infections from COVID-19 CT scans. For the real-world task, PPPML-HMI achieved $\sim$5\% higher Dice score on average compared to conventional FL under the heterogeneous scenario. Meanwhile, we applied the improved deep leakage from gradients to simulate adversarial attacks and showed the solid privacy-preserving capability of PPPML-HMI. By applying PPPML-HMI to both tasks with different neural networks, a varied number of users, and sample sizes, we further demonstrated the strong robustness of PPPML-HMI.

Viaarxiv icon

Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare

Feb 20, 2023
Juexiao Zhou, Haoyang Li, Xingyu Liao, Bin Zhang, Wenjia He, Zhongxiao Li, Longxi Zhou, Xin Gao

Figure 1 for Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
Figure 2 for Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
Figure 3 for Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
Figure 4 for Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare

Revoking personal private data is one of the basic human rights, which has already been sheltered by several privacy-preserving laws in many countries. However, with the development of data science, machine learning and deep learning techniques, this right is usually neglected or violated as more and more patients' data are being collected and used for model training, especially in intelligent healthcare, thus making intelligent healthcare a sector where technology must meet the law, regulations, and privacy principles to ensure that the innovation is for the common good. In order to secure patients' right to be forgotten, we proposed a novel solution by using auditing to guide the forgetting process, where auditing means determining whether a dataset has been used to train the model and forgetting requires the information of a query dataset to be forgotten from the target model. We unified these two tasks by introducing a new approach called knowledge purification. To implement our solution, we developed AFS, a unified open-source software, which is able to evaluate and revoke patients' private data from pre-trained deep learning models. We demonstrated the generality of AFS by applying it to four tasks on different datasets with various data sizes and architectures of deep learning networks. The software is publicly available at \url{https://github.com/JoshuaChou2018/AFS}.

Viaarxiv icon