The rapid advancements in natural language processing, particularly the development of large language models (LLMs), have opened new avenues for managing complex clinical text data. However, the inherent complexity and specificity of medical texts present significant challenges for the practical application of prompt engineering in diagnostic tasks. This paper explores LLMs with new prompt engineering technology to enhance model interpretability and improve the prediction performance of pulmonary disease based on a traditional deep learning model. A retrospective dataset including 2965 chest CT radiology reports was constructed. The reports were from 4 cohorts, namely, healthy individuals and patients with pulmonary tuberculosis, lung cancer, and pneumonia. Then, a novel prompt engineering strategy that integrates feature summarization (F-Sum), chain of thought (CoT) reasoning, and a hybrid retrieval-augmented generation (RAG) framework was proposed. A feature summarization approach, leveraging term frequency-inverse document frequency (TF-IDF) and K-means clustering, was used to extract and distill key radiological findings related to 3 diseases. Simultaneously, the hybrid RAG framework combined dense and sparse vector representations to enhance LLMs' comprehension of disease-related text. In total, 3 state-of-the-art LLMs, GLM-4-Plus, GLM-4-air (Zhipu AI), and GPT-4o (OpenAI), were integrated with the prompt strategy to evaluate the efficiency in recognizing pneumonia, tuberculosis, and lung cancer. The traditional deep learning model, BERT (Bidirectional Encoder Representations from Transformers), was also compared to assess the superiority of LLMs. Finally, the proposed method was tested on an external validation dataset consisted of 343 chest computed tomography (CT) report from another hospital. Compared with BERT-based prediction model and various other prompt engineering techniques, our method with GLM-4-Plus achieved the best performance on test dataset, attaining an F1-score of 0.89 and accuracy of 0.89. On the external validation dataset, F1-score (0.86) and accuracy (0.92) of the proposed method with GPT-4o were the highest. Compared to the popular strategy with manually selected typical samples (few-shot) and CoT designed by doctors (F1-score=0.83 and accuracy=0.83), the proposed method that summarized disease characteristics (F-Sum) based on LLM and automatically generated CoT performed better (F1-score=0.89 and accuracy=0.90). Although the BERT-based model got similar results on the test dataset (F1-score=0.85 and accuracy=0.88), its predictive performance significantly decreased on the external validation set (F1-score=0.48 and accuracy=0.78). These findings highlight the potential of LLMs to revolutionize pulmonary disease prediction, particularly in resource-constrained settings, by surpassing traditional models in both accuracy and flexibility. The proposed prompt engineering strategy not only improves predictive performance but also enhances the adaptability of LLMs in complex medical contexts, offering a promising tool for advancing disease diagnosis and clinical decision-making.

To develop and validate a deep learning model based on three-dimensional features (DL_3D) for distinguishing lung adenocarcinoma (LUAD) from tuberculoma (TBM). A total of 1160 patients were collected from three hospitals. A vision transformer network-based DL_3D model was trained, and its performance in differentiating LUAD from TBM was evaluated using validation and external test sets. The performance of the DL_3D model was compared with that of two-dimensional features (DL_2D), radiomics, and six radiologists. Diagnostic performance was assessed using the area under the receiver operating characteristic curves (AUCs) analysis. The study included 840 patients in the training set (mean age, 54.8 years [range, 19-86 years]; 514 men), 210 patients in the validation set (mean age, 54.3 years [range, 18-86 years]; 128 men), and 110 patients in the external test set (mean age, 54.7 years [range, 22-88 years]; 51 men). In both the validation and external test sets, DL_3D exhibited excellent diagnostic performance (AUCs, 0.895 and 0.913, respectively). In the test set, the DL_3D model showed better performance (AUC, 0.913; 95% CI: 0.854, 0.973) than the DL_2D (AUC, 0.804, 95% CI: 0.722, 0.886; p < 0.001), radiomics (AUC, 0.676, 95% CI: 0.574, 0.777; p < 0.001), and six radiologists (AUCs, 0.692 to 0.810; p value range < 0.001-0.035). The DL_3D model outperforms expert radiologists in distinguishing LUAD from TBM. Question Can a deep learning model perform in differentiating LUAD from TBM on non-enhanced CT images? Findings The DL_3D model demonstrated higher diagnostic performance than the DL_2D model, radiomics model, and six radiologists in differentiating LUAD and TBM. Clinical relevance The DL_3D model could accurately differentiate between LUAD and TBM, which can help clinicians make personalized treatment plans.

Agentic Artificial Intelligence (AI) systems leveraging Large Language Models (LLMs) exhibit significant potential for complex reasoning, planning, and tool utilization. We demonstrate that a specialized computer vision system can be built autonomously from a natural language prompt using Agentic AI methods. This involved extending SimpleMind (SM), an open-source Cognitive AI environment with configurable tools for medical image analysis, with an LLM-based agent, implemented using OpenManus, to automate the planning (tool configuration) for a particular computer vision task. We provide a proof-of-concept demonstration that an agentic system can interpret a computer vision task prompt, plan a corresponding SimpleMind workflow by decomposing the task and configuring appropriate tools. From the user input prompt, "provide sm (SimpleMind) config for lungs, heart, and ribs segmentation for cxr (chest x-ray)"), the agent LLM was able to generate the plan (tool configuration file in YAML format), and execute SM-Learn (training) and SM-Think (inference) scripts autonomously. The computer vision agent automatically configured, trained, and tested itself on 50 chest x-ray images, achieving mean dice scores of 0.96, 0.82, 0.83, for lungs, heart, and ribs, respectively. This work shows the potential for autonomous planning and tool configuration that has traditionally been performed by a data scientist in the development of computer vision applications.

Agentic Artificial Intelligence (AI) systems leveraging Large Language Models (LLMs) exhibit significant potential for complex reasoning, planning, and tool utilization. We demonstrate that a specialized computer vision system can be built autonomously from a natural language prompt using Agentic AI methods. This involved extending SimpleMind (SM), an open-source Cognitive AI environment with configurable tools for medical image analysis, with an LLM-based agent, implemented using OpenManus, to automate the planning (tool configuration) for a particular computer vision task. We provide a proof-of-concept demonstration that an agentic system can interpret a computer vision task prompt, plan a corresponding SimpleMind workflow by decomposing the task and configuring appropriate tools. From the user input prompt, "provide sm (SimpleMind) config for lungs, heart, and ribs segmentation for cxr (chest x-ray)"), the agent LLM was able to generate the plan (tool configuration file in YAML format), and execute SM-Learn (training) and SM-Think (inference) scripts autonomously. The computer vision agent automatically configured, trained, and tested itself on 50 chest x-ray images, achieving mean dice scores of 0.96, 0.82, 0.83, for lungs, heart, and ribs, respectively. This work shows the potential for autonomous planning and tool configuration that has traditionally been performed by a data scientist in the development of computer vision applications.

Small cell lung cancer (SCLC) is aggressive with poor survival outcomes, and most patients develop resistance to chemotherapy. No predictive biomarkers currently guide therapy. This study evaluates radiomic features to predict PFS and OS in limited-stage SCLC (LS-SCLC) and assesses PFS, OS, and the added benefit of chemoimmunotherapy (CHIO) in extensive-stage SCLC (ES-SCLC). A total of 660 SCLC patients (470 ES-SCLC, 190 LS-SCLC) from three sites were analyzed. LS-SCLC patients received chemotherapy and radiation, while ES-SCLC patients received either chemotherapy alone or chemoimmunotherapy. Radiomic and quantitative vasculature tortuosity features were extracted from CT scans. A LASSO-Cox regression model was used to construct the ES- Risk-Score (ESRS) and LS- Risk-Score (LSRS). ESRS was associated with PFS in training (HR = 1.54, adj. P = .0013) and validation sets (HR = 1.32, adj. P = .0001; HR = 2.4, adj. P = .0073) and with OS in training (HR = 1.37, adj. P = .0054) and validation sets (HR = 1.35, adj. P < .0006; HR = 1.6, adj. P < .0085) in ES-SCLC patients treated with chemotherapy. High-risk patients had improved PFS (HR = 0.68, adj. P < .001) and OS (HR = 0.78, adj. P = .026) with chemoimmunotherapy. LSRS was associated with PFS in training and validation sets (HR = 1.9, adj. P = .007; HR = 1.4, adj. P = .0098; HR = 2.1, adj. P = .028) in LS-SCLC patients receiving chemoradiation. Radiomics is prognostic for PFS and OS and predicts chemoimmunotherapy benefit in high-risk ES-SCLC patients.

<b>Background:</b> Studies of artificial intelligence (AI) for lung nodule detection on CT have primarily been conducted in investigational settings and/or focused on lung cancer screening. <b>Objective:</b> To evaluate the impact of AI assistance on radiologists' diagnostic performance for detecting lung metastases on chest CT in patients with colorectal cancer (CRC) in real-world clinical practice and to assess the clinical utility of AI assistance in this setting. <b>Methods:</b> This retrospective study included patients with CRC who underwent chest CT as surveillance for lung metastasis from May 2020 to December 2020 (conventional interpretation) or May 2022 to December 2022 (AI-assisted interpretation). Between periods, the institution implemented a commercial AI lung nodule detection system. During the second period, radiologists interpreted examinations concurrently with AI-generated reports, using clinical judgment regarding whether to report AI-detected nodules. The reference standard for metastasis incorporated pathologic and clinical follow-up criteria. Diagnostic performance (sensitivity, specificity, accuracy), and clinical utility (diagnostic yield, false-referral rate, management changes after positive reports) were compared between groups based on clinical radiology reports. Net benefit was estimated using decision curve analysis equation. Standalone AI interpretation was evaluated. <b>Results:</b> The conventional interpretation group included 647 patients (mean age, 64±11 years; 394 men, 253 women; metastasis prevalence, 4.3%); AI-assisted interpretation group included 663 patients (mean age, 63±12 years; 381 men, 282 women; metastasis prevalence, 4.4%). The AI-assisted interpretation group compared with the conventional interpretation group showed higher sensitivity (72.4% vs 32.1%; p=.008), accuracy (98.5% vs 96.0%; p=.005), and frequency of management changes (55.2% vs 25.0%, p=.02), without significant difference in specificity (99.7% vs 98.9%; p=.11), diagnostic yield (3.2% vs 1.4%, p=.30) or false-referral rate (0.3% vs 1.1%, p=.10). AI-assisted interpretation had positive estimated net benefit across outcome ratios. Standalone AI correctly detected metastasis in 24 of 29 patients but had 381 false-positive detections in 634 patients without metastasis; only one AI false-positive was reported as positive by interpretating radiologists. <b>Conclusion:</b> AI assistance yielded increased sensitivity, accuracy, and frequency of management changes, without significantly changed specificity. False-positive AI results minimally impacted radiologists' interpretations. <b>Clinical Impact:</b> The findings support clinical utility of AI assistance for CRC metastasis surveillance.

Chest radiography frequently serves as baseline imaging for most lung diseases¹. Deep learning has great potential for automating the interpretation of chest radiography². However, existing chest radiographic deep learning models are limited in diagnostic scope, generalizability, adaptability, robustness and extensibility. To overcome these limitations, we have developed Ark⁺, a foundation model applied to chest radiography and pretrained by cyclically accruing and reusing the knowledge from heterogeneous expert labels in numerous datasets. Ark⁺ excels in diagnosing thoracic diseases. It expands the diagnostic scope and addresses potential misdiagnosis. It can adapt to evolving diagnostic needs and respond to novel diseases. It can learn rare conditions from a few samples and transfer to new diagnostic settings without training. It tolerates data biases and long-tailed distributions, and it supports federated learning to preserve privacy. All codes and pretrained models have been released, so that Ark⁺ is open for fine-tuning, local adaptation and improvement. It is extensible to several modalities. Thus, it is a foundation model for medical imaging. The exceptional capabilities of Ark⁺ stem from our insight: aggregating various datasets diversifies the patient populations and accrues knowledge from many experts to yield unprecedented performance while reducing annotation costs³. The development of Ark⁺ reveals that open models trained by accruing and reusing knowledge from heterogeneous expert annotations with a multitude of public (big or small) datasets can surpass the performance of proprietary models trained on large data. We hope that our findings will inspire more researchers to share code and datasets or federate privacy-preserving data to create open foundation models with diverse, global expertise and patient populations, thus accelerating open science and democratizing AI for medicine.

Chronic obstructive pulmonary disease (COPD) is one of the leading causes of morbidity and mortality in China, highlighting the importance of early diagnosis and ongoing monitoring for effective management. In recent years, hyperpolarized 129Xe MRI technology has gained significant clinical attention due to its ability to non-invasively and visually assess lung ventilation, microstructure, and gas exchange function. Its recent clinical approval in China, the United States and several European countries, represents a significant advancement in pulmonary imaging. This review provides an overview of the latest developments in hyperpolarized 129Xe MRI technology for COPD assessment in China. It covers the progress in instrument development, advanced imaging techniques, artificial intelligence-driven reconstruction methods, molecular imaging, and the application of this technology in both COPD patients and animal models. Furthermore, the review explores potential technical innovations in 129Xe MRI and discusses future directions for its clinical applications, aiming to address existing challenges and expand the technology's impact in clinical practice.

Timely and accurate classification of bacterial pneumonia (BP) is essential for guiding antibiotic therapy. However, distinguishing BP from non-bacterial pneumonia (NBP) using computed tomography (CT) is challenging due to overlapping imaging features and limited biomarker specificity, often leading to delayed or empirical treatment. This study aimed to develop and evaluate MPMT-Pneumo, a multi-plane, multi-modal deep learning model, to improve BP versus NBP differentiation. A total of 384 patients with microbiologically confirmed pneumonia (239 BP, 145 NBP) from two hospitals were included and divided into training and test sets. MPMT-Pneumo utilized a hybrid CNN-Transformer architecture to integrate features from axial, coronal, sagittal CT views and four routine inflammatory biomarkers (WBC, ANC, CRP, PCT). Poly Focal Loss addressed class imbalance during training. Performance was evaluated using Area Under the Curve (AUC), accuracy, and sensitivity on the test set. MPMT-Pneumo was benchmarked against recent deep learning models, biomarker-only models, and clinical radiologists' CT interpretations. Ablation studies assessed component contributions. MPMT-Pneumo achieved an AUC of 0.874, accuracy of 0.852, and sensitivity of 0.894 on the test set, outperforming baseline deep learning models and biomarker-only models. Sensitivity for BP detection surpassed that of less experienced radiologists and was comparable to the most experienced. Ablation studies confirmed the importance of both multi-plane imaging and biomarkers. MPMT-Pneumo provides a clinically applicable solution for BP classification and shows great potential in improving diagnostic accuracy and promoting more rational antibiotic use in clinical practice.

With the increasing prevalence of respiratory diseases such as pneumonia and COVID-19, timely and accurate diagnosis is critical. This paper makes significant contributions to the field of respiratory disease classification by utilizing X-ray images and advanced machine learning techniques such as deep learning (DL) and Vision Transformers (ViT). First, the paper systematically reviews the current diagnostic methodologies, analyzing the recent advancement in DL and ViT techniques through a comprehensive analysis of the review articles published between 2017 and 2024, excluding short reviews and overviews. The review not only analyses the existing knowledge but also identifies the critical gaps in the field as well as the lack of diversity of the comprehensive and diverse datasets for training the machine learning models. To address such limitations, the paper extensively evaluates DL-based models on publicly available datasets, analyzing key performance metrics such as accuracy, precision, recall, and F1-score. Our evaluations reveal that the current datasets are mostly limited to the narrow subsets of pulmonary diseases, which might lead to some challenges, including overfitting, poor generalization, and reduced possibility of using advanced machine learning techniques in real-world applications. For instance, DL and ViT models require extensive data for effective learning. The primary contribution of this paper is not only the review of the most recent articles and surveys of respiratory diseases and DL models, including ViT, but also introduces a novel, diverse dataset comprising 7867 X-ray images from 5263 patients across three local hospitals, covering 49 distinct pulmonary diseases. The dataset is expected to enhance DL and ViT model training and improve the generalization of those models in various real-world medical image scenarios. By addressing the data scarcity issue, this paper paves the for more reliable and robust disease classification, improving clinical decision-making. Additionally, the article highlights the critical challenges that still need to be addressed, such as dataset bias and variations of X-ray image quality, as well as the need for further clinical validation. Furthermore, the study underscores the critical role of DL in medical diagnosis and highlights the necessity of comprehensive, well-annotated datasets to improve model robustness and clinical reliability. Through these contributions, the paper provides the basis and foundation of future research on respiratory disease diagnosis using AI-driven methodologies. Although the paper tries to cover all the work done between 2017 and 2024, this research might have some limitations of this research, including the review period before 2017 might have foundational work. At the same time, the rapid development of AI might make the earlier methods less relevant.