Jianqi Sun

Background: Combined pulmonary fibrosis and emphysema (CPFE) is a clinical syndrome defined by the coexistence of upper‐lobe emphysema and lower‐lobe pulmonary fibrosis. It is characterized by clinical, functional, and radiologic features that differ significantly from isolated idiopathic pulmonary fibrosis or chronic obstructive pulmonary disease. Summary: This review summarizes recent advances in CPFE, focusing on etiologic classification, clinical and radiologic features, diagnosis and treatment, prognostic evaluation, and emerging perspectives in artificial intelligence (AI). Based on current research, we summarize the etiologic classification of CPFE into four types: smoking‐related, systemic autoimmune rheumatic disease‐associated, occupational‐ and environmental‐related, and idiopathic. These types differ in epidemiologic characteristics, imaging patterns, and disease progression. Consequently, future research is expected to focus on mechanism‐driven phenotyping and quantitative imaging analysis, where AI may provide additional value in disease identification, risk stratification, and dynamic prognostic assessment. Key Message: This review proposes a novel framework for CPFE, integrating etiologic subtyping and a diagnostic algorithm to guide precise management, and highlights AI‐powered strategies for future personalized interventions.

Unsupervised anomaly detection (UAD) in brain MRI is crucial for early diagnosis, yet generalizing existing methods across diverse diseases, sequences, and missing data scenarios remains a significant challenge. Current reconstruction-based methods often fail to detect subtle anomalies, while conventional translation methods lack flexibility regarding input sequences. To address these limitations, we propose UniTransAD, a unified translation-based anomaly detection framework. UniTransAD introduces three key innovations: (1) a unified cyclic-translation inference paradigm built upon content-style disentanglement, capable of processing diverse brain MRI inputs; (2) a Dynamic Style Prototype Memory (DSPM) that enables a flexible and robust cyclic-inference mechanism; and (3) a dual-level detection mechanism that combines pixel-level translation errors with feature-level dissimilarities to enhance detection specificity. Furthermore, to rigorously evaluate generalization beyond disease-specific datasets, we establish the Brain-OmniA evaluation dataset, aggregating seven public datasets covering distinct brain pathologies and sequences. Extensive experiments demonstrate that UniTransAD significantly outperforms state-of-the-art methods on Brain-OmniA with superior flexibility. In summary, UniTransAD offers a robust, flexible and generalizable solution for clinical anomaly detection in heterogeneous clinical environments. Our code, pre-trained models, and full dataset are available at: https://github.com/zhibaishouheilab/UniTransAD.

Background: Pulmonary alveolar proteinosis (PAP) typically manifests as diffuse lung disease, while nodular PAP presenting as pulmonary nodules is extremely rare and often radiologically indistinguishable from early-stage lung adenocarcinoma (LUAD). Objectives: This study aims to establish an accurate diagnostic algorithm to prevent unnecessary invasive procedures in patients with nodular PAP. Design: This study was a retrospective, single-center study. Methods: This study enrolled 16 pathologically confirmed nodular PAP patients and 52 early-stage LUAD patients, systematically comparing their clinical characteristics and biochemical markers. A radiomics model was developed based on CT imaging features, followed by a multimodal model incorporating significant clinical and biochemical discriminators. Results: The nodular PAP cohort demonstrated a 3:5 male-to-female ratio, equivalent distribution of solitary versus multiple nodules, and nodule diameters spanning 3–28 mm. Nodular PAP patients were significantly younger (mean 51.4 vs 67.0 years, p < 0.001), had higher body mass index (BMI, 25.8 ± 2.5 vs 23.7 ± 2.8 kg/m², p < 0.01), and lower lactate dehydrogenase levels (LDH, 188.44 ± 26.71 vs 214.79 ± 56.84 U/L, p = 0.01) compared to LUAD patients. The radiomic model achieved an AUC (area under the curve) of 0.91, while the multimodal model combining clinical and biochemical features showed similar performance (AUC = 0.97). Conclusion: This study provides the characterization of nodular PAP and establishes radiomic and multimodal diagnostic models with similar accuracy, which are reliable tools to make a differential diagnosis between nodular PAP and LUAD and to prevent unnecessary surgery.

Cervical spondylosis, a complex and prevalent condition, demands precise and efficient diagnostic techniques for accurate assessment. While MRI offers detailed visualization of cervical spine anatomy, manual interpretation remains labor-intensive and prone to error. To address this, we developed an innovative AI-assisted Expert-based Diagnosis System that automates both segmentation and diagnosis of cervical spondylosis using MRI. Leveraging multi-center datasets of cervical MRI images from patients with cervical spondylosis, our system features a pathology-guided segmentation model capable of accurately segmenting key cervical anatomical structures. The segmentation is followed by an expert-based diagnostic framework that automates the calculation of critical clinical indicators. Our segmentation model achieved an impressive average Dice coefficient exceeding 0.90 across four cervical spinal anatomies and demonstrated enhanced accuracy in herniation areas. Diagnostic evaluation further showcased the system's precision, with the lowest mean average errors (MAE) for the C2-C7 Cobb angle and the Maximum Spinal Cord Compression (MSCC) coefficient. In addition, our method delivered high accuracy, precision, recall, and F1 scores in herniation localization, K-line status assessment, T2 hyperintensity detection, and Kang grading. Comparative analysis and external validation demonstrate that our system outperforms existing methods, establishing a new benchmark for segmentation and diagnostic tasks for cervical spondylosis.

Osteoporotic vertebral compression fractures (OVCFs) are prevalent in the elderly population, typically assessed on computed tomography (CT) scans by evaluating vertebral height loss. This assessment helps determine the fracture's impact on spinal stability and the need for surgical intervention. However, the absence of pre-fracture CT scans and standardized vertebral references leads to measurement errors and inter-observer variability, while irregular compression patterns further challenge the precise grading of fracture severity. While deep learning methods have shown promise in aiding OVCFs screening, they often lack interpretability and sufficient sensitivity, limiting their clinical applicability. To address these challenges, we introduce a novel vertebra synthesis-height loss quantification-OVCFs grading framework. Our proposed model, HealthiVert-GAN, utilizes a coarse-to-fine synthesis network designed to generate pseudo-healthy vertebral images that simulate the pre-fracture state of fractured vertebrae. This model integrates three auxiliary modules that leverage the morphology and height information of adjacent healthy vertebrae to ensure anatomical consistency. Additionally, we introduce the Relative Height Loss of Vertebrae (RHLV) as a quantification metric, which divides each vertebra into three sections to measure height loss between pre-fracture and post-fracture states, followed by fracture severity classification using a Support Vector Machine (SVM). Our approach achieves state-of-the-art classification performance on both the Verse2019 dataset and in-house dataset, and it provides cross-sectional distribution maps of vertebral height loss. This practical tool enhances diagnostic accuracy in clinical settings and assisting in surgical decision-making.