Repository Collection:

COPD Multi-Task Diagnosis on Chest X-Ray Using CNN-Based Slot Attention

2025-12-31T15:00:00Z

Title: COPD Multi-Task Diagnosis on Chest X-Ray Using CNN-Based Slot Attention All Author(s): Wangsu Jeon; Hyeonung Jang; Hongchang Lee; Seongjun Choi Abstract: This study proposes a unified deep-learning framework for the concurrent classification of Chronic Obstructive Pulmonary Disease (COPD) severity and regression of the FEV1/FVC ratio from chest X-ray (CXR) images. We integrated a ConvNeXt-Large backbone with a Slot Attention mechanism to effectively disentangle and refine disease-relevant features for multi-task learning. Evaluation on a clinical dataset demonstrated that the proposed model with a 5-slot configuration achieved superior performance compared to standard CNN and Vision Transformer baselines. On the independent test set, the model attained an Accuracy of 0.9107, Sensitivity of 0.8603, and Specificity of 0.9324 for three-class severity stratification. Simultaneously, it achieved a Mean Absolute Error (MAE) of 8.2649 and a Mean Squared Error (MSE) of 151.4704, and an R2 of 0.7591 for FEV1/FVC ratio estimation. Qualitative analysis using saliency maps also suggested that the slot-based approach contributes to attention patterns that are more constrained to clinically relevant pulmonary structures. These results suggest that our slot-attention-based multi-task model offers a robust solution for automated COPD assessment from standard radiographs.

Diagnostic Accuracy and Clinical Value of a Domain-specific Multimodal Generative AI Model for Chest Radiograph Report Generation

2024-12-31T15:00:00Z

Title: Diagnostic Accuracy and Clinical Value of a Domain-specific Multimodal Generative AI Model for Chest Radiograph Report Generation All Author(s): Eun Kyoung Hong; Jiyeon Ham; Byungseok Roh; Jawook Gu; Beomhee Park; Sunghun Kang; Kihyun You; Jihwan Eom; Byeonguk Bae; Jae-Bock Jo; Ok Kyu Song; Woong Bae; Ro Woon Lee; Chong Hyun Suh; Chan Ho Park; Seong Jun Choi; Jai Soung Park; Jae-Hyeong Park; Hyun Jeong Jeon; Jeong-Ho Hong; Dosang Cho; Han Seok Choi; Tae Hee Kim Abstract: Background Generative artificial intelligence (AI) is anticipated to alter radiology workflows, requiring a clinical value assessment for frequent examinations like chest radiograph interpretation. Purpose To develop and evaluate the diagnostic accuracy and clinical value of a domain-specific multimodal generative AI model for providing preliminary interpretations of chest radiographs. Materials and Methods For training, consecutive radiograph-report pairs from frontal chest radiography were retrospectively collected from 42 hospitals (2005–2023). The trained domain-specific AI model generated radiology reports for the radiographs. The test set included public datasets (PadChest, Open-i, VinDr-CXR, and MIMIC-CXR-JPG) and radiographs excluded from training. The sensitivity and specificity of the model-generated reports for 13 radiographic findings, compared with radiologist annotations (reference standard), were calculated (with 95% CIs). Four radiologists evaluated the subjective quality of the reports in terms of acceptability, agreement score, quality score, and comparative ranking of reports from (a) the domain-specific AI model, (b) radiologists, and (c) a general-purpose large language model (GPT-4Vision). Acceptability was defined as whether the radiologist would endorse the report as their own without changes. Agreement scores from 1 (clinically significant discrepancy) to 5 (complete agreement) were assigned using RADPEER; quality scores were on a 5-point Likert scale from 1 (very poor) to 5 (excellent). Results A total of 8 838 719 radiograph-report pairs (training) and 2145 radiographs (testing) were included (anonymized with respect to sex and gender). Reports generated by the domain-specific AI model demonstrated high sensitivity for detecting two critical radiographic findings: 95.3% (181 of 190) for pneumothorax and 92.6% (138 of 149) for subcutaneous emphysema. Acceptance rate, evaluated by four radiologists, was 70.5% (6047 of 8680), 73.3% (6288 of 8580), and 29.6% (2536 of 8580) for model-generated, radiologist, and GPT-4Vision reports, respectively. Agreement scores were highest for the model-generated reports (median = 4 [IQR, 3–5]) and lowest for GPT-4Vision reports (median = 1 [IQR, 1–3]; P < .001). Quality scores were also highest for the model-generated reports (median = 4 [IQR, 3–5]) and lowest for the GPT-4Vision reports (median = 2 [IQR, 1–3]; P < .001). From the ranking analysis, model-generated reports were most frequently ranked the highest (60.0%; 5146 of 8580), and GPT-4Vision reports were most frequently ranked the lowest (73.6%; 6312 of 8580). Conclusion A domain-specific multimodal generative AI model demonstrated potential for high diagnostic accuracy and clinical value in providing preliminary interpretations of chest radiographs for radiologists.

Innate immune signatures in the nasopharynx after SARS-CoV-2 infection and links with the clinical outcome of COVID-19 in Omicron-dominant period

2023-12-31T15:00:00Z

Title: Innate immune signatures in the nasopharynx after SARS-CoV-2 infection and links with the clinical outcome of COVID-19 in Omicron-dominant period All Author(s): Hyunkyung Cha; Chan Mi Lee; Sujin Kim; Chang Kyung Kang; Pyoeng Gyun Choe; Yoon Kyung Jeon; Hyeon Jae Jo; Nam Joong Kim; Wan Beom Park; Hyun Jik Kim Abstract: While severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is characterized by impaired induction of interferons (IFNs) and IFN-stimulated genes (ISGs), the IFNs and ISGs in upper airway is essential to restrict the spread of respiratory virus. Here, we identified the prominent IFN and ISG upregulation in the nasopharynx (NP) of mild and even severe coronavirus disease 2019 (COVID-19) patients (CoV2+) in Omicron era and to compare their clinical outcome depending on the level of IFNs and ISGs. Whereas the induction of IFNB was minimal, transcription of IFNA, IFNG, and IFNLs was significantly increased in the NP of CoV2 + patients. IFNs and ISGs may be more upregulated in the NP of CoV2 + patients at early phases of infection according to viral RNA levels and this is observed even in severe cases. IFN-related innate immune response might be characteristic in macrophages and monocytes at the NP and the CoV2 + patients with higher transcription of IFNs and ISGs in the NP showed a correlation with good prognosis of COVID-19. This study presents that IFNs and ISGs may be upregulated in the NP, even in severe CoV2 + patients depending on viral replication during Omicron-dominant period and the unique IFN-responsiveness in the NP links with COVID-19 clinical outcomes.

Responses of nasal polyp-derived macrophages to inflammatory cues and potential pathological roles in type 2 chronic rhinosinusitis with nasal polyps

2024-12-31T15:00:00Z

Title: Responses of nasal polyp-derived macrophages to inflammatory cues and potential pathological roles in type 2 chronic rhinosinusitis with nasal polyps All Author(s): Hyunkyung Cha; Ara Jo; Hee-Suk Lim; Kyoung Mi Eun; Jin-A Park; Seung-No Hong; Dae Woo Kim Abstract: Objective.: The role of highly plastic and heterogeneous macrophages in the pathogenesis of nasal polyps (NP) is not well understood. We aimed to investigate the distribution and responses of NP-derived macrophages to inflammatory cues according to endotypes of chronic rhinosinusitis with nasal polyps (CRSwNP). Methods.: The distribution of macrophage subsets was analyzed using NP bulk RNA sequencing data with CIBERSORTx program. The cytokines and chemokines produced by NP-derived macrophages following stimulation with interleukin-4 (IL-4), staphylococcal enterotoxin B (SEB), and lipopolysaccharide (LPS) were evaluated using a multiplex cytokine assay. Immunofluorescence staining in NP tissues was conducted to validate the findings. Results.: Type 2 (T2) CRSwNP exhibited a significantly higher proportion of M2 macrophages, whereas both M1 and M2 macrophage populations were elevated in non-type 2 (NT2) CRSwNP. Baseline cytokine analysis of NP-derived macrophages revealed an increase in TSLP levels in CRSwNP compared to controls. Furthermore, TSLP expression was significantly upregulated from baseline levels following IL-4 or SEB stimulation in T2 CRSwNP. Notably, IL-4 stimulation led to an increase in OSM only in T2 CRSwNP. Additionally, the number and proportion of TSLP- and OSM-expressing cells among CD163-positive cells were significantly higher in the NP of T2 CRSwNP patients. Conclusion.: NP-derived macrophages from T2 CRSwNP exhibit elevated expression of TSLP and OSM in response to IL-4 or SEB, potentially contributing to the pathophysiology of T2 CRSwNP.