Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

BACKGROUND: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. OBJECTIVE: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. METHODS: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. RESULTS: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). CONCLUSIONS: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Correction: Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

[This corrects the article DOI: 10.2196/42717.].

Erratum: Correction of Affiliations in the Article "Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019".

This corrects the article on p. e413 in vol. 35, PMID: 33258333.

Sesquiterpene Lactones with Anti-Inflammatory Activity from the Halophyte Sonchus brachyotus DC.

There were five sesquiterpene lactones, belonging to the eudesmanolide class, isolated from the halophyte Sonchus brachyotus DC. The structures of the compounds were determined using spectroscopic methods, including 1D and 2D NMR spectra, MS data, and optical rotation values. Compounds 4 and 5 were characterized by the position of p-hydroxyphenylacetyl group in the sugar moiety. In the evaluation of anti-inflammatory effects on LPS-activated RAW264.7 macrophages, compound 1, 5α,6ßH-eudesma-3,11(13)-dien-12,6α-olide, potently suppressed the expression of iNOS and COS-2, as well as the production of TNF-α, IL-6, and IL-10. Treatment of 1 regulates the Nrf2/HO-1 pathway.

Deep Learning-Based Automatic CT Quantification of Coronavirus Disease 2019 Pneumonia: An International Collaborative Study.

OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.

Antibiofilm Activity of Phorbaketals from the Marine Sponge Phorbas sp. against Staphylococcus aureus.

Biofilm formation by Staphylococcus aureus plays a critical role in the persistence of chronic infections due to its tolerance against antimicrobial agents. Here, we investigated the antibiofilm efficacy of six phorbaketals: phorbaketal A (1), phorbaketal A acetate (2), phorbaketal B (3), phorbaketal B acetate (4), phorbaketal C (5), and phorbaketal C acetate (6), isolated from the Korean marine sponge Phorbas sp. Of these six compounds, 3 and 5 were found to be effective inhibitors of biofilm formation by two S. aureus strains, which included a methicillin-resistant S. aureus. In addition, 3 also inhibited the production of staphyloxanthin, which protects microbes from reactive oxygen species generated by neutrophils and macrophages. Transcriptional analyses showed that 3 and 5 inhibited the expression of the biofilm-related hemolysin gene hla and the nuclease gene nuc1.

Hepatitis virus B and C infections are associated with an increased risk of non-Hodgkin lymphoma: A nested case-control study using a national sample cohort.

BACKGROUND: Hepatitis B virus (HBV) and hepatitis C virus (HCV) are suspected of being associated with non-Hodgkin lymphoma (NHL); however, persuasive data are lacking. Hence, a nested large-population case-control study was performed to investigate such associations in Koreans. METHODS: Data were collected from 929 patients with NHL and 3716 healthy subjects, who were matched 1:4 for age, sex, income, and region of residence, from the Korean Health Insurance Review and Assessment Service-National Sample Cohort. The diagnoses of NHL and HBV/HCV infection were based on the International Classification of Diseases (version 10) codes. Conditional logistic regression models were used to assess odds ratios (ORs) for NHL with respect to HBV or HCV with adjustment for the Charlson comorbidity index. RESULTS: HBV and HCV rates were higher in the NHL group (3.3% and 1.3%, respectively) than in the control group (0.9% and 0.3%, respectively; P < .001 for each). The adjusted OR of hepatitis infection in patients with NHL were 3.25 (95% confidence interval [CI] = 1.99-5.31) for HBV and 3.36 (95% CI = 1.51-7.46) for HCV (P < .001 for each). Subgroups categorized by age (<55 vs ≥55 years) or sex showed significantly higher adjusted ORs of HBV for NHL. Moreover, patients with NHL ≥ 55 years of age or those who were female showed significantly higher adjusted ORs of HCV; those <55 years or who were male also tended to have higher ORs of HCV. CONCLUSION: Infection with either HBV or HCV is associated with NHL in Koreans.

Plasma vs. serum in circulating tumor DNA measurement: characterization by DNA fragment sizing and digital droplet polymerase chain reaction.

Background Choosing the specimen type is the first step of the pre-analytical process. Previous reports suggested plasma as the optimal specimen for circulating tumor DNA (ctDNA) analysis. However, head-to-head comparisons between plasma and serum using platforms with high analytical sensitivity, such as droplet digital polymerase chain reaction (ddPCR), are limited, and several recent studies have supported the clinical utility of serum-derived ctDNA. This study aimed to compare the DNA profiles isolated from plasma and serum, characterize the effects of the differences between specimens on ctDNA measurement, and determine the major contributors to these differences. Methods We isolated cell-free DNA (cfDNA) from 119 matched plasma/serum samples from cancer patients and analyzed the cfDNA profiles by DNA fragment sizing. We then assessed KRAS mutations in ctDNA from matched plasma/serum using ddPCR. Results The amount of large DNA fragments was increased in serum, whereas that of cfDNA fragments (<800 bp) was similar in both specimens. ctDNA was less frequently detected in serum, and the KRAS-mutated fraction in serum was significantly lower than that in plasma. The differences in ctDNA fractions between the two specimen types correlated well with the amount of large DNA fragments and white blood cell and neutrophil counts. Conclusions Our results provided detailed insights into the differences between plasma and serum using DNA fragment sizing and ddPCR, potentially contributing to ctDNA analysis standardization. Our study also suggested that using plasma minimizes the dilution of tumor-derived DNA and optimizes the sensitivity of ctDNA analysis. So, plasma should be the preferred specimen type.

Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019.

BACKGROUND: The Korean Society of Thoracic Radiology (KSTR) recently constructed a nation-wide coronavirus disease 2019 (COVID-19) database and imaging repository, referred to the Korean imaging cohort of COVID-19 (KICC-19) based on the collaborative efforts of its members. The purpose of this study was to provide a summary of the clinico-epidemiological data and imaging data of the KICC-19. METHODS: The KSTR members at 17 COVID-19 referral centers retrospectively collected imaging data and clinical information of consecutive patients with reverse transcription polymerase chain reaction-proven COVID-19 in respiratory specimens from February 2020 through May 2020 who underwent diagnostic chest computed tomography (CT) or radiograph in each participating hospital. RESULTS: The cohort consisted of 239 men and 283 women (mean age, 52.3 years; age range, 11-97 years). Of the 522 subjects, 201 (38.5%) had an underlying disease. The most common symptoms were fever (n = 292) and cough (n = 245). The 151 patients (28.9%) had lymphocytopenia, 86 had (16.5%) thrombocytopenia, and 227 patients (43.5%) had an elevated CRP at admission. The 121 (23.4%) needed nasal oxygen therapy or mechanical ventilation (n = 38; 7.3%), and 49 patients (9.4%) were admitted to an intensive care unit. Although most patients had cured, 21 patients (4.0%) died. The 465 (89.1%) subjects underwent a low to standard-dose chest CT scan at least once during hospitalization, resulting in a total of 658 CT scans. The 497 subjects (95.2%) underwent chest radiography at least once during hospitalization, which resulted in a total of 1,475 chest radiographs. CONCLUSION: The KICC-19 was successfully established and comprised of 658 CT scans and 1,475 chest radiographs of 522 hospitalized Korean COVID-19 patients. The KICC-19 will provide a more comprehensive understanding of the clinical, epidemiological, and radiologic characteristics of patients with COVID-19.

Increased risk of lymphoid malignancy in patients with herpes zoster: a longitudinal follow-up study using a national cohort.

BACKGROUND: The association between herpes zoster and the risk of lymphoid neoplasms in Asian populations has not yet been established. We performed a longitudinal follow-up study using a nationwide cohort to assess the risk of lymphoid neoplasms arising after herpes zoster infection in the adult Korean population. METHODS: Data from participants ≥20 years of age who were registered in the Korean National Health Insurance Service-National Sample Cohort database between 2002 and 2013 were collected. We extracted the data of participants with herpes zoster (n = 59,495) as well as those of matched references at a ratio of 1:4 (n = 237,980) and investigated the subsequent occurrence of lymphoid neoplasms. A stratified Cox proportional hazards model was used to calculate unadjusted hazard ratios (HRs) as well as those adjusted for the Charlson comorbidity index score. RESULTS: The rate of lymphoid neoplasms was higher in the herpes zoster group (0.15% [90/59,495]) than in the reference group (0.08% [212/237,980], P < 0.001). The unadjusted and adjusted HRs of herpes zoster in patients with lymphoid neoplasms were 1.68 (95% confidence interval [CI] = 1.31-2.15) and 1.58 (95% CI = 1.23-2.02), respectively (P < 0.001 for both). On subgroup analyses according to age and sex, herpes zoster was associated with an increased risk of lymphoid neoplasms in all subgroups; the adjusted HRs were 1.53 (95% CI = 1.05-2.24) for patients < 60 years old, 1.58 (95% CI = 1.14-2.20) for patients ≥60 years old, 1.64 (95% CI = 1.16-2.31) for men, and 1.51 (95% CI = 1.06-2.16) for women (P < 0.05 for all). On subgroup analysis of lymphoid neoplasm subtypes, herpes zoster was associated with the risk of Hodgkin's disease (adjusted HR: 3.23 [95% CI = 1.17-8.93]) and multiple myeloma/malignant plasma cell neoplasms (adjusted HR: 2.17 [95% CI = 1.33-3.54]) (P < 0.05 for both). CONCLUSION: Herpes zoster is associated with lymphoid neoplasm development in the Korean population irrespective of age and sex. The risks of Hodgkin's disease and plasma cell neoplasms are significantly elevated in patients with herpes zoster.

A comparison of complete blood count reference intervals in healthy elderly vs. younger Korean adults: a large population study.

Background The use of laboratory reference intervals based on younger populations is of questionable validity in older populations. We established reference intervals for 16 complete blood count (CBC) parameters in healthy elderly Koreans aged ≥60 years and compared them to those of individuals aged 20-59 years. Methods Among 64,532 individuals (39,609 men and 24,923 women) aged ≥20 years who underwent medical checkups, 8151 healthy subjects (12.6%, 5270 men and 2881 women, including 675 and 511, respectively, who were ≥60 years of age) were enrolled based on stringent criteria including laboratory, imaging and endoscopy results; previous medical history; and medication history. CBC parameters were measured using an Advia2120i instrument. Results Overall, healthy individuals aged ≥60 years did not require separate reference intervals from those aged <60 years except for red cell distribution width (RDW) and mean corpuscular hemoglobin (MCH) in women. However, subjects aged ≥60 years still required sex-specific reference intervals for red blood cell count, hemoglobin, hematocrit, MCH, monocytes and eosinophils. Separate reference intervals were required for MCH, eosinophils and basophils for certain age subgroups of men aged ≥60 years, and for MCH and RDW in certain age subgroups of women aged ≥60 years, compared to counterparts <60 years of age. Conclusions Healthy elderly Koreans can use the same reference intervals as younger populations. Thus, abnormal CBC results may not necessarily be attributable to physiologic changes but possible underlying diseases that should be investigated.

Mean Platelet Volume and Platelet Distribution Width Indicate that Platelets Remain Small for Most of Their Lifespans in Patients with Essential Thrombocythemia.

BACKGROUND: Platelets are large when young and immature and shrink as they age. The mean platelet volume (MPV) and platelet distribution width (PDW) reflect the volume and distribution of platelets, respectively. We compared the MPVs and PDWs of patients with immune thrombocytopenic purpura (ITP) or essential thrombocythemia (ET) to those of healthy individuals to test whether these values can reflect the pathomechanisms of these diseases. METHODS: Platelet counts, MPVs, and PDWs were measured in 153 healthy individuals and in 20 and 34 patients with ITP and ET, respectively, using an XN-3000 instrument. RESULTS: The MPVs and PDWs were significantly higher in ITP patients than in healthy individuals or ET patients. The MPVs were significantly lower in ET patients than in both ITP patients and healthy individuals; however, the PDWs in ET patients were similar to those in healthy individuals. The MPVs and PDWs did not correlate with platelet count in ITP or ET patients. CONCLUSIONS: Our data suggested an increased production of young, large platelets and nondiscriminatory destruction of circulating platelets irrespective of their ages in ITP. Decreased MPVs and unelevated PDWs in ET suggest that clonal process-produced platelets remain small throughout their lifespans.

A Myelodysplastic Syndrome with Concurrent Basophilia and Eosinophilia Lacking Oncogenic Mutations in 54 Relevant Genes.

Myelodysplastic syndromes (MDS) with basophilia or eosinophilia are very rare and portend poor prognoses. We present a rare patient who had MDS with excess blasts as well as peripheral basophilia and concurrent bone marrow (BM) basophilia/eosinophilia. She had a complex karyotype including 5q and 7q deletions; however, no oncogenic mutations were observed on next-generation sequencing of 54 genes known to be frequently mutated in acute myeloid leukemia/MDS. Peripheral basophilia resolved after decitabine treatment. Ours is the first report to describe a genome-wide analysis and the use of decitabine to successfully treat basophilia in an MDS patient with concurrent BM basophilia/eosinophilia.

Reclassification of BRCA1 and BRCA2 variants of uncertain significance: a multifactorial analysis of multicentre prospective cohort.

BACKGROUND: BRCA1 and BRCA2 (BRCA1/2) variants classified ambiguously as variants of uncertain significance (VUS) are a major challenge for clinical genetic testing in breast cancer; their relevance to the cancer risk is unclear and the association with the response to specific BRCA1/2-targeted agents is uncertain. To minimise the proportion of VUS in BRCA1/2, we performed the multifactorial likelihood analysis and validated this method using an independent cohort of patients with breast cancer. METHODS: We used a data set of 2115 patients with breast cancer from the nationwide multicentre prospective Korean Hereditary Breast Cancer study. In total, 83 BRCA1/2 VUSs (BRCA1, n=26; BRCA2, n=57) were analysed. The multifactorial probability was estimated by combining the prior probability with the overall likelihood ratio derived from co-occurrence of each VUS with pathogenic variants, personal and family history, and tumour characteristics. The classification was compared with the interpretation according to the American College of Medical Genetics and Genomics-Association for Molecular Pathology (ACMG/AMP) guidelines. An external validation was conducted using independent data set of 810 patients. RESULTS: We were able to redefine 38 VUSs (BRCA1, n=10; BRCA2, n=28). The revised classification was highly correlated with the ACMG/AMP guideline-based interpretation (BRCA1, p for trend=0.015; BRCA2, p=0.001). Our approach reduced the proportion of VUS from 19% (154/810) to 8.9% (72/810) in the retrospective validation data set. CONCLUSION: The classification in this study would minimise the 'uncertainty' in clinical interpretation, and this validated multifactorial model can be used for the reliable annotation of BRCA1/2 VUSs.

Derivation of an endogenous small RNA from double-stranded Sox4 sense and natural antisense transcripts in the mouse brain.

Natural antisense transcripts (NATs) are involved in cellular development and regulatory processes. Multiple NATs at the Sox4 gene locus are spatiotemporally regulated throughout murine cerebral corticogenesis. In the study, we evaluated the potential functional role of Sox4 NATs at Sox4 gene locus. We demonstrated Sox4 sense and NATs formed dsRNA aggregates in the cytoplasm of brain cells. Over expression of Sox4 NATs in NIH/3T3 cells generally did not alter the level of Sox4 mRNA expression or protein translation. Upregulation of a Sox4 NAT known as Sox4ot1 led to the production of a novel small RNA, Sox4_sir3. Its biogenesis is Dicer1-dependent and has characteristics resemble piRNA. Expression of Sox4_sir3 was observed in the marginal and germinative zones of the developing and postnatal brains suggesting a potential role in regulating neurogenesis. We proposed that Sox4 sense-NATs serve as Dicer1-dependent templates to produce a novel endo-siRNA- or piRNA-like Sox4_sir3.

An Ensemble Method for Classifying Regional Disease Patterns of Diffuse Interstitial Lung Disease Using HRCT Images from Different Vendors.

We propose the use of ensemble classifiers to overcome inter-scanner variations in the differentiation of regional disease patterns in high-resolution computed tomography (HRCT) images of diffuse interstitial lung disease patients obtained from different scanners. A total of 600 rectangular 20 × 20-pixel regions of interest (ROIs) on HRCT images obtained from two different scanners (GE and Siemens) and the whole lung area of 92 HRCT images were classified as one of six regional pulmonary disease patterns by two expert radiologists. Textual and shape features were extracted from each ROI and the whole lung parenchyma. For automatic classification, individual and ensemble classifiers were trained and tested with the ROI dataset. We designed the following three experimental sets: an intra-scanner study in which the training and test sets were from the same scanner, an integrated scanner study in which the data from the two scanners were merged, and an inter-scanner study in which the training and test sets were acquired from different scanners. In the ROI-based classification, the ensemble classifiers showed better (p < 0.001) accuracy (89.73%, SD = 0.43) than the individual classifiers (88.38%, SD = 0.31) in the integrated scanner test. The ensemble classifiers also showed partial improvements in the intra- and inter-scanner tests. In the whole lung classification experiment, the quantification accuracies of the ensemble classifiers with integrated training (49.57%) were higher (p < 0.001) than the individual classifiers (48.19%). Furthermore, the ensemble classifiers also showed better performance in both the intra- and inter-scanner experiments. We concluded that the ensemble classifiers provide better performance when using integrated scanner images.

Performance Evaluation of the Roche Cobas 5800 HBV and HCV Tests: Comparison of the 200 and 500 µL Protocols.

Background: Clinical management of patients infected with hepatitis B virus (HBV) or hepatitis C virus (HCV) relies on the viral load (VL). The Cobas 5800 system (Roche Diagnostics) can determine VLs in 200 and 500 µL samples, but the performance of each protocol has not been compared. We evaluated the performance of both protocols for the HBV and HCV tests. Methods: Precision and linearity were verified using commercial panels. Probit analyses were used to determine limits of detection (LoDs). The results obtained with 336 samples were compared using the 200 and 500 µL protocols. Data from 6,737 retrospective HBV and 768 HCV samples were compared to estimate the effects of the different LoDs on the diagnostic results of the protocols. Correlations between protocols were tested with Spearman's rank correlation coefficients (rho). Results: The precision and linearity of both protocols were verified. The LoDs for the 200 and 500 µL protocols were 6.5 and 2.7 IU/mL for HBV and 29.7 and 8.2 IU/mL for HCV, respectively. The agreement between the protocols ranged from 0.8 to 1.0. The results obtained with the HBV and HCV tests showed a strong correlation (rho=0.994). Only 0.4% of HBV and 0.4% of HCV test results were affected by the LoDs of the 200 µL protocol. Conclusions: The Cobas 5800 200 and 500 µL protocols for the HBV DNA and HCV RNA tests demonstrated excellent performance. These findings establish the 200 µL protocol as a new option for low-volume samples, especially for pediatric and difficult-to-bleed patients.

Temporally resolved proteomics identifies nidogen-2 as a cotarget in pancreatic cancer that modulates fibrosis and therapy response.

Pancreatic ductal adenocarcinoma (PDAC) is characterized by increasing fibrosis, which can enhance tumor progression and spread. Here, we undertook an unbiased temporal assessment of the matrisome of the highly metastatic KPC (Pdx1-Cre, LSL-KrasG12D/+, LSL-Trp53R172H/+) and poorly metastatic KPflC (Pdx1-Cre, LSL-KrasG12D/+, Trp53fl/+) genetically engineered mouse models of pancreatic cancer using mass spectrometry proteomics. Our assessment at early-, mid-, and late-stage disease reveals an increased abundance of nidogen-2 (NID2) in the KPC model compared to KPflC, with further validation showing that NID2 is primarily expressed by cancer-associated fibroblasts (CAFs). Using biomechanical assessments, second harmonic generation imaging, and birefringence analysis, we show that NID2 reduction by CRISPR interference (CRISPRi) in CAFs reduces stiffness and matrix remodeling in three-dimensional models, leading to impaired cancer cell invasion. Intravital imaging revealed improved vascular patency in live NID2-depleted tumors, with enhanced response to gemcitabine/Abraxane. In orthotopic models, NID2 CRISPRi tumors had less liver metastasis and increased survival, highlighting NID2 as a potential PDAC cotarget.

Quantitative assessment of change in regional disease patterns on serial HRCT of fibrotic interstitial pneumonia with texture-based automated quantification system.

OBJECTIVES: To evaluate the usefulness of a texture-based automated quantification system (AQS) for evaluating the extent and interval change of regional disease patterns on initial and follow-up high-resolution computed tomographies (HRCTs) of fibrotic interstitial pneumonia (FIP). METHODS: Eighty-nine patients with clinically and/or biopsy confirmed usual interstitial pneumonia (UIP) (n = 71) and non-specific interstitial pneumonia (NSIP) (n = 18) were included. An AQS to quantify five disease patterns (ground-glass opacity [GGO], reticular opacity [RO], honeycombing [HC], emphysema [EMPH], consolidation [CONS]) and normal lung was developed. The extent and interval changes of each disease pattern, FS (fibrosis score), TA (total abnormal lung fraction) of entire lung on initial and 1-year follow-up HRCTs were quantified. The agreement between the results of AQS and two readers was assessed. Results of AQS were correlated with forced vital capacity (FVC) and carbon monoxide diffusing capacity (DLco). RESULTS: The Intraclass correlation coefficient (ICC) study revealed acceptable agreement between visual assessment and AQS (r = 0.78, 0.66 for HC; 0.76, 0.61 for FS; 0.64, 0.68 for TA, initial and follow-up HRCTs, respectively). Linear regression analysis revealed the extent of HC, TA on initial CT, interval changes of FS contributed negatively to DLco, and interval changes of FS, TA contributed negatively to FVC. CONCLUSIONS: Our AQS is comparable with visual assessment for evaluating the disease extent and the interval changes of FIP on HRCT.