Deep Learning-based Outcome Prediction in Progressive Fibrotic Lung Disease Using High-Resolution Computed Tomography.

Rationale: Reliable outcome prediction in patients with fibrotic lung disease using baseline high-resolution computed tomography (HRCT) data remains challenging. Objectives: To evaluate the prognostic accuracy of a deep learning algorithm (SOFIA [Systematic Objective Fibrotic Imaging Analysis Algorithm]), trained and validated in the identification of usual interstitial pneumonia (UIP)-like features on HRCT (UIP probability), in a large cohort of well-characterized patients with progressive fibrotic lung disease drawn from a national registry. Methods: SOFIA and radiologist UIP probabilities were converted to Prospective Investigation of Pulmonary Embolism Diagnosis (PIOPED)-based UIP probability categories (UIP not included in the differential, 0-4%; low probability of UIP, 5-29%; intermediate probability of UIP, 30-69%; high probability of UIP, 70-94%; and pathognomonic for UIP, 95-100%), and their prognostic utility was assessed using Cox proportional hazards modeling. Measurements and Main Results: In multivariable analysis adjusting for age, sex, guideline-based radiologic diagnosis, anddisease severity (using total interstitial lung disease [ILD] extent on HRCT, percent predicted FVC, DlCO, or the composite physiologic index), only SOFIA UIP probability PIOPED categories predicted survival. SOFIA-PIOPED UIP probability categories remained prognostically significant in patients considered indeterminate (n = 83) by expert radiologist consensus (hazard ratio, 1.73; P < 0.0001; 95% confidence interval, 1.40-2.14). In patients undergoing surgical lung biopsy (n = 86), after adjusting for guideline-based histologic pattern and total ILD extent on HRCT, only SOFIA-PIOPED probabilities were predictive of mortality (hazard ratio, 1.75; P < 0.0001; 95% confidence interval, 1.37-2.25). Conclusions: Deep learning-based UIP probability on HRCT provides enhanced outcome prediction in patients with progressive fibrotic lung disease when compared with expert radiologist evaluation or guideline-based histologic pattern. In principle, this tool may be useful in multidisciplinary characterization of fibrotic lung disease. The utility of this technology as a decision support system when ILD expertise is unavailable requires further investigation.

Biomarker signatures for progressive idiopathic pulmonary fibrosis.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease in which circulatory biomarkers have the potential for guiding management in clinical practice. We assessed the prognostic role of serum biomarkers in three independent IPF cohorts: Australian Idiopathic Pulmonary Fibrosis Registry (AIPFR), Trent Lung Fibrosis (TLF) and Prospective Observation of Fibrosis in the Lung Clinical Endpoints (PROFILE). METHODS: In the AIPFR cohort, candidate proteins were assessed by ELISA as well as in an unbiased proteomic approach. LASSO (least absolute shrinkage and selection operator) regression was used to restrict the selection of markers that best accounted for the progressor phenotype at 1 year in the AIPFR cohort, and subsequently prospectively selected for replication in the validation TLF cohort and assessed retrospectively in the PROFILE cohort. Four significantly replicating biomarkers were aggregated into a progression index model based on tertiles of circulating concentrations. RESULTS: 189 participants were included in the AIPFR cohort, 205 participants from the TLF cohort and 122 participants from the PROFILE cohort. Differential biomarker expression was observed by ELISA and replicated for osteopontin, matrix metallopeptidase-7, intercellular adhesion molecule-1 and periostin for those with a progressor phenotype at 1 year. Proteomic data did not replicate. The progression index in the AIPFR, TLF and PROFILE cohorts predicted risk of progression, mortality and progression-free survival. A statistical model incorporating the progression index demonstrated the capacity to distinguish disease progression at 12 months, which was increased beyond the clinical GAP (gender, age and physiology) score model alone in all cohorts, and significantly so within the incidence-based TLF and PROFILE cohorts. CONCLUSION: A panel of circulatory biomarkers can provide potentially valuable clinical assistance in the prognosis of IPF patients.

Melanoma with osseous or chondroid differentiation: a report of eight cases including SATB2 expression and mutation analysis.

Melanoma can present with osteocartilaginous differentiation, however few reports exist on this rare subtype. We present eight cases of melanoma with osteocartilaginous differentiation to highlight its clinical, pathological and molecular features. The cases showed no association with gender (5 males and 3 females) or age (range 23-84 years). Cases included both primary melanomas and distant metastases (6 and 2, respectively), with the majority arising from cutaneous sites (7/8) and the remaining case from a mucosal site. Tumour-infiltrating lymphocyte (TIL) score ranged from 0 to 3 (median 1), and 2/8 lesions had evidence of inflammatory changes or antecedent trauma. No recurrent mutations were found in the tumours by next generation sequencing, and the mutations observed were typical of melanoma rather than osteosarcomatous lesions. The majority of tumours stained positive for melanoma markers including S100, HMB45, Melan-A, SOX10 and MITF. Staining of the osteoblastic marker SATB2 varied from negative to widespread positive. We demonstrate that melanomas with osteocartilaginous differentiation are heterogeneous in presentation and are not typified by a recurrent mutation in cancer associated genes. Where uncertainty exists in diagnosing an osteocartilaginous lesion, a diagnosis of melanoma can be supported by the presence of genomic mutations typical of melanoma such as BRAF, NRAS and NF1, and IHC staining positive for S100, HMB45, Melan-A, SOX10 and MITF. SATB2 may be positive in these lesions and thus should not be used to rule out melanoma.

Cryobiopsy versus open lung biopsy in the diagnosis of interstitial lung disease (COLDICE): protocol of a multicentre study.

Introduction: Transbronchial lung cryobiopsy (TBLC) is a novel, minimally invasive technique for obtaining lung tissue for histopathological assessment in interstitial lung disease (ILD). Despite its increasing popularity, the diagnostic accuracy of TBLC is not yet known. The COLDICE Study (Cryobiopsy versus Open Lung biopsy in the Diagnosis of Interstitial lung disease allianCE) aims to evaluate the agreement between TBLC and surgical lung biopsy sampled concurrently from the same patients, for both histopathological and multidisciplinary discussion (MDD) diagnoses. Methods and analysis: This comparative, multicentre, prospective trial is enrolling patients with ILD requiring surgical lung biopsy to aid with their diagnosis. Participants are consented for both video-assisted thoracoscopic surgical (VATS) biopsy and TBLC within the same anaesthetic episode. Specimens will be blindly assessed by three expert pathologists both individually and by consensus. Each tissue sample will then be considered in conjunction with clinical and radiological data, within a centralised MDD. Each patient will be presented twice in random order, once with TBLC data and once with VATS data. Meeting participants will be blinded to the method of tissue sampling. The accuracy of TBLC will be assessed by agreement with VATS at (1) histopathological analysis and (2) MDD diagnosis. Data will be collected on interobserver agreement between pathologists, interobserver agreement between MDD participants, and detailed clinical and procedural characteristics. Ethics and dissemination: The study is being conducted in accordance with the International Conference on Harmonisation Guideline for Good Clinical Practice and Australian legislation for the ethical conduct of research. Trial registration number: ACTRN12615000718549.

Gastroesophageal reflux and antacid therapy in IPF: analysis from the Australia IPF Registry.

BACKGROUND AND OBJECTIVE: Gastroesophageal reflux disease (GORD) is highly prevalent in idiopathic pulmonary fibrosis (IPF) and may play a role in its pathogenesis. Recent IPF treatment guidelines suggest that all patients with IPF be considered for antacid therapy. However, emerging evidence suggests that antacid therapy does not improve IPF patient outcomes and may increase the risk of pulmonary infection. METHODS: Using prospectively collected data from the Australian IPF Registry including use of antacid therapy, GORD diagnosis and GORD symptoms, the relationship of these GORD variables to survival and disease progression was assessed. The severity of GORD symptoms using the frequency scale for symptoms of GORD (FSSG) and its relationships to outcomes was also assessed for the first time in an IPF cohort. RESULTS: Five hundred eighty-seven (86%) of the 684 patients in the Australian IPF Registry were eligible for inclusion. Patients were mostly male (69%), aged 71.0 ± 8.5 years with moderate disease (FVC 81.7 ± 21.5%; DLco 48.5 ± 16.4%). Most patients were taking antacids (n = 384; 65%), though fewer had a diagnosis of GORD (n = 243, 41.4%) and typical GORD symptoms were even less common (n = 171, 29.1%). The mean FSSG score was 8.39 ± 7.45 with 43% (n = 251) having a score > 8. Overall, there was no difference in survival or disease progression, regardless of antacid treatment, GORD diagnosis or GORD symptoms. CONCLUSIONS: Neither the use of antacid therapy nor the presence of GORD symptoms affects longer term outcomes in IPF patients. This contributes to the increasing evidence that antacid therapy may not be beneficial in IPF patients and that GORD directed therapy should be considered on an individual basis to treat the symptoms of reflux.

Implications of the diagnostic criteria of idiopathic pulmonary fibrosis in clinical practice: Analysis from the Australian Idiopathic Pulmonary Fibrosis Registry.

BACKGROUND AND OBJECTIVE: Current guidelines for the diagnosis of idiopathic pulmonary fibrosis (IPF) provide specific criteria for diagnosis in the setting of multidisciplinary discussion (MDD). We evaluate the utility and reproducibility of these diagnostic guidelines, using clinical data from the Australian IPF Registry. METHODS: All patients enrolled in the registry undergo a diagnostic review whereby international IPF guidelines are applied via a registry MDD. We investigated the clinical applicability of these guidelines with regard to: (i) adherence to guidelines, (ii) Natural history of IPF diagnostic categories and (iii) Concordance for diagnostic features. RESULTS: A total of 417 participants (69% male, 70.6 ± 8.0 years) with a clinical diagnosis of IPF underwent MDD. The 23% of participants who did not meet IPF diagnostic criteria displayed identical disease behaviour to those with confirmed IPF. Honeycombing on radiology was associated with a worse prognosis and this translated into poorer prognosis in the 'definite' IPF group. While there was moderate agreement for IPF diagnostic categories, agreement for specific radiological features, other than honeycombing, was poor. CONCLUSION: In clinical practice, physicians do not always follow IPF diagnostic guidelines. We demonstrate a cohort of IPF patients who do not meet IPF diagnostic guideline criteria, based largely on their radiology and lack of lung biopsy, but who have outcomes identical to those with IPF.

Baseline characteristics of idiopathic pulmonary fibrosis: analysis from the Australian Idiopathic Pulmonary Fibrosis Registry.

7The prevalence of idiopathic pulmonary fibrosis (IPF), a fatal and progressive lung disease, is estimated at 1.25-63 out of 100 000, making large population studies difficult. Recently, the need for large longitudinal registries to study IPF has been recognised.The Australian IPF Registry (AIPFR) is a national registry collating comprehensive longitudinal data of IPF patients across Australia. We explored the characteristics of this IPF cohort and the effect of demographic and physiological parameters and specific management on mortality.Participants in the AIPFR (n=647, mean age 70.9±8.5 years, 67.7% male, median follow up 2 years, range 6 months-4.5 years) displayed a wide range of age, disease severity and co-morbidities that is not present in clinical trial cohorts. The cumulative mortality rate in year one, two, three and four was 5%, 24%, 37% and 44% respectively. Baseline lung function (forced vital capacity, diffusing capacity of the lung for carbon monoxide, composite physiological index) and GAP (gender, age, physiology) stage (hazard ratio 4.64, 95% CI 3.33-6.47, p<0.001) were strong predictors of mortality. Patients receiving anti-fibrotic medications had better survival (hazard ratio 0.56, 95% CI 0.34-0.92, p=0.022) than those not on anti-fibrotic medications, independent of underlying disease severity.The AIPFR provides important insights into the understanding of the natural history and clinical management of IPF.

Clinical impact of the interstitial lung disease multidisciplinary service.

BACKGROUND AND OBJECTIVE: Multidisciplinary discussions (MDDs) have been shown to improve diagnostic accuracy in interstitial lung disease (ILD) diagnosis. However, their clinical impact on patient care has never been clearly demonstrated. We describe the effect that an ILD multidisciplinary service has upon the diagnosis and management of patients with suspected ILD. METHODS: Patients at two specialized centres with suspected ILD underwent ILD multidisciplinary team review (ILD-MDT) (standard ILD clinic visit and diagnostic review at ILD-MDD). We compared changes in ILD diagnosis and management at referral to those following the ILD-MDT. RESULTS: Ninety patients, 60% males (54/90), aged 67.3 years (SD = 11.4) were reviewed for suspected ILD. Overall, the ILD-MDT resulted in a change in specific ILD diagnosis in 48/90 (53%) patients. Of the 27 patients referred with a diagnosis of idiopathic pulmonary fibrosis (IPF), the diagnosis was changed at MDD in 10 patients. In contrast, seven patients had their diagnosis changed to IPF. There was also a significant reduction in 'unclassifiable' diseases and disease behaviour classifications provided additional information beyond ILD diagnosis. CONCLUSION: Dedicated tertiary ILD-MDT service has an important clinical impact on the care of the ILD patient, with frequent changes in ILD diagnosis and subsequent management. Further research to investigate long-term clinical outcomes of ILD-MDT is required.

Lung asbestos content in lungs resected for primary lung cancer.

INTRODUCTION: The majority of Australia's burden of lung cancer occurs in current or former tobacco smokers. To determine the possible contribution of asbestos exposure in Australians presenting with primary lung cancer, we measured lung asbestos content in cases resected consecutively at a single cardio-thoracic hospital. METHODS: Asbestos bodies were quantified by lung tissue digestion, filtration, and light microscopy, and were correlated with exposure questionnaires and clinicopathological features. RESULTS: We demonstrate high intrarater reproducibility and interrater reliability using these methods. In 463 patients with resected primary lung cancers, asbestos content ranged from 0 to 749 asbestos bodies per gram wet weight (AB/gww). Forty-eight percent of patients had no asbestos bodies identified. One-third had less than or equal to 20 AB/gww (a level previously found to be consistent with urban dwelling). Nineteen percent had lung content in excess of this level. Only 20 cases had AB >100/gww, approximately equivalent to the Helsinki threshold for attribution of lung cancer to asbestos. Median asbestos body counts were higher in patients who reported previous asbestos exposure than in those who reported no exposure. A subgroup of cases gave detailed exposure histories that did not predict presence or absence of asbestos bodies in men or women. In cases with cumulative tobacco exposure less than 20 pack-years, asbestos body counts exceeding 20 AB/gww were overrepresented. CONCLUSIONS: We found that the majority of patients with primary lung cancer at a single Australian center have detectable asbestos in resected lung tissue, but fiber burdens are generally low. The contributory role of this low-level asbestos exposure in causing lung cancer remains uncertain.

Pulmonary fibrosis and ferruginous bodies associated with exposure to synthetic fibers.

Exposure to synthetic fibers with employment in textile mills can be associated with an elevated risk of interstitial lung disease (ILD). A mechanism of injury has not been determined. ILD can follow exposures to inorganic fibers (e.g., asbestos) which are associated with a mobilization of iron and catalysis of an oxidative stress. We describe 2 patients with ILD associated with exposure to synthetic textile fibers who demonstrated carbon-based ferruginous bodies suggesting an in vivo accumulation of iron by synthetic fibers after deposition in the lung. These iron-laden bodies varied from perfectly linear fibers to almost particulate matter. Linear structures were irregularly interrupted by deposition of iron-abundant material. The capacity of these synthetic fibers to complex iron and generate an oxidative stress is confirmed in vitro.