scispace - formally typeset
Search or ask a question

Showing papers by "Andrew G. Nicholson published in 2019"


Journal ArticleDOI
TL;DR: A new approach—based on deep convolutional neural networks—called MesoNet is developed to accurately predict the overall survival of mesothelioma patients from whole-slide digitized images, without any pathologist-provided locally annotated regions, and it is demonstrated that the model was more accurate in predicting patient survival than using current pathology practices.
Abstract: Malignant mesothelioma (MM) is an aggressive cancer primarily diagnosed on the basis of histological criteria1. The 2015 World Health Organization classification subdivides mesothelioma tumors into three histological types: epithelioid, biphasic and sarcomatoid MM. MM is a highly complex and heterogeneous disease, rendering its diagnosis and histological typing difficult and leading to suboptimal patient care and decisions regarding treatment modalities2. Here we have developed a new approach-based on deep convolutional neural networks-called MesoNet to accurately predict the overall survival of mesothelioma patients from whole-slide digitized images, without any pathologist-provided locally annotated regions. We validated MesoNet on both an internal validation cohort from the French MESOBANK and an independent cohort from The Cancer Genome Atlas (TCGA). We also demonstrated that the model was more accurate in predicting patient survival than using current pathology practices. Furthermore, unlike classical black-box deep learning methods, MesoNet identified regions contributing to patient outcome prediction. Strikingly, we found that these regions are mainly located in the stroma and are histological features associated with inflammation, cellular diversity and vacuolization. These findings suggest that deep learning models can identify new features predictive of patient survival and potentially lead to new biomarker discoveries.

306 citations


Journal ArticleDOI
TL;DR: The questions cover topics such as the best IHC markers for distinguishing NSCLC subtypes, differences in thyroid transcription factor 1 clones, and the utility of IHC in diagnosing uncommon subtypes of lung cancer and distinguishing primary from metastatic tumors.

195 citations


Journal ArticleDOI
TL;DR: This review focuses on improving early disease recognition and evaluating its pathophysiological impact and discusses working approaches for its management.
Abstract: Pleuroparenchymal fibroelastosis (PPFE) is an unusual pulmonary disease with unique clinical, radiological, and pathological characteristics. Designated a rare idiopathic interstitial pneumonia in 2013, its name refers to a combination of fibrosis involving the visceral pleura and fibroelastotic changes predominating in the subpleural lung parenchyma. Although a number of disease associations have been described, no single cause of PPFE has been unequivocally identified. A diagnosis of PPFE is most commonly achieved by identifying characteristic abnormalities on computed tomographic scans. The earliest changes are consistently located in the upper lobes close to the lung apices, the same locations where subsequent disease progression is also most conspicuous. When sufficiently severe, the disease leads to progressive volume loss of the upper lobes, which, in combination with decreased body mass, produces platythorax. Once regarded as a slowly progressing entity, it is now acknowledged that some patients with PPFE follow an inexorably progressive course that culminates in irreversible respiratory failure and early death. In the absence of effective medical drug treatment, lung transplant remains the only therapeutic option for this disorder. This review focuses on improving early disease recognition and evaluating its pathophysiological impact and discusses working approaches for its management.

90 citations


Book ChapterDOI
01 Jan 2019
TL;DR: This chapter discusses the spectrum of congenital lung disease from the upper airway down to the lung parenchyma and microvasculature, and associated relevant malformations in the chest wall and mediastinum, and systemically.
Abstract: This chapter discusses the spectrum of congenital lung disease from the upper airway down to the lung parenchyma and microvasculature, and associated relevant malformations in the chest wall and mediastinum, and systemically. A systematic way of describing an individual malformation is proposed, using clear words to delineate the components of the malformation before planning treatment. Congenital lung disease may present in utero right up to old age. Many large malformations diagnosed antenatally largely regress in the third trimester of pregnancy, and are only detectable postnatally on computed tomography (CT) scanning. Management of asymptomatic congenital cystic malformations is controversial; many remain symptom free for a long time, whereas others become the seat of infection or malignancy, or result in other complications, such as air embolism. Histological overlap between what were once thought of as discrete entities, such as congenital cystic adenomatoid malformation and sequestration, are common, and attempting to determine histology from clinical images is fraught with difficulty. Newer imaging techniques, such as magnetic resonance and CT angiography, are increasingly used to image congenital lung malformations, with conventional angiography reserved for situations when therapeutic embolization of the malformation is being considered. Advances in surgical techniques, in particular for congenital diaphragmatic hernia, mean that there are more survivors into childhood and adult life. The optimal follow-up for patients with congenital lung malformations, whether surgically treated or not, remains to be determined.

32 citations


Journal ArticleDOI
TL;DR: Contrary to current classifications, NEHI, PIG, and ACD-CAD should be considered as overlapping manifestations of pulmonary dysmaturation, frequently associated with disorders of alveolar growth, rather than as separate conditions.

28 citations


Journal ArticleDOI
TL;DR: The role of large-scale somatically acquired mutations in mitochondrial DNA (mtDNA) and consecutive respiratory chain dysfunction as a trigger of ROS-formation and lung fibrosis is investigated and acquired mtDNA-mutations may both trigger and perpetuate ROS- formation in ILD.
Abstract: Reactive oxygen species (ROS) are implicated in the aetiology of interstitial lung disease (ILD). We investigated the role of large-scale somatically acquired mutations in mitochondrial DNA (mtDNA) and consecutive respiratory chain dysfunction as a trigger of ROS-formation and lung fibrosis. Mitochondria were analysed in lung biopsies from 30 patients with idiopathic or connective tissue disease (CTD)-related ILD and 13 controls. In 17 patients we had paired biopsies from upper and lower lobes. Control samples were taken from lung cancer resections without interstitial fibrosis. Malondialdehyde, a marker of ROS-formation, was elevated in ILD-biopsies (p = 0.044). The activity of the mitochondrial respiratory chain (cytochrome c-oxidase/succinate dehydrogenase [COX/SDH]-ratio) was depressed in ILD (median = 0.10,) compared with controls (0.12, p < 0.001), as was the expression of mtDNA-encoded COX-subunit-2 protein normalized for the nucleus-encoded COX-subunit-4 (COX2/COX4-ratio; ILD-median = 0.6; controls = 2.2; p < 0.001). Wild-type mtDNA copies were slightly elevated in ILD (p = 0.088). The common mtDNA deletion was only present at low levels in controls (median = 0%) and at high levels in ILD (median = 17%; p < 0.001). In ILD-lungs with paired biopsies, lower lobes contained more malondialdehyde and mtDNA deletions than upper lobes and had lower COX2/COX4-ratios and COX/SDH-ratios (all p < 0.001). Acquired mtDNA-mutations and consecutive respiratory chain dysfunction may both trigger and perpetuate ROS-formation in ILD.

27 citations


Journal ArticleDOI
TL;DR: Three cases presenting with recurrent pulmonary haemorrhage who, several years after first presentation, develop anti myeloperoxidase antibodies (MPO) positivity, emphysema on CT and, in one case, renal involvement, highlight a possible role played by autoimmune phenomena, even when DAH is initially diagnosed as “idiopathic”.
Abstract: Diffuse alveolar haemorrhage (DAH) is characterized by the diffuse accumulation of red blood cells within the alveoli, presence of ground glass opacities and/or consolidation on computed tomography (CT). Aside from identifiable non-immune causes, DAH is classically subdivided into idiopathic (idiopathic pulmonary haemosiderosis, IPH) and autoimmune DAH. Here we describe three cases presenting with recurrent pulmonary haemorrhage, initially classified as IPH, who, several years after first presentation, develop anti myeloperoxidase antibodies (MPO) positivity, emphysema on CT and, in one case, renal involvement. Patient 1 was diagnosed with IPH aged 14. Her disease remained poorly controlled despite immunosuppression, although ANCA remained negative over the years. Nineteen years from initial presentation, she developed MPO-ANCA positive antibodies and mild renal impairment. She was treated with Rituximab with good response. From first presentation, the chest CT was consistently characterized by diffuse ground-glass opacities and interlobular septal thickening. Ten years later, cystic opacities consistent with emphysema, with a striking peribronchovascular distribution, developed. Patient 2 was diagnosed with IPH aged 32. He was treated with corticosteroids and methotrexate, with fluctuating response. At 11 years from initial presentation, MPO-ANCA positivity was identified, and emphysema with a peribronchovascular distribution was observed on CT, with subsequent significant increase in extent. Patient 3 was diagnosed with IPH at the age of seven, and had recurrent episodes of haemoptysis of varying degree of severity, treated with intermittent courses of corticosteroids until age 11, when he was intubated due to severe DAH. Eight years after the diagnosis emphysematous changes were noted on CT and MPO-ANCA positivity developed for the first time 11 years after initial diagnosis. We believe these three cases highlight: 1) the possibility of development of ANCA positivity several years down the line from first DAH presentation 2) the possibility that DAH may lead to cystic/emphysematous changes with peribronchovascular distribution on CT. Moreover, the need for ongoing immunosuppressive treatment and the development of emphysema, emphasize a possible role played by autoimmune phenomena, even when DAH is initially diagnosed as “idiopathic”. Further studies are required to better understand the relationship between DAH, ANCA positivity and development of emphysema.

23 citations


Journal ArticleDOI
TL;DR: A randomised trial of smokers with COPD showed that a proposed sequential policy using sputum testing to select who receives low-dose CT and autofluorescence bronchoscopy was ineffective and did not improve the efficiency of lung cancer screening.
Abstract: Background Low-dose computed tomography (LDCT) screening detects early-stage lung cancer and reduces mortality. We proposed a sequential approach targeted to a high-risk group as a potentially efficient screening strategy. Methods LungSEARCH was a national multicentre randomised trial. Current/ex-smokers with mild/moderate chronic obstructive pulmonary disease (COPD) were allocated (1:1) to have 5 years surveillance or not. Screened participants provided annual sputum samples for cytology and cytometry, and if abnormal were offered annual LDCT and autofluorescence bronchoscopy (AFB). Those with normal sputum provided annual samples. The primary end-point was the percentage of lung cancers diagnosed at stage I/II (nonsmall cell) or limited disease (small cell). Results 1568 participants were randomised during 2007–2011 from 10 UK centres. 85.2% of those screened provided an adequate baseline sputum sample. There were 42 lung cancers among 785 screened individuals and 36 lung cancers among 783 controls. 54.8% (23 out of 42) of screened individuals versus 45.2% (14 out of 31) of controls with known staging were diagnosed with early-stage disease (one-sided p=0.24). Relative risk was 1.21 (95% CI 0.75–1.95) or 0.82 (95% CI 0.52–1.31) for early-stage or advanced cancers, respectively. Overall sensitivity for sputum (in those randomised to surveillance) was low (40.5%) with a cumulative false-positive rate (FPR) of 32.8%. 55% of cancers had normal sputum results throughout. Among sputum-positive individuals who had AFB, sensitivity was 45.5% and cumulative FPR was 39.5%; the corresponding measures for those who had LDCT were 100% and 16.1%, respectively. Conclusions Our sequential strategy, using sputum cytology/cytometry to select high-risk individuals for AFB and LDCT, did not lead to a clear stage shift and did not improve the efficiency of lung cancer screening.

16 citations


Journal ArticleDOI
TL;DR: Rec retrospective response analysis of BAP1 expression in archival tumor biopsies taken from patients in the MS01 trial suggests B AP1 expression may modify response to vinorelbine in MPM, possibly due to prevention of mitotic microtubule formation.

11 citations



Journal ArticleDOI
TL;DR: A novel imaging marker that can help to differentiate between benign and malignant pulmonary nodules is described, however, attachment of a nodule to a pleural surface should not be used in isolation to distinguish IPLNs from lung malignancy.
Abstract: Purpose:A common diagnostic dilemma in the assessment of small pulmonary nodules on computed tomography (CT) is in distinguishing benign intrapulmonary lymph nodes (IPLNs) from small primary pulmonary malignancies. Several CT features have been described of IPLNs, including attachment to a pleural s

Journal ArticleDOI
TL;DR: This study uniquely examined agreement between observers of varying experience in the CT evaluation of chILD to inform whether the current status of CT imaging and knowledge can be diagnostic of specific chILDs.
Abstract: Making chILD diagnoses on CT is poorly reproducible, even amongst sub-specialists. CT might best improve diagnostic confidence in a multidisciplinary team setting when augmented with clinical, functional and haematological results. http://bit.ly/327jRCw.

Proceedings ArticleDOI
TL;DR: The Flex 19G EBUS-TBNA needle was safely used in this study as mentioned in this paper, however, the efficacy was similar to the 21G needle, and the Mair score did not differ between the two needles with a mean of 4.52 (+/- 2.28).
Abstract: Background: Endobronchial Ultrasound guidance allows lymph nodes in the mediastinum to be sampled under direct vision. The currently available EBUS-TBNA needles usually provide adequate samples for cytological assessment, but do not always contain sufficient material for the preparation of a cell block, thereby precluding histological assessment. Larger core tissue biopsy specimens are more likely to establish a diagnosis in suspected lung cancer patients. It can also improve the diagnostic yield of EBUS-TBNA for lymphoma and sarcoidosis. Objectives: This study that aims to determine the efficacy of the Flex 19G EBUS-TBNA (Olympus) compared to a standard 21G needle in patients with enlarged mediastinal and hilar lymph nodes. We evaluated the adequacy of the samples obtained with a modified Mair score. Methods: We completed a prospective randomised diagnostic clinical study of all cases performed at two study sites. Results: A total of 500 subjects underwent an EBUS procedure. 453 lesions with a mean lymph node size of 19.2mm (+/- SD 9.97) were sampled using Flex 19G & 480 lesions with a mean lymph node size of 17.8mm (+/- 8.15) were obtained using the standard needle. The Mair score did not differ between the two needles with a mean of 4.52 (+/- 2.28) for the Flex 19G & 4.40 (+/- 2.44) for the standard needle (p= 0.468). The complication rates were: 3.2% (19G) & 3.6% (21G). The sensitivity was 77% & specificity 100% with both needles. Conclusion: The Flex 19G EBUS-TBNA needle was safely used in this study. However, the efficacy was similar to the 21G needle.

Journal Article
TL;DR: This study investigated the reproducibility of the WHO classification among a large group of international pathologists with expertise in thymic pathology and by using whole slide imaging to facilitate rapid diagnostic turnover.


Journal ArticleDOI



Journal ArticleDOI
TL;DR: The patterns of lung disease associated with common CTDs, lung disease in pediatric CTD patients, and newly recognized conditions are described.
Abstract: Connective tissue diseases (CTDs) are a heterogeneous group of disorders, acquired or hereditary, involving an autoimmune-mediated inflammation of connective tissues in the whole body. Lung involvement is common with CTDs, and associated with significant morbidity and mortality. Each compartment of the lung may be affected, often simultaneously, depending on the type of CTD. In addition, the lung may show pathological changes related to treatment, such as infection, drug reaction, and neoplasia. A multidisciplinary approach to diagnose these patients is essential and incorporates radiological and clinical as well as pathological data. In this review we describe the patterns of lung disease associated with common CTDs, lung disease in pediatric CTD patients, and newly recognized conditions.

Proceedings ArticleDOI
01 Dec 2019-Thorax
TL;DR: Bronchoscopy is a safe and well tolerated procedure in patients with IPF supporting its use as part of the diagnostic assessment of interstitial lung disease and as a research tool.
Abstract: Introduction Retrospective and anecdotal evidence have been used to suggest that bronchoscopy in patients with IPF could be associated with an increased risk of acute exacerbations or acute respiratory deterioration. We aim to clarify the safety of BAL in patients with IPF in the prospectively recruited PROFILE cohort. Methods Patients diagnosed with IPF within the past 6 months were invited to participate in the PROFILE study. Patients were assessed at baseline, 1, 3, and 6 months and annually for 3 years. Fibreoptic bronchoscopy with BAL was performed at baseline in a subset of the Royal Brompton portion of the cohort. The procedure involved installation of 240 ml of warm saline in four aliquots into the right middle lobe followed by gentle aspiration by hand.Continuous variables are presented as means (±SD) and categorical variables as proportions. Differences between subject groups were evaluated with the use of the Mann–Whitney test for continuous variables and Fisher exact test for categorical variables. Time-to-event curves were calculated using the Kaplan–Meier method and compared with the use of the log-rank test. Results 302 patients were prospectively recruited, of whom 223 underwent bronchoscopy (74%). The 79 IPF patients who did not undergo BAL were older (71.6 vs. 67.8 years, P=0.001) and had a lower DLCo (39.2% vs. 47.6%, P=0.001) compared to subjects undergoing bronchoscopy. All subjects in the bronchoscopy cohort tolerated the procedure well. A leukocyte differential profile was determined in all cases and no immediate ( Conclusions Bronchoscopy is a safe and well tolerated procedure in patients with IPF supporting its use as part of the diagnostic assessment of interstitial lung disease and as a research tool.