Filters








41 Hits in 0.74 sec

Radiology in diffuse parenchymal lung disease and lung nodules

Nicola Sverzellati, Sujal Desai
<span title="2017-05-17">2017</span> <i title="European Respiratory Society (ERS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/i7rifwqqxnfyphfdjsv4kpe5lm" style="color: black;">European Respiratory Review</a> </i> &nbsp;
DESAI  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1183/16000617.0049-2017">doi:10.1183/16000617.0049-2017</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28515042">pmid:28515042</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6zob47jkbvhollknrdy5pqvgcu">fatcat:6zob47jkbvhollknrdy5pqvgcu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501230447/https://err.ersjournals.com/content/errev/26/144/170049.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f3/e7/f3e7841b8da4fb7fb145e1deb9fb8383f0927c94.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1183/16000617.0049-2017"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Anomalous origin of the right coronary artery from the pulmonary trunk

Maksim Zagura, Sa Tran, Sujal Desai
<span title="2016-04-07">2016</span> <i title="BMJ"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vj2dulzo3zey5h33y57oieqfce" style="color: black;">BMJ Case Reports</a> </i> &nbsp;
DESCRIPTION A 55-year-old woman presented to cardiology clinic with chest heaviness, which worsened with walking and deep inspiration. The sensation of chest heaviness had lasted for about a year. Cardiac and chest auscultation were unremarkable. The patient's cardiovascular risk factors included treated hypertension. There was no family history of coronary artery disease. The patient's ECG demonstrated sinus bradycardia with no ST-segment changes and normal QRS morphology. Transthoracic
more &raquo; ... diography showed normal left ventricular systolic function with mild left ventricular hypertrophy and no valvular abnormality. Furthermore, stress echocardiography was negative for ischaemia at 80% of maximum heart rate. Subsequently, the patient was referred to CT cardiac angiography. The patient's calcium score was 0. Contrast angiography demonstrated that the right coronary artery (RCA) had originated from the pulmonary trunk (figures 1 and 2A). The origin of the left coronary artery was normal (figure 2B). Tortuous collaterals from the LAD to the inferior wall of the heart were noted (figure 2B). In neither the left main stem, left anterior descending artery, circumflex artery nor RCA was luminal stenosis identified. Furthermore, exercise stress echocardiography was conducted, which was negative for ischaemia. The patient's management was discussed at a joint cardiology and cardiothoracic meeting and it was decided to continue conservative treatment. However, further follow-up was advised. Coronary artery anomalies are present in up to 1% of the population and are classified into anomalies of origin, anomalies of the course and anomalies of termination. 1 Ectopic origin of a coronary artery from the pulmonary trunk is part of a group of rare anomalies that carry a high risk of myocardial infarction and sudden death. Increased risk of Figure 1 Maximum intensity projection. The right coronary artery originates from the pulmonary trunk. RCA, right coronary artery. Figure 2 Three-dimensional volume rendering images. (A) The right coronary artery arises from the pulmonary trunk and passes to the right and inferiorly in the right atrioventricular groove. (B) There is a normal origin of the left coronary artery. Collateral vessels from LAD to inferior wall of the left ventricle are noted (white arrowheads). In neither the left nor right coronary artery, nor in their major branches, was luminal stenosis detected. LAD, left anterior descending artery; LCX, left circumflex artery; LM, left main stem; RCA, right coronary artery.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/bcr-2016-214876">doi:10.1136/bcr-2016-214876</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/27056940">pmid:27056940</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4840708/">pmcid:PMC4840708</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bfacd3vjanfc5k2mgnu7lwyhfa">fatcat:bfacd3vjanfc5k2mgnu7lwyhfa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200324011740/https://casereports.bmj.com/content/casereports/2016/bcr-2016-214876.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b2/c7/b2c7e3559cb54ba62ed98a28f043890cfac00291.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/bcr-2016-214876"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> bmj.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4840708" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Plain Film and HRCT Diagnosis of Interstitial Lung Disease [chapter]

Sujal R. Desai, Helmut Prosch, Jeffrey R. Galvin
<span title="">2019</span> <i title="Springer Singapore"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jyopc6cf5ze5vipjlm4aztcffi" style="color: black;">Communications in Computer and Information Science</a> </i> &nbsp;
Desai et al. Plain Film and HRCT Diagnosis of Interstitial Lung Disease  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11149-6_4">doi:10.1007/978-3-030-11149-6_4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bwdy7upo6jcehjfyrwmipntn6e">fatcat:bwdy7upo6jcehjfyrwmipntn6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190426210549/https://link.springer.com/content/pdf/10.1007%2F978-3-030-11149-6_4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/de/a3/dea3ba22e131164e972fd0469637c23f6b9da6ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11149-6_4"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

COVID-19 pneumonia and the pulmonary vasculature – a marriage made in hell

Peter M. George, Sujal R. Desai
<span title="2021-04-16">2021</span> <i title="European Respiratory Society (ERS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/atorwtwpevgcpi2i5crcljmqoe" style="color: black;">European Respiratory Journal</a> </i> &nbsp;
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1183/13993003.00811-2021">doi:10.1183/13993003.00811-2021</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33863736">pmid:33863736</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fclv5nujcvcrblwpmfbzbe4mne">fatcat:fclv5nujcvcrblwpmfbzbe4mne</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716114953/https://erj.ersjournals.com/content/erj/early/2021/03/25/13993003.00811-2021.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e0/94/e0941e041f9e79f489165ce2395c4ff465fd7836.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1183/13993003.00811-2021"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Is MC Dropout Bayesian? [article]

Loic Le Folgoc and Vasileios Baltatzis and Sujal Desai and Anand Devaraj and Sam Ellis and Octavio E. Martinez Manzanera and Arjun Nair and Huaqi Qiu and Julia Schnabel and Ben Glocker
<span title="2021-10-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall within the variational inference (VI) framework; and to propose a highly multimodal, faithful predictive posterior. We question the properties of MC Dropout for approximate inference, as in fact MC Dropout changes the Bayesian model; its predictive posterior
more &raquo; ... signs 0 probability to the true model on closed-form benchmarks; the multimodality of its predictive posterior is not a property of the true predictive posterior but a design artefact. To address the need for VI on arbitrary models, we share a generic VI engine within the pytorch framework. The code includes a carefully designed implementation of structured (diagonal plus low-rank) multivariate normal variational families, and mixtures thereof. It is intended as a go-to no-free-lunch approach, addressing shortcomings of mean-field VI with an adjustable trade-off between expressivity and computational complexity.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.04286v1">arXiv:2110.04286v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2bwdvjnfw5dzpduj6io4jdyo5q">fatcat:2bwdvjnfw5dzpduj6io4jdyo5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211014222418/https://arxiv.org/pdf/2110.04286v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/51/d0/51d0d91522685714f0df6e3472caf6b5cc5bb436.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.04286v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification [article]

Vasileios Baltatzis, Kyriaki-Margarita Bintsi, Loic Le Folgoc, Octavio E. Martinez Manzanera, Sam Ellis, Arjun Nair, Sujal Desai, Ben Glocker, Julia A. Schnabel
<span title="2021-08-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Using publicly available data to determine the performance of methodological contributions is important as it facilitates reproducibility and allows scrutiny of the published results. In lung nodule classification, for example, many works report results on the publicly available LIDC dataset. In theory, this should allow a direct comparison of the performance of proposed methods and assess the impact of individual contributions. When analyzing seven recent works, however, we find that each
more &raquo; ... ys a different data selection process, leading to largely varying total number of samples and ratios between benign and malignant cases. As each subset will have different characteristics with varying difficulty for classification, a direct comparison between the proposed methods is thus not always possible, nor fair. We study the particular effect of truthing when aggregating labels from multiple experts. We show that specific choices can have severe impact on the data distribution where it may be possible to achieve superior performance on one sample distribution but not on another. While we show that we can further improve on the state-of-the-art on one sample selection, we also find that on a more challenging sample selection, on the same database, the more advanced models underperform with respect to very simple baseline methods, highlighting that the selected data distribution may play an even more important role than the model architecture. This raises concerns about the validity of claimed methodological contributions. We believe the community should be aware of these pitfalls and make recommendations on how these can be avoided in future work.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05386v1">arXiv:2108.05386v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l7ahpm25jzg4zjoub2rhppwrxu">fatcat:l7ahpm25jzg4zjoub2rhppwrxu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210815133227/https://arxiv.org/pdf/2108.05386v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/8c/d08c074971ea204077d0ea73a19a4eb096ab209f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05386v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Lung Injury and Its Prognostic Significance in Acute Liver Failure

Vinod K. Audimoolam, Mark J. W. McPhail, Julia A. Wendon, Chris Willars, William Bernal, Sujal R. Desai, Georg Auzinger
<span title="">2014</span> <i title="Ovid Technologies (Wolters Kluwer Health)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/levvd3o2lvbxnhbgn7uvq37lqi" style="color: black;">Critical Care Medicine</a> </i> &nbsp;
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1097/01.ccm.0000435666.15070.d5">doi:10.1097/01.ccm.0000435666.15070.d5</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24152589">pmid:24152589</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i3czkzvmzjfutnnk4cjnswvvna">fatcat:i3czkzvmzjfutnnk4cjnswvvna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20131203132805/http://pdfs.journals.lww.com/ccmjournal/9000/00000/Lung_Injury_and_Its_Prognostic_Significance_in.97697.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/99/30/9930a100835a8f760b2a85991efbdad25f73833c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1097/01.ccm.0000435666.15070.d5"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Pulmonary function, CT and echocardiographic abnormalities in sickle cell disease

Alan Lunt, Sujal R Desai, Athol U Wells, David M Hansell, Sitali Mushemi, Narbeh Melikian, Ajay M Shah, Swee Lay Thein, Anne Greenough
<span title="2014-03-28">2014</span> <i title="BMJ"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dky225fdr5cuvo5ohu2cze6r5y" style="color: black;">Thorax</a> </i> &nbsp;
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/thoraxjnl-2013-204809">doi:10.1136/thoraxjnl-2013-204809</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24682519">pmid:24682519</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pgspz2alybeajb6bu6hgdw64xa">fatcat:pgspz2alybeajb6bu6hgdw64xa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501201015/https://thorax.bmj.com/content/thoraxjnl/69/8/746.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/49/34/4934ab619a9fa8936cdc25e6b3caadbb82dac3ac.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/thoraxjnl-2013-204809"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> bmj.org </button> </a>

Functional associations of pleuroparenchymal fibroelastosis and emphysema with hypersensitivity pneumonitis

Joseph Jacob, Arlette Odink, Anne Laure Brun, Claudio Macaluso, Angelo de Lauretis, Maria Kokosi, Anand Devaraj, Sujal Desai, Elisabetta Renzoni, Athol U. Wells
<span title="">2018</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e4m7pymct5h25ijp5abh6fazwm" style="color: black;">Respiratory Medicine</a> </i> &nbsp;
A B S T R A C T BACKGROUND: Pleuroparenchymal fibroelastosis (PPFE) has been described in hypersensitivity pneumonitis (HP) yet its functional implications are unclear. Combined pulmonary fibrosis and emphysema (CPFE) has occasionally been described in never-smokers with HP, but epidemiological data regarding its prevalence is sparse. CTs in a large HP cohort were therefore examined to identify the prevalence and effects of PPFE and emphysema. Methods: 233 HP patients had CT extents of
more &raquo; ... ial lung disease (ILD) and emphysema quantified to the nearest 5%. Lobar percentage pleural involvement of PPFE was quantified on a 4-point categorical scale: 0 = absent, 1 = affecting < 10%, 2 = affecting 10-33%, 3 = affecting > 33%. Marked PPFE reflected a total lung score of ≥3/18. Results were evaluated against FVC, DLco and mortality. RESULTS: Marked PPFE prevalence was 23% whilst 23% of never-smokers had emphysema. Following adjustment for patient age, gender, smoking status, and ILD and emphysema extents, marked PPFE independently linked to reduced baseline FVC (p = 0.0002) and DLco (p = 0.002) and when examined alongside the same covariates, independently linked to worsened survival (p = 0.01). CPFE in HP demonstrated a characteristic functional profile of artificial lung volume preservation and disproportionate DLco reduction. CPFE did not demonstrate a worsened outcome when compared to HP patients without emphysema beyond that explained by CT extents of ILD and emphysema. CONCLUSIONS: PPFE is not uncommon in HP, and is independently associated with impaired lung function and increased mortality. Emphysema was identified in 23% of HP never-smokers. CPFE appears not to link to a malignant microvascular phenotype as outcome is explained by ILD and emphysema extents.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.rmed.2018.03.031">doi:10.1016/j.rmed.2018.03.031</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29724400">pmid:29724400</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5948318/">pmcid:PMC5948318</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yxtcoummnbf2bfmvo75eydmueu">fatcat:yxtcoummnbf2bfmvo75eydmueu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190428222553/http://spiral.imperial.ac.uk/bitstream/10044/1/61403/2/Functional%20associations%20of%20pleuroparenchymal%20fibroelastosis%20and%20emphysema%20with%20hypersensitivity%20pneumonitis.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8c/6f/8c6f4cdff236bb2a8828ac691fe7145ae05da6ca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.rmed.2018.03.031"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948318" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data [article]

Vasileios Baltatzis, Loic Le Folgoc, Sam Ellis, Octavio E. Martinez Manzanera, Kyriaki-Margarita Bintsi, Arjun Nair, Sujal Desai, Ben Glocker, Julia A. Schnabel
<span title="2021-08-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely
more &raquo; ... tified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.04815v1">arXiv:2108.04815v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xuxwwxi325henj2rqs6vqlmlka">fatcat:xuxwwxi325henj2rqs6vqlmlka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210812192932/https://arxiv.org/pdf/2108.04815v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ea/bb/eabb31b6caca9cbdce012bcd0f835084613eb060.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.04815v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Pleuroparenchymal Fibroelastosis: A Review of Clinical, Radiological and Pathological Characteristics

Felix Chua, Sujal R Desai, Andrew G Nicholson, Anand Devaraj, Elisabetta Renzoni, Alexandra Rice, Athol U Wells
<span title="2019-08-19">2019</span> <i title="American Thoracic Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sqohg3ss6jbi5cjufyjsz6agle" style="color: black;">Annals of the American Thoracic Society</a> </i> &nbsp;
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
more &raquo; ... ost 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.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1513/annalsats.201902-181cme">doi:10.1513/annalsats.201902-181cme</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/31425665">pmid:31425665</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6945468/">pmcid:PMC6945468</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gt25iq2pnfhmrgfxrnzv2nkhxq">fatcat:gt25iq2pnfhmrgfxrnzv2nkhxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200513050740/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC6945468&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/54/2e/542e7b7d8b6ab1956ca3b8a2be8ba7012833a00d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1513/annalsats.201902-181cme"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6945468" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Respiratory follow-up of patients with COVID-19 pneumonia

Peter M George, Shaney L Barratt, Robin Condliffe, Sujal R Desai, Anand Devaraj, Ian Forrest, Michael A Gibbons, Nicholas Hart, R Gisli Jenkins, Danny F McAuley, Brijesh V Patel, Erica Thwaite (+1 others)
<span title="2020-08-24">2020</span> <i title="BMJ"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dky225fdr5cuvo5ohu2cze6r5y" style="color: black;">Thorax</a> </i> &nbsp;
The COVID-19 pandemic has led to an unprecedented surge in hospitalised patients with viral pneumonia. The most severely affected patients are older men, individuals of black and Asian minority ethnicity and those with comorbidities. COVID-19 is also associated with an increased risk of hypercoagulability and venous thromboembolism. The overwhelming majority of patients admitted to hospital have respiratory failure and while most are managed on general wards, a sizeable proportion require
more &raquo; ... ive care support. The long-term complications of COVID-19 pneumonia are starting to emerge but data from previous coronavirus outbreaks such as severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) suggest that some patients will experience long-term respiratory complications of the infection. With the pattern of thoracic imaging abnormalities and growing clinical experience, it is envisaged that interstitial lung disease and pulmonary vascular disease are likely to be the most important respiratory complications. There is a need for a unified pathway for the respiratory follow-up of patients with COVID-19 balancing the delivery of high-quality clinical care with stretched National Health Service (NHS) resources. In this guidance document, we provide a suggested structure for the respiratory follow-up of patients with clinicoradiological confirmation of COVID-19 pneumonia. We define two separate algorithms integrating disease severity, likelihood of long-term respiratory complications and functional capacity on discharge. To mitigate NHS pressures, virtual solutions have been embedded within the pathway as has safety netting of patients whose clinical trajectory deviates from the pathway. For all patients, we suggest a holistic package of care to address breathlessness, anxiety, oxygen requirement, palliative care and rehabilitation.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/thoraxjnl-2020-215314">doi:10.1136/thoraxjnl-2020-215314</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32839287">pmid:32839287</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7447111/">pmcid:PMC7447111</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rzraubsg4nak7l5b6vbgtxmvgm">fatcat:rzraubsg4nak7l5b6vbgtxmvgm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210113110753/https://thorax.bmj.com/content/thoraxjnl/75/11/1009.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8a/47/8a47e94239229a7c42c113736006cd7f877032b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1136/thoraxjnl-2020-215314"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> bmj.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7447111" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data [article]

Loic Le Folgoc and Vasileios Baltatzis and Amir Alansary and Sujal Desai and Anand Devaraj and Sam Ellis and Octavio E. Martinez Manzanera and Fahdi Kanavati and Arjun Nair and Julia Schnabel and Ben Glocker
<span title="2021-07-31">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for machine learning models. They cause significant gaps between model performance in the lab and in the real world. Our work is a solution to prevalence bias. Prevalence bias is the discrepancy between the prevalence of a pathology and its sampling rate in the
more &raquo; ... ning dataset, introduced upon collecting data or due to the practioner rebalancing the training batches. This paper lays the theoretical and computational framework for training models, and for prediction, in the presence of prevalence bias. Concretely a bias-corrected loss function, as well as bias-corrected predictive rules, are derived under the principles of Bayesian risk minimization. The loss exhibits a direct connection to the information gain. It offers a principled alternative to heuristic training losses and complements test-time procedures based on selecting an operating point from summary curves. It integrates seamlessly in the current paradigm of (deep) learning using stochastic backpropagation and naturally with Bayesian models.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00250v1">arXiv:2108.00250v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n6dplrl3kjg7rg5lrqhts7smki">fatcat:n6dplrl3kjg7rg5lrqhts7smki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210804085758/https://arxiv.org/pdf/2108.00250v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/34/68/3468859f8cebc4a63f76494acd8fdd9e38bbe8aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00250v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Aetiology, Risk Factors, and Biomarkers in Systemic Sclerosis with Interstitial Lung Disease

Dinesh Khanna, Donald P. Tashkin, Christopher P Denton, Elisabetta A. Renzoni, Sujal R Desai, John Varga
<span title="2019-12-16">2019</span> <i title="American Thoracic Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/k7oewgqstrfjbifylyk4zmr6h4" style="color: black;">American Journal of Respiratory and Critical Care Medicine</a> </i> &nbsp;
Systemic sclerosis (SSc) is a complex, multiorgan, autoimmune disease. Lung fibrosis occurs in ∼80% of patients with SSc; 25% to 30% develop progressive interstitial lung disease (ILD). The pathogenesis of fibrosis in SSc-associated ILD (SSc-ILD) involves cellular injury, activation/differentiation of mesenchymal cells, and morphological/biological changes in epithelial/endothelial cells. Risk factors for progressive SSc-ILD include older age, male sex, degree of lung involvement on baseline
more &raquo; ... h-resolution computed tomography imaging, reduced DlCO, and reduced FVC. SSc-ILD does not share the genetic risk architecture observed in idiopathic pulmonary fibrosis (IPF), with key risk factors yet to be identified. Presence of anti-Scl-70 antibodies and absence of anti-centromere antibodies indicate increased likelihood of progressive ILD. Elevated levels of serum Krebs von den Lungen-6 and C-reactive protein are both associated with SSc-ILD severity and predict SSc-ILD progression. A promising prognostic indicator is serum chemokine (C-C motif) ligand 18. SSc-ILD shares similarities with IPF, although clear differences exist. Histologically, a nonspecific interstitial pneumonia pattern is commonly observed in SSc-ILD, whereas IPF is defined by usual interstitial pneumonia. The course of SSc-ILD is variable, ranging from minor, stable disease to a progressive course, whereas all patients with IPF experience progression of disease. Although appropriately treated patients with SSc-ILD have better chances of stabilization and survival, a relentlessly progressive course, akin to IPF, is seen in a minority. Better understanding of cellular and molecular pathogenesis, genetic risk, and distinctive features of SSc-ILD and identification of robust prognostic biomarkers are needed for optimal disease management.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1164/rccm.201903-0563ci">doi:10.1164/rccm.201903-0563ci</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/31841044">pmid:31841044</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7068837/">pmcid:PMC7068837</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m6fsmoydfrcofcr4fyhray7biu">fatcat:m6fsmoydfrcofcr4fyhray7biu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715101022/https://escholarship.org/content/qt625910zx/qt625910zx.pdf?t=qaezeb" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/da/a8/daa88f6a07362801bd32e433a4eff49be2788c72.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1164/rccm.201903-0563ci"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7068837" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

SAPSAM - Sparsely Annotated Pathological Sign Activation Maps - A novel approach to train Convolutional Neural Networks on lung CT scans using binary labels only [article]

Mario Zusag, Sujal Desai, Marcello Di Paolo, Thomas Semple, Anand Shah, Elsa Angelini
<span title="2019-02-06">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Chronic Pulmonary Aspergillosis (CPA) is a complex lung disease caused by infection with Aspergillus. Computed tomography (CT) images are frequently requested in patients with suspected and established disease, but the radiological signs on CT are difficult to quantify making accurate follow-up challenging. We propose a novel method to train Convolutional Neural Networks using only regional labels on the presence of pathological signs, to not only detect CPA, but also spatially localize
more &raquo; ... ical signs. We use average intensity projections within different ranges of Hounsfield-unit (HU) values, transforming input 3D CT scans into 2D RGB-like images. CNN architectures are trained for hierarchical tasks, leading to precise activation maps of pathological patterns. Results on a cohort of 352 subjects demonstrate high classification accuracy, localization precision and predictive power of 2 year survival. Such tool opens the way to CPA patient stratification and quantitative follow-up of CPA pathological signs, for patients under drug therapy.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.02629v1">arXiv:1902.02629v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5iaz5bh47nd2tjy64c7euhxsdi">fatcat:5iaz5bh47nd2tjy64c7euhxsdi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191021190304/https://arxiv.org/pdf/1902.02629v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/35/13/35134babb619384659aa5a88a860933498673941.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.02629v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 41 results