Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.oa4853

Federico Felder, Yang Nan, Guang Yang, John Mackintosh, Lucio Calandriello, Mario Silva, Ian Glaspole, Nicole Goh, Wendy Cooper, Christopher Grainge, Peter Hopkins, Yuben Moodley, Navaratnam Vidya, Paul Reynolds, Athol Wells, Tamera Corte, Simon Walsh

{"title":"Deep learning-based quantification of traction bronchiectasis severity for predicting outcome in idiopathic pulmonary fibrosis","authors":"Federico Felder, Yang Nan, Guang Yang, John Mackintosh, Lucio Calandriello, Mario Silva, Ian Glaspole, Nicole Goh, Wendy Cooper, Christopher Grainge, Peter Hopkins, Yuben Moodley, Navaratnam Vidya, Paul Reynolds, Athol Wells, Tamera Corte, Simon Walsh","doi":"10.1183/13993003.congress-2023.oa4853","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.oa4853","url":null,"abstract":"Aim: We investigated the prognostic utility a novel deep learning algorithm for quantifying severity of traction bronchiectasis in patients with idiopathic pulmonary fibrosis (IPF) enrolled in the Australian IPF Registry (AIPFR). Methods: Visual evaluation of HRCTs from the AIPFR was performed by 2 expert thoracic radiologists evaluated. Total airway volume (TAV) was quantified using a novel 3D U-Net-based deep learning algorithm. SOFIA UIP probability scores were obtained using a previously reported deep learning algorithm, trained in the identification of UIP features. Results: Total airway volume was an independent predictor of mortality when controlling for visual-based evaluation of total fibrosis extent (HR 1.96, p<0.0001), %Predicted FVC (HR 2.15, p<0.0001) or the CPI (n=217, HR 1.52, p=0.02. On bivariable analysis both TAV (HR 2.13, p<0.0001) and SOFIA-UIP probability (HR 1.30, p<0.0001) independently predicted mortality. On bivariable analysis with total fibrosis extent, TAV independently predicted mortality in UIP-like disease (HR 1.50, p=0.03) and was the only predictor of mortality (HR 5.33, p<0.0001) in those meeting indeterminate/alternative diagnosis criteria. An increase in TAV of 1% of total lung volume was associated with a 3-fold increased likelihood of developing progressive disease (OR 3.04 p=0.009) when controlling for total fibrosis extent. Conclusion: In IPF, automated quantification of TAV predicts mortality independently of total fibrosis extent on HRCT and can be used to identify patients at risk of progression at 12 months. In collaboration with the AIPFR and The Open Source Imaging Consortium","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136193982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A deep learning algorithm for predicting disease progression in idiopathic pulmonary fibrosis 用于预测特发性肺纤维化疾病进展的深度学习算法

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.oa4852

Yingying Fang, Federico Felder, Guang Yang, John Mackintosh, Lucio Calandriello, Mario Silva, Wendy Cooper, Ian Glaspole, Nicole Goh, Christopher Grainge, Peter Hopkins, Yuben Moodley, Navaratnam Vidya, Paul Reynolds, Athol Wells, Tamera Corte, Simon Walsh

{"title":"A deep learning algorithm for predicting disease progression in idiopathic pulmonary fibrosis","authors":"Yingying Fang, Federico Felder, Guang Yang, John Mackintosh, Lucio Calandriello, Mario Silva, Wendy Cooper, Ian Glaspole, Nicole Goh, Christopher Grainge, Peter Hopkins, Yuben Moodley, Navaratnam Vidya, Paul Reynolds, Athol Wells, Tamera Corte, Simon Walsh","doi":"10.1183/13993003.congress-2023.oa4852","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.oa4852","url":null,"abstract":"Aim: We investigated the prognostic utility a deep learning algorithm for predicting risk of progression in patients with idiopathic pulmonary fibrosis (IPF). Progression was defined as an FVC decline of 10% at 12 months, death, or transplantation. Methods: A deep learning algorithm (DL_IPF) was trained on HRCTs from The Open-Source Imaging Consortium (OSIC) and tested in Australian IPF Registry (AIPFR). A visual-based total fibrosis score was obtained for AIPF HRCTs. SOFIA UIP probability scores were obtained using a previously reported deep learning algorithm, trained in the identification of UIP features. The prognostic utility of DL_IPF (yielding a progression probability) was evaluated against conventional measures of disease severity and SOFIA-based UIP probability scores. Results: DL_IPF analysis independently predicted mortality, controlling for visual-based total fibrosis extent (n=501, HR 1.03, p<0.0001). Progression probability scores were converted to PG_PIOPED scores using PIOPED diagnostic probability thresholds. PG_PIOPED (HR 2.74, p<0.0001) and SOFIA PIOPED scores (HR 1.35, p<0.0001) independently predicted mortality. PG_PIOPED scores predicted mortality in patients with an “indeterminate” HRCT pattern (n=82, HR 8.06, p<0.0001) and patients who underwent surgical lung biopsy (SLB) (n=82, HR 3.00, p<0.0001). An increase in PFF_PIOPED score by one category, was associated with a 3.2-fold increased likelihood of developing progressive disease (OR 3.21 p<0.0001) when controlling for total fibrosis extent. Conclusion: Deep learning may be used to identify suspected IPF patients at risk of progression at 12 months","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136194092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Use of dynamic chest radiographic measurements to estimate total lung capacity in patients with respiratory disease 使用动态胸片测量估计呼吸系统疾病患者的总肺活量

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa2291

Fred Fyles, Ryan Robinson, Thomas Fitzmaurice, Rachel Burton, Amy Nuttall, Ram Bedi, Hassan Burhan

{"title":"Use of dynamic chest radiographic measurements to estimate total lung capacity in patients with respiratory disease","authors":"Fred Fyles, Ryan Robinson, Thomas Fitzmaurice, Rachel Burton, Amy Nuttall, Ram Bedi, Hassan Burhan","doi":"10.1183/13993003.congress-2023.pa2291","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa2291","url":null,"abstract":"Introduction: Pulmonary Function Tests (PFTs) are key in diagnosing numerous conditions, but require experienced operators and are expensive to obtain. Studies demonstrate correlation between projected lung area (PLA) at maximal inspiration measured using Dynamic Chest Radiography (DCR) and spirometric measurements, e.g. total lung capacity (TLC) (Hino et al. EJR Open. 2020;7:100263). DCR is an imaging modality in which sequential radiographs are used to form a moving image, providing functional/structural information. We describe use of DCR to estimate TLC in respiratory patients. Methods: 42 patients with underlying respiratory conditions (asthma n=12, COPD n=10, recent history CoVid-19 n=12, ILD n=9) underwent DCR during which they were instructed to take a deep breath in and out. PLA at maximal inspiration was measured by automated proprietary software, and then used to estimate TLC (DCR-TLC). DCR-TLC was compared to TLC measured with whole body plethysmography (WBP-TLC) and Pearson’s correlation coefficient derived. Results: Results are outlined in Table 1. Correlation between DCR-TLC and WBP-TLC was 0.86, and >0.8 across all subgroups. Conclusion: DCR-TLC had a good degree of correlation with WBP-TLC across a range of different respiratory conditions, suggesting potential future use as a clinical surrogate. Further research is needed to correlate PFT results with DCR-derived measurements.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"11 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136200685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Correlation between ventilation heterogeneity and virtual scintigraphy through Functional Respiratory Imaging (FRI) 功能呼吸成像(FRI)与通气异质性的相关性研究

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa2277

Hosein Sadafi, Maarten Lanclus, navid Monshi Tousi, Stijn Bonte, Jan De Backer

引用次数: 0

CT imaging differences between different Covid-19 strains 不同新型冠状病毒株CT表现差异

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa3526

Aleksandar Ivkovic, Tamara Milosavljevic, Ivana Svilarov, Stevan Ivkovic, Dusan Ivkovic

{"title":"CT imaging differences between different Covid-19 strains","authors":"Aleksandar Ivkovic, Tamara Milosavljevic, Ivana Svilarov, Stevan Ivkovic, Dusan Ivkovic","doi":"10.1183/13993003.congress-2023.pa3526","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa3526","url":null,"abstract":"Purpose: To explore the CT findings and pneumonia progression pattern of the Alpha, Delta, Omicron variants and subtypes of SARS-CoV-2 by comparing them with the pre-existing wild type. Method: In this retrospective comparative study, a total of 15874 patients with COVID-19 were included: 1281 patients with wild type (748 men, 52.6 years), 7945 with Alpha variant (4972 men, 46.2), 4233 with Delta variant (2548 men) and 2415 with Omicron and subtypes (1301 man, 44.2). Chest CT evaluation included opacities and repairing changes as well as lesion distribution and laterality. Chest CT severity score was also calculated. These parameters were statistically compared across the variants. Results: Ground glass opacity (GGO), crazy paving, subpleural fibrosis with consolidation and repairing changes were more frequent in the order of Delta variant, Alpha variant, Omicron variant, and wild type throughout the disease course. Delta variant showed GGO and crazy paving with consolidation more noticeable than did the others on days 1–8). Wild strain had more unclear CT presentation. Alfa strain was the first strain with sharp CT presentation. Delta strain was with fast development of subpleural fibrosis. Omicron strain had smaller areas of CGO. Total lung CT severity scores of Delta variant were higher than those of wild type on days 1–14 and that of Alpha variant on days 1–4. Alpha strain had higher severity score on days 15 to 21 with more complications. Omicron strain severity were mostly in range 0-5 and 18-23 with small percent in range 6-17. Conclusions: There was difference in the CT findings and severity scores between all different types and subtypes.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136201747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spirometry and chest HRCT abnormalities in symptomatic and asymptomatic patients with inflammatory bowel disease 有症状和无症状的炎症性肠病患者的肺量测定和胸部HRCT异常

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa4013

Asmaa Mohammed Elshazly, Rasha Dabees, Mahmoud Reda, Fahmy Hablas, Ahmed Samir, Nashwa Abdel-Wahab

{"title":"Spirometry and chest HRCT abnormalities in symptomatic and asymptomatic patients with inflammatory bowel disease","authors":"Asmaa Mohammed Elshazly, Rasha Dabees, Mahmoud Reda, Fahmy Hablas, Ahmed Samir, Nashwa Abdel-Wahab","doi":"10.1183/13993003.congress-2023.pa4013","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa4013","url":null,"abstract":"Background: Ulcerative colitis (UC) and Crohn’s disease (CD) are the major subtypes of inflammatory bowel disease (IBD). Lung involvement is an IBD related extra-intestinal manifestations which is poorly studied. Objectives: We aimed to study radiological abnormalities and spirometric findings in symptomatic and asymptomatic patients recently diagnosed with IBD.  Methods: A prospective cross-sectional study enrolled 71 patients (39 (55%) patients with CD and 32 (45%) patients with UC) presented to Main Alexandria University Hospital between 2019 and 2022. Patients were disease-naïve diagnosed by endoscopy. Those with bronco-pulmonary diseases prior to the diagnosis of IBD, cardiac, renal or hepatic diseases were excluded. All patients underwent clinical evaluation, spirometry, and HRCT scan of the chest. Results: The median age of the studied population was 32 (25–37) years being slightly more females (53.5%). Of total population 12 patients (16.9%) were asymptomatic and 59 patients (83.1%) were symptomatic. FEF25-75 and PEFR were significantly lower in the asymptomatic patients (p<0.001 and 0.006 respectively). Further, 7 patients (58.3%) of the asymptomatic group had abnormal HRCT findings where ground glass opacity and bronchiectasis were the frequently reported abnormality without statistically significant difference compared to symptomatic group (p>0.05). Conclusion: Lung involvement in IBD occurs even in asymptomatic population that warrant lung screening with simple tools as spirometry and HRCT scan which can help in early diagnosis and proper management.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136259461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thromboembolic complications during SARS-CoV-2 infection in the elderly 老年人SARS-CoV-2感染期间的血栓栓塞并发症

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa3537

Hamida Kwas, Sabrine Majdoub Fehri

{"title":"Thromboembolic complications during SARS-CoV-2 infection in the elderly","authors":"Hamida Kwas, Sabrine Majdoub Fehri","doi":"10.1183/13993003.congress-2023.pa3537","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa3537","url":null,"abstract":"Introduction: Classified as a pandemic by the WHO on March 11, 2020, infection with COVID-19 represents a real medical challenge. It is considered as a systemic disease with a pro-thrombotic state, at the origin of thromboembolic events (TEE). The aim of the present study is to determine the clinical and therapeutic particularities and evolution of TEE during infection by SARS-CoV-2 in elderly subjects. Methods: This was a retrospective and descriptive study including 150 patients, aged 65 and over, hospitalized in the COVID-19 unit during the period from January to March 2021. Results: Thirty four patients developed thromboembolic complications. The average age of our patients was 77.94 ± 7.198 years. The sex ratio (M/F) was 2.4. Comorbidities were noted in 82.4% of patients, dominated by arterial hypertension (61.8%) and diabetes (38.2%). The symptomatology was dominated by cough and acute dyspnea. Signs of acute respiratory failure were noted in 85.3% of cases. Venous thromboembolic complications were observed in 85.3% of patients represented by pulmonary embolism in all cases. Arterial thromboembolic complications were noted in 14.7% of patients represented by thoracic (60%) and abdominal (40%) thromboembolic events. The use of mechanical ventilation was necessary in 8.8% of patients. Low molecular weight heparin was prescribed in 94.1% of patients and unfractionated heparin in 5.9% of patients with chronic renal failure. Death occurred in 70.6% of patients. Conclusion: SARS-CoV-2 infection is a polymorphic disease and responsible for several TEE. In the absence of effective treatment, prevention of thrombosis is necessary to improve the prognosis.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136260806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of benralizumab on small airway dysfunction using functional respiratory imaging in patients with severe eosinophilic asthma 贝纳利珠单抗对严重嗜酸性哮喘患者小气道功能障碍的影响

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa2289

Lennart Conemans, Mieke Crutsen, Wendel Dierckx, Sami Simons, Martijn Spruit, Bita Hajian

{"title":"Effect of benralizumab on small airway dysfunction using functional respiratory imaging in patients with severe eosinophilic asthma","authors":"Lennart Conemans, Mieke Crutsen, Wendel Dierckx, Sami Simons, Martijn Spruit, Bita Hajian","doi":"10.1183/13993003.congress-2023.pa2289","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa2289","url":null,"abstract":"Introduction: Severe eosinophilic asthma (SEA) is known to respond favorably to benralizumab. Small airway dysfunction (SAD) is present across GINA stages and correlates with asthma severity. To date, effects of benralizumab on SAD in patients with SEA are unknown. This study aimed to detect changes in SAD after initiation of benralizumab in patients with SEA using Functional Respiratory Imaging (FRI). Methods: An open-label, single-arm trial in adult patients with SEA eligible for treatment with benralizumab was designed. Spirometry guided HRCT scans at FRC and TLC were evaluated before and after benralizumab and analyzed using computational fluid dynamics (FLUIDDA NV). Primary outcome was FRI based SAD, defined as change in specific image-based airway volume (SIVAW). Wilcoxon signed ranks test was used. Preliminary data are reported. Results: 18 patients were included, 6 of which completed the study to date. SIVAW (mL/L) at FRC increased from baseline (T0; 5.54; 4.73-7.09; median, IQR) to week 4 (6.34; 5,86-7.21 p=0.046) and week 12 (6.66; 4.89-7.94 p=0.028). SIVAW at TLC increased (T0 8.11; 6.75-8.65) to week 4 (8.39, 6.86-8.94 p=0.028). Specific image-based airway resistance (SIRAW in kPa*s) at T0 at FRC (1.26; 0.58-9.22) and TLC (0.64; 0.40-0.78) decreased at week 4 (FRC 0.54; 0.41-1.36, TLC 0.46; 0.34-0.58 p=0.028) and 12 (FRC 0.42; 0.19-4.25, TLC 0.46; 0.34-0.58 p=0.028). ACQ-6 (3.17 to 2.33) and SGRQ (67 to 55) improved (p<0.05) from T0 to week 12 as did FEV1 (1.40L (58%) to 1.72L (74%) p=0.028). Conclusion: FRI is feasible in patients with SEA and can detect improvements in SAD as early as 4 weeks after treatment initiation with benralizumab.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136194397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Imaging of human airways by endoscope-compatible dynamic microscopic optical coherence tomography 内窥镜兼容动态显微光学相干层析成像的人体气道成像

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa2290

Cornelia Holzhausen, Hinnerk Schulz-Hildebrandt, Martin Ahrens, Klaus Rabe, Heike Biller, Mustafa Abdo, David Ellebrecht, Sönke Von Weihe, Christoph Fraune, Stefan Steurer, Gereon Hüttmann, Peter König, Mario Pieper

{"title":"Imaging of human airways by endoscope-compatible dynamic microscopic optical coherence tomography","authors":"Cornelia Holzhausen, Hinnerk Schulz-Hildebrandt, Martin Ahrens, Klaus Rabe, Heike Biller, Mustafa Abdo, David Ellebrecht, Sönke Von Weihe, Christoph Fraune, Stefan Steurer, Gereon Hüttmann, Peter König, Mario Pieper","doi":"10.1183/13993003.congress-2023.pa2290","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa2290","url":null,"abstract":"With the improvement of chest CT and the implementation of lung cancer screening, there will be an increasing demand for biopsy work-up of detected lung lesions. Many new navigation devices with or without endobronchial ultrasound have been developed to facilitate localization and subsequent sampling by bronchoscopy. Nevertheless, in several trials the diagnostic yield remained limited. Subsurface real-time imaging at cellular level is needed. We hypothesize that optical coherence tomography (OCT), which is based on the backscattering of light, can fulfil those demands. OCT has a high penetration depth compared to other optical methods and reaches microscopic resolution (mOCT). It allows direct capture of cross-sectional images without contrast agent. By analysing the dynamic changes of cells a high cell-specific contrast is achieved (dmOCT). The usability of dmOCT for diagnostics was tested with an endoscope-compatible setup on freshly excised human lung tissue. The setup provided high-resolution images, enabled us to identify the organ-specific architecture of the airways, to picture epithelium, connective tissue, vessels, smooth muscles, bronchial glands and to discriminate cells, such as ciliated epithelial cells, goblet cells, and immune cells. In samples of squamous cell carcinomas we could capture the altered tissue architecture and growth pattern of the neoplasia comprised of irregular nests set in a desmoplastic stroma. Furthermore, inflammation was identified by the presence of sub- and intraepithelial immune cells. The dmOCT could complement bronchoscopy and, with further advancements, such as automatic focus shift or motion correction, might reduce the need for biopsies.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136194521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Differentiating diffuse cystic lung disease and emphysema cases from normal using Artificial Intelligence 应用人工智能鉴别弥漫性囊性肺疾病与肺气肿

Imaging Pub Date : 2023-09-09 DOI: 10.1183/13993003.congress-2023.pa2292

Katie Noonan, Ronan Hearne, Brian Gaffney, Brian Sheehy, Niall Mcveigh, Yasuhito Sekimoto, Ali Ataya, Nishant Gupta, Francis Mccormack, Raphaël Borie, Francesco Bonella, David Murphy, Kathleen Curran, Cormac Mccarthy

{"title":"Differentiating diffuse cystic lung disease and emphysema cases from normal using Artificial Intelligence","authors":"Katie Noonan, Ronan Hearne, Brian Gaffney, Brian Sheehy, Niall Mcveigh, Yasuhito Sekimoto, Ali Ataya, Nishant Gupta, Francis Mccormack, Raphaël Borie, Francesco Bonella, David Murphy, Kathleen Curran, Cormac Mccarthy","doi":"10.1183/13993003.congress-2023.pa2292","DOIUrl":"https://doi.org/10.1183/13993003.congress-2023.pa2292","url":null,"abstract":"Introduction: Diffuse Cystic Lung Disease (DCLD) share a common phenotype of multiple thin-walled pulmonary cysts. Their relative scarcity and visual similarity to more prevalent diseases like emphysema, gives rise to frequent misdiagnosis, leading to dramatically worse clinical outcomes and a higher burden on the healthcare system. Aims and Objectives: To stratify DCLD and Emphysema from those with no disease (Normal) using Artificial Intelligence (AI) techniques applied to CT images. Methods: Deep learning models to stratify DCLD and Emphysema patients from normal patients were employed in two studies. The first study isolated the lungs and trained three CNN classifiers (DenseNet201, ResNet50, and Xception) for comparison. The second study trained a ResNet50 model with a Convolutional Block Attention Module to assess potential benefits of using attention components. Explainability was explored using GradCam. Results: The first study used 118 DCLD and control cases, and the second study used 20 DCLD, emphysema and control cases. These datasets yielded 17,460 and 5,312 CT slices respectively. Train and test datasets were created with a 90/10 and 75/25 split respectively. Validation sets were derived from training data during training. Care was taken to ensure that there was no patient overlap between training, validation and testing datasets. AUCs above 0.97 and 0.921, and Average PR above 0.95 and 0.93 were observed across the two studies respectively. Conclusions: The high specificity and AUC scores achieved by the models supports its use case as a decision support tool for radiologists in the analysis of Emphysema and DCLD cases.","PeriodicalId":34850,"journal":{"name":"Imaging","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136195381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Imaging最新文献