Andrea Alessandro Esposito1, Stefania Zannoni2, Laura Castoldi3, Caterina Giannitto4, Emanuele Avola2, Elena Casiraghi5, Onofrio Catalano6, Gianpaolo Carrafiello7. 1. Department of Radiology, Foundation IRCCS Ca' Granda Ospedale Maggiore Policlinico, Via Sforza 35, 20122, Milan, Italy. andrea.esposito@policlinico.mi.it. 2. Post-Graduate School in Radiodiagnostics, Università Degli Studi Di Milano, Via Festa del Perdono 7, 20122, Milan, Italy. 3. Department of Surgical Emergency, Foundation IRCCS Ca' Granda Ospedale Maggiore Policlinico, Via Sforza 35, 20122, Milan, Italy. 4. Department of Radiology, Istituto Clinico Humanitas, Via Manzoni 56, 20089, Rozzano, MI, Italy. 5. Department of Computer Science, University of Milan, Via Celoria 18, 20133, Milan, Italy. 6. Department of Radiology, Massachusetts General Hospital, 55 Fruit St, Boston, MA, 02114, USA. 7. Department of Radiology, Foundation IRCCS Ca' Granda Ospedale Maggiore Policlinico, Via Sforza 35, 20122, Milan, Italy.
Abstract
PURPOSE: To assess the incidence of erroneous diagnosis of pneumatosis (pseudo-pneumatosis) in patients who underwent an emergency abdominal CT and to verify the performance of imaging features, supported by artificial intelligence (AI) techniques, to reduce this misinterpretation. METHODS: We selected 71 radiological reports where the presence of pneumatosis was considered definitive or suspected. Surgical findings, clinical outcomes, and reevaluation of the CT scans were used to assess the correct diagnosis of pneumatosis. We identified four imaging signs from literature, to differentiate pneumatosis from pseudo-pneumatosis: gas location, dissecting gas in the bowel wall, a circumferential gas pattern, and intramural gas beyond a gas-fluid/faecal level. Two radiologists reevaluated in consensus all the CT scans, assessing the four above-mentioned variables. Variable discriminative importance was assessed using the Fisher exact test. Accurate and statistically significant variables (p-value < 0.05, accuracy > 75%) were pooled using boosted Random Forests (RFs) executed using a Leave-One-Out cross-validation (LOO cv) strategy to obtain unbiased estimates of individual variable importance by permutation analysis. After the LOO cv, the comparison of the variable importance distribution was validated by one-sided Wilcoxon test. RESULTS: Twenty-seven patients proved to have pseudo-pneumatosis (error: 38%). The most significant features to diagnose pneumatosis were presence of dissecting gas in the bowel wall (accuracy: 94%), presence of intramural gas beyond a gas-fluid/faecal level (accuracy: 86%), and a circumferential gas pattern (accuracy: 78%). CONCLUSION: The incidence of pseudo-pneumatosis can be high. The use of a checklist which includes three imaging signs can be useful to reduce this overestimation.
PURPOSE: To assess the incidence of erroneous diagnosis of pneumatosis (pseudo-pneumatosis) in patients who underwent an emergency abdominal CT and to verify the performance of imaging features, supported by artificial intelligence (AI) techniques, to reduce this misinterpretation. METHODS: We selected 71 radiological reports where the presence of pneumatosis was considered definitive or suspected. Surgical findings, clinical outcomes, and reevaluation of the CT scans were used to assess the correct diagnosis of pneumatosis. We identified four imaging signs from literature, to differentiate pneumatosis from pseudo-pneumatosis: gas location, dissecting gas in the bowel wall, a circumferential gas pattern, and intramural gas beyond a gas-fluid/faecal level. Two radiologists reevaluated in consensus all the CT scans, assessing the four above-mentioned variables. Variable discriminative importance was assessed using the Fisher exact test. Accurate and statistically significant variables (p-value < 0.05, accuracy > 75%) were pooled using boosted Random Forests (RFs) executed using a Leave-One-Out cross-validation (LOO cv) strategy to obtain unbiased estimates of individual variable importance by permutation analysis. After the LOO cv, the comparison of the variable importance distribution was validated by one-sided Wilcoxon test. RESULTS: Twenty-seven patients proved to have pseudo-pneumatosis (error: 38%). The most significant features to diagnose pneumatosis were presence of dissecting gas in the bowel wall (accuracy: 94%), presence of intramural gas beyond a gas-fluid/faecal level (accuracy: 86%), and a circumferential gas pattern (accuracy: 78%). CONCLUSION: The incidence of pseudo-pneumatosis can be high. The use of a checklist which includes three imaging signs can be useful to reduce this overestimation.
Authors: Ismael Mora-Guzmán; José Luis Muñoz de Nova; Lourdes Del Campo Del Val; Elena Martín-Pérez Journal: Dig Liver Dis Date: 2017-04-03 Impact factor: 4.088
Authors: Jack Wittenberg; Mukesh G Harisinghani; Kartik Jhaveri; Jose Varghese; Peter R Mueller Journal: Radiographics Date: 2002 Sep-Oct Impact factor: 5.333
Authors: Mary T Hawn; Cheri L Canon; Mark E Lockhart; Quintin H Gonzalez; Gregg Shore; Anthony Bondora; Selwyn M Vickers Journal: Am Surg Date: 2004-01 Impact factor: 0.688