1
|
Dreizin D, Nixon B, Hu J, Albert B, Yan C, Yang G, Chen H, Liang Y, Kim N, Jeudy J, Li G, Smith EB, Unberath M. A pilot study of deep learning-based CT volumetry for traumatic hemothorax. Emerg Radiol 2022; 29:995-1002. [PMID: 35971025 DOI: 10.1007/s10140-022-02087-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Accepted: 08/08/2022] [Indexed: 12/17/2022]
Abstract
PURPOSE We employ nnU-Net, a state-of-the-art self-configuring deep learning-based semantic segmentation method for quantitative visualization of hemothorax (HTX) in trauma patients, and assess performance using a combination of overlap and volume-based metrics. The accuracy of hemothorax volumes for predicting a composite of hemorrhage-related outcomes - massive transfusion (MT) and in-hospital mortality (IHM) not related to traumatic brain injury - is assessed and compared to subjective expert consensus grading by an experienced chest and emergency radiologist. MATERIALS AND METHODS The study included manually labeled admission chest CTs from 77 consecutive adult patients with non-negligible (≥ 50 mL) traumatic HTX between 2016 and 2018 from one trauma center. DL results of ensembled nnU-Net were determined from fivefold cross-validation and compared to individual 2D, 3D, and cascaded 3D nnU-Net results using the Dice similarity coefficient (DSC) and volume similarity index. Pearson's r, intraclass correlation coefficient (ICC), and mean bias were also determined for the best performing model. Manual and automated hemothorax volumes and subjective hemothorax volume grades were analyzed as predictors of MT and IHM using AUC comparison. Volume cut-offs yielding sensitivity or specificity ≥ 90% were determined from ROC analysis. RESULTS Ensembled nnU-Net achieved a mean DSC of 0.75 (SD: ± 0.12), and mean volume similarity of 0.91 (SD: ± 0.10), Pearson r of 0.93, and ICC of 0.92. Mean overmeasurement bias was only 1.7 mL despite a range of manual HTX volumes from 35 to 1503 mL (median: 178 mL). AUC of automated volumes for the composite outcome was 0.74 (95%CI: 0.58-0.91), compared to 0.76 (95%CI: 0.58-0.93) for manual volumes, and 0.76 (95%CI: 0.62-0.90) for consensus expert grading (p = 0.93). Automated volume cut-offs of 77 mL and 334 mL predicted the outcome with 93% sensitivity and 90% specificity respectively. CONCLUSION Automated HTX volumetry had high method validity, yielded interpretable visual results, and had similar performance for the hemorrhage-related outcomes assessed compared to manual volumes and expert consensus grading. The results suggest promising avenues for automated HTX volumetry in research and clinical care.
Collapse
Affiliation(s)
- David Dreizin
- Department of Diagnostic Radiology and Nuclear Medicine, R Adams Cowley Shock Trauma Center, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD, 21201, USA.
| | - Bryan Nixon
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Jiazhen Hu
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Benjamin Albert
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Chang Yan
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Gary Yang
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Haomin Chen
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Yuanyuan Liang
- Epidemiology & Public Health, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Nahye Kim
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Jean Jeudy
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Guang Li
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Elana B Smith
- Department of Diagnostic Radiology and Nuclear Medicine, R Adams Cowley Shock Trauma Center, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD, 21201, USA
| | - Mathias Unberath
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| |
Collapse
|
2
|
Dreizin D, Yu T, Motley K, Li G, Morrison JJ, Liang Y. Blunt splenic injury: Assessment of follow-up CT utility using quantitative volumetry. FRONTIERS IN RADIOLOGY 2022; 2. [PMID: 36120383 PMCID: PMC9479763 DOI: 10.3389/fradi.2022.941863] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Purpose: Trials of non-operative management (NOM) have become the standard of care for blunt splenic injury (BSI) in hemodynamically stable patients. However, there is a lack of consensus regarding the utility of follow-up CT exams and relevant CT features. The purpose of this study is to determine imaging predictors of splenectomy on follow-up CT using quantitative volumetric measurements. Methods: Adult patients who underwent a trial of non-operative management (NOM) with follow-up CT performed for BSI between 2017 and 2019 were included (n = 51). Six patients (12% of cohort) underwent splenectomy; 45 underwent successful splenic salvage. Voxelwise measurements of splenic laceration, hemoperitoneum, and subcapsular hematoma were derived from portal venous phase images of admission and follow-up scans using 3D slicer. Presence/absence of pseudoaneurysm on admission and follow-up CT was assessed using arterial phase images. Multivariable logistic regression was used to determine independent predictors of decision to perform splenectomy. Results: Factors significantly associated with splenectomy in bivariate analysis incorporated in multivariate logistic regression included final hemoperitoneum volume (p = 0.003), final subcapsular hematoma volume (p = 0.001), change in subcapsular hematoma volume between scans (p = 0.09) and new/persistent pseudoaneurysm (p = 0.003). Independent predictors of splenectomy in the logistic regression were final hemoperitoneum volume (unit OR = 1.43 for each 100 mL change; 95% CI: 0.99–2.06) and new/persistent pseudoaneurysm (OR = 160.3; 95% CI: 0.91–28315.3). The AUC of the model incorporating both variables was significantly higher than AAST grading (0.91 vs. 0.59, p = 0.025). Mean combined effective dose for admission and follow up CT scans was 37.4 mSv. Conclusion: Follow-up CT provides clinically valuable information regarding the decision to perform splenectomy in BSI patients managed non-operatively. Hemoperitoneum volume and new or persistent pseudoaneurysm at follow-up are independent predictors of splenectomy.
Collapse
Affiliation(s)
- David Dreizin
- Trauma and Emergency Radiology, Department of Diagnostic Radiology and Nuclear Medicine, School of Medicine, R Adams Cowley Shock Trauma Center, University of Maryland, Baltimore, MD, United States
- CORRESPONDENCE: David Dreizin
| | - Theresa Yu
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States
| | - Kaitlynn Motley
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States
| | - Guang Li
- Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States
| | - Jonathan J. Morrison
- Vascular Surgery, R Adams Cowley Shock Trauma Center, University of Maryland School of Medicine, Baltimore, MD, United States
| | - Yuanyuan Liang
- Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, MD, United States
| |
Collapse
|
3
|
Leone E, Garipoli A, Ripani U, Lanzetti RM, Spoliti M, Creta D, Giannace C, Galluzzo A, Trinci M, Galluzzo M. Imaging Review of Pelvic Ring Fractures and Its Complications in High-Energy Trauma. Diagnostics (Basel) 2022; 12:diagnostics12020384. [PMID: 35204475 PMCID: PMC8870907 DOI: 10.3390/diagnostics12020384] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Revised: 01/26/2022] [Accepted: 01/31/2022] [Indexed: 02/06/2023] Open
Abstract
Pelvic ring fractures are common in high-energy blunt trauma, especially in traffic accidents. These types of injuries have a high rate of morbidity and mortality, due to the common instability of the fractures, and the associated intrapelvic vascular and visceral complications. Computed tomography (CT) is the gold standard technique in the evaluation of pelvic trauma because it can quickly and accurately identify pelvic ring fractures, intrapelvic active bleeding, and lesions of other body systems. To properly guide the multidisciplinary management of the polytrauma patient, a classification criterion is mandatory. In this review, we decided to focus on the Young and Burgess classification, because it combines the mechanism and the stability of the fractures, helping to accurately identify injuries and related complications.
Collapse
Affiliation(s)
- Edoardo Leone
- Department of Emergency Radiology, Azienda Ospedaliera San Camillo-Forlanini, 00152 Rome, Italy; (M.T.); (M.G.)
- Correspondence:
| | - Andrea Garipoli
- Department of Radiology, Università Campus Bio-Medico di Roma, 00128 Rome, Italy;
| | - Umberto Ripani
- Department of Emergency and Major Trauma, Division of Anaesthesia, Analgesia and Intensive Care and Pain Therapy, Ospedali Riuniti di Ancona, 60162 Ancona, Italy;
| | - Riccardo Maria Lanzetti
- Orthopaedics and Traumatology Unit, Department of Emergency and Acceptance, Azienda Ospedaliera San Camillo-Forlanini, 00152 Rome, Italy; (R.M.L.); (M.S.)
| | - Marco Spoliti
- Orthopaedics and Traumatology Unit, Department of Emergency and Acceptance, Azienda Ospedaliera San Camillo-Forlanini, 00152 Rome, Italy; (R.M.L.); (M.S.)
| | - Domenico Creta
- Physical Medicine and Rehabilitation Service, Casa di Cura Privata Madre Fortunata Toniolo, 40141 Bologna, Italy;
| | | | - Antonio Galluzzo
- Department of Radiology, Università Degli Studi di Firenze, 50121 Florence, Italy;
| | - Margherita Trinci
- Department of Emergency Radiology, Azienda Ospedaliera San Camillo-Forlanini, 00152 Rome, Italy; (M.T.); (M.G.)
| | - Michele Galluzzo
- Department of Emergency Radiology, Azienda Ospedaliera San Camillo-Forlanini, 00152 Rome, Italy; (M.T.); (M.G.)
| |
Collapse
|
4
|
Spiliopoulos S, Theodosis A, Palialexis K, Efthimiou E, Reppas L, Argentos S, Filippiadis D, Kelekis N, Brountzos E. MDCTA volumetric analysis for the quantification and grading of acute non-cerebral, non-gastrointestinal hemorrhage: a feasibility study. Emerg Radiol 2021; 28:1151-1159. [PMID: 34365575 DOI: 10.1007/s10140-021-01975-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2021] [Accepted: 07/27/2021] [Indexed: 02/05/2023]
Abstract
PURPOSE To assess the feasibility of multi-detector computed tomography angiography (MDCTA) volumetry for the quantification and grading of acute non-cerebral, non-gastrointestinal bleeding. METHODS This retrospective, single-center study investigated consecutive patients with MDCTA positive for active non-cerebral, non-gastrointestinal bleeding, between January 2020 and June 2020. Outcome measures were the quantification of active extravasation at the arterial and parenchymal phase using volumetry measurements, the calculation of active bleeding rate and bleeding grading, 30-day mortality rate, identification of independent predictors of mortality and correlation between volumetric analysis, various clinical features, and the decision to proceed with an intervention. RESULTS In total 30 patients (17 females; 56.6%; mean age 70.0 ± 16.0 years) were analyzed. Volumetric analysis was feasible in all cases resulting in excellent inter-observer variability (interclass correlation coefficient 0.999 for arterial and 0.919 for venous volume measurements). Mean volume of contrast extravasation was 1.06 ± 1.09 ml and 3.07 ± 2.48 ml at the arterial and parenchymal phases, respectively. Mean bleeding rate was 6.95 ± 7.82 ml/min. High bleeding volume at arterial phase (grade 4 bleeding) was the only independent predictor of 30-day mortality (HR 1383.58; p = 0.042). There was a positive correlation between bleeding volume at arterial phase (rs = 0.340; p = 0.033) and arterial bleeding rate (rs = 0.381; p = 0.019) with the decision to proceed with an intervention. Bleeding volume of 0.6 ml was the cutoff value for the prediction of intervention (sensitivity 96.3%; specificity 66.7%). CONCLUSIONS MDCTA volumetric analysis for the quantification and grading of acute hemorrhage was feasible with excellent inter-observer agreement. The proposed bleeding grading system could optimize decision making and predict clinical outcomes.
Collapse
Affiliation(s)
- Stavros Spiliopoulos
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece.
| | - Antonios Theodosis
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Konstantinos Palialexis
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Evgenia Efthimiou
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Lazaros Reppas
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Stylianos Argentos
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Dimitrios Filippiadis
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Nikolaos Kelekis
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| | - Elias Brountzos
- 2nd Department of Radiology, Division of Interventional Radiology, Medical School, National and Kapodistrian University of Athens, "Attikon" University General Hospital, 1st Rimini St, GR 12461, Chaidari, Athens, Greece
| |
Collapse
|
5
|
Dreizin D. Commentary on "Multidetector CT in Vascular Injuries Resulting from Pelvic Fractures". Radiographics 2019; 39:2130-2133. [PMID: 31721653 PMCID: PMC6884065 DOI: 10.1148/rg.2019190192] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Affiliation(s)
- David Dreizin
- Department of Diagnostic Radiology and Nuclear Medicine, R. Adams Cowley Shock Trauma Center, University of Maryland School of Medicine Baltimore, Maryland
| |
Collapse
|