Only moderate intra- and inter-observer agreement between radiologists and surgeons when grading blunt paediatric hepatic injury on CT scan

Management of pediatric blunt abdominal trauma with split liver or spleen injuries: a retrospective study

BACKGROUND

Blunt abdominal trauma is a prevailing cause of pediatric morbidity and mortality. It constitutes the most frequent type of pediatric injuries. Contrast-enhanced sonography (CEUS) and contrast-enhanced computed tomography (CECT) are considered pivotal diagnostic modalities in hemodynamically stable patients.

AIM

To report the experience in management of pediatric split liver and spleen injuries using CEUS and CECT.

PATIENTS AND METHODS

This study included 246 children who sustained blunt abdominal trauma, and admitted and treated at three tertiary hospitals in the period of 5 years. Primary resuscitation was offered to all children based on the advanced trauma and life support (ATLS) protocol. A special algorithm for decision-making was followed. It incorporated the FAST, baseline ultrasound (US), CEUS, and CECT. Patients were treated according to the imaging findings and hemodynamic stability.

RESULTS

All 246 children who sustained a blunt abdominal were studied. Patients' age was 10.5 ± 2.1. Road traffic accidents were the most common cause of trauma; 155 patients (63%). CECT showed the extent of injury in 153 patients' spleen (62%) and 78 patients' liver (32%), while the remaining 15 (6%) patients had both injuries. CEUS detected 142 (57.7%) spleen injury, and 67 (27.2%) liver injury.

CONCLUSIONS

CEUS may be a useful diagnostic tool among hemodynamically stable children who sustained low-to-moderate energy isolated blunt abdominal trauma. It may be also helpful for further evaluation of uncertain CECT findings and follow-up of conservatively managed traumatic injuries.

Automated quantitative assessment of pediatric blunt hepatic trauma by deep learning-based CT volumetry

BACKGROUND

To develop an end-to-end deep learning method for automated quantitative assessment of pediatric blunt hepatic trauma based on contrast-enhanced computed tomography (CT).

METHODS

This retrospective study included 170 children with blunt hepatic trauma between May 1, 2015, and August 30, 2021, who had undergone contrast-enhanced CT. Both liver parenchyma and liver trauma regions were manually segmented from CT images. Two deep convolutional neural networks (CNNs) were trained on 118 cases between May 1, 2015, and December 31, 2019, for liver segmentation and liver trauma segmentation. Liver volume and trauma volume were automatically calculated based on the segmentation results, and the liver parenchymal disruption index (LPDI) was computed as the ratio of liver trauma volume to liver volume. The segmentation performance was tested on 52 cases between January 1, 2020, and August 30, 2021. Correlation analysis among the LPDI, trauma volume, and the American Association for the Surgery of Trauma (AAST) liver injury grade was performed using the Spearman rank correlation. The performance of severity assessment of pediatric blunt hepatic trauma based on the LPDI and trauma volume was evaluated using receiver operating characteristic (ROC) analysis.

RESULTS

The Dice, precision, and recall of the developed deep learning framework were 94.75, 94.11, and 95.46% in segmenting the liver and 72.91, 72.40, and 76.80% in segmenting the trauma regions. The LPDI and trauma volume were significantly correlated with AAST grade (rho = 0.823 and rho = 0.831, respectively; p < 0.001 for both). The area under the ROC curve (AUC) values for the LPDI and trauma volume to distinguish between high-grade and low-grade pediatric blunt hepatic trauma were 0.942 (95% CI, 0.882-1.000) and 0.952 (95% CI, 0.895-1.000), respectively.

CONCLUSIONS

The developed end-to-end deep learning method is able to automatically and accurately segment the liver and trauma regions from contrast-enhanced CT images. The automated LDPI and liver trauma volume can act as objective and quantitative indexes to supplement the current AAST grading of pediatric blunt hepatic trauma.

A deep learning framework for automated detection and quantitative assessment of liver trauma

Background

Both early detection and severity assessment of liver trauma are critical for optimal triage and management of trauma patients. Current trauma protocols utilize computed tomography (CT) assessment of injuries in a subjective and qualitative (v.s. quantitative) fashion, shortcomings which could both be addressed by automated computer-aided systems that are capable of generating real-time reproducible and quantitative information. This study outlines an end-to-end pipeline to calculate the percentage of the liver parenchyma disrupted by trauma, an important component of the American Association for the Surgery of Trauma (AAST) liver injury scale, the primary tool to assess liver trauma severity at CT.

Methods

This framework comprises deep convolutional neural networks that first generate initial masks of both liver parenchyma (including normal and affected liver) and regions affected by trauma using three dimensional contrast-enhanced CT scans. Next, during the post-processing step, human domain knowledge about the location and intensity distribution of liver trauma is integrated into the model to avoid false positive regions. After generating the liver parenchyma and trauma masks, the corresponding volumes are calculated. Liver parenchymal disruption is then computed as the volume of the liver parenchyma that is disrupted by trauma.

Results

The proposed model was trained and validated on an internal dataset from the University of Michigan Health System (UMHS) including 77 CT scans (34 with and 43 without liver parenchymal trauma). The Dice/recall/precision coefficients of the proposed segmentation models are 96.13/96.00/96.35% and 51.21/53.20/56.76%, respectively, in segmenting liver parenchyma and liver trauma regions. In volume-based severity analysis, the proposed model yields a linear regression relation of 0.95 in estimating the percentage of liver parenchyma disrupted by trauma. The model shows an accurate performance in avoiding false positives for patients without any liver parenchymal trauma. These results indicate that the model is generalizable on patients with pre-existing liver conditions, including fatty livers and congestive hepatopathy.

Conclusion

The proposed algorithms are able to accurately segment the liver and the regions affected by trauma. This pipeline demonstrates an accurate performance in estimating the percentage of liver parenchyma that is affected by trauma. Such a system can aid critical care medical personnel by providing a reproducible quantitative assessment of liver trauma as an alternative to the sometimes subjective AAST grading system that is used currently.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00759-9.

Management of renal injury in a UK major trauma centre

Introduction

This study reviews the type, severity, management and follow-up of renal trauma presenting to a major trauma centre in the northwest of England in the four years following inception of the major trauma centre. Given the recent introduction of major trauma centres nationally, research is needed within every specialty to ensure that the centralisation of services benefits all patients affected by these changes.

Methods

Patients presenting to Aintree University Hospital with renal trauma between June 2012 and June 2016 were identified using the Trauma Audit and Research Network (TARN) database. The data gathered retrospectively for each patient included mechanism of injury, injury severity score, American Association for the Surgery of Trauma (AAST) grading, management of injury, and follow-up.

Results

Out of a total of 2595 trauma patients, 33 renal injuries were identified. The 31 patients who received imaging were classified according to AAST grading, with 8 Grade I (25.8%), 4 Grade II (12.9%), 8 Grade III (25.8%), 4 Grade IV (12.9%), and 7 Grade V (22.6%) injuries. Twenty-five out of the 30 surviving patients received conservative treatment, three patients received angioembolisation (AE), one patient received a laparotomy with renal suturing, and one patient required a nephrectomy. Of these 30 surviving patients, seven received urology follow-up in clinic (23%).

Conclusion

The findings appear to support the growing trend towards the conservative management of high-grade renal injuries, and provide further evidence for the value of AE in renal trauma. The success of AE in this study appears to support the centralisation of services in renal trauma; however, the low nephrectomy rate could be interpreted as suggestive of the opposite. The study revealed that improvements to follow-up are needed, and that further research should seek to inform the optimal radiological follow-up of high-grade renal injury.

The medico-legal assessment of aesthetic damage. A correlation analysis between experts and an operative proposal

Aesthetic damage, defined as any detrimental modification of the individual morpho-functional exterior attributes, is difficult to assess, since the perception of its entity is rather subjective. This study aims to provide a medico-legal contribution to the assessment of this kind of damage. 60 photographic images, representing stabilized aesthetic damage, were collected and showed to 16 expert evaluators, who were required to exclusively quantify the objective component of the aesthetic impairment. The inter-observer agreement for the assessments was calculated using the Intraclass Correlation Coefficient (ICC). Looking into specific characteristics of both the injury and the damaged subject, the assessors were more consistent in quantifying the damage in male subjects (ICC 0.68) and in subjects aged over 50 years (ICC 0.81) as well as in assessing extensive damages (ICC 0.61) than those of mild severity (ICC 0.41). The assessment of impairments located in the facial area resulted in a high level of concordance (ICC 0.73), while damages located the head and neck regions presented the lowest concordance (ICC 0.35). The evaluators were more consistent in assessing the outcomes of burns (ICC 0.70). Regardless the various reasons underlying the different degree of concordance, these results and the high degree of the overall concordance (ICC 0.63) point out the skillfulness of medicolegal professionals to formulate a complex judgment as more objectively as possible. Finally, an operative proposal was outlined to guide medico-legal professionals or interns in evaluating the aesthetic damage as more objectively as possible.

Triple-split-bolus versus single-bolus CT in abdominal trauma patients: a comparative study

Background Split-bolus computed tomography (CT) is a recent development in trauma imaging. Instead of multiple scans in different contrast phases after a single contrast bolus, split-bolus protocols consist of one single scan of the thorax and abdomen after two or three contrast injections at different points of time. Purpose To evaluate and compare image quality and injury findings of a new triple-split-bolus CT (TS-CT) protocol of thorax and abdomen with those of a portal venous phase CT (PV-CT) in the same patient group. Material and Methods Trauma patients in 2009-2012 who underwent both the TS-CT initially and a PV-CT during the next six weeks were included. The TS-CT examination was performed as one CT run after application of three contrast boluses (total 175 mL) to enhance renal pelvis and urinary tract, the abdominal organs, and the large arterial vessels. The PV-CT had a fixed delay of 85 s. We measured attenuation in Hounsfield units (HU), evaluated possible organ injury and assessed image quality on a 5-point scale. Results Thirty-five patients were included. Attenuation measurements of major abdominal vessels, organs, and renal pelvis were significantly higher with the TS-CT protocol. Performance in organ injury diagnosis and image quality was equal in both protocols. Conclusion The overall performance of the TS-CT protocol is similar to the standard PV-CT. Excellent visualization of the arterial tree and the collecting system may eliminate the need for separate scans.

Added value of double reading in diagnostic radiology,a systematic review

Objectives

Double reading in diagnostic radiology can find discrepancies in the original report, but a systematic program of double reading is resource consuming. There are conflicting opinions on the value of double reading. The purpose of the current study was to perform a systematic review on the value of double reading.

Methods

A systematic review was performed to find studies calculating the rate of misses and overcalls with the aim of establishing the added value of double reading by human observers.

Results

The literature search resulted in 1610 hits. After abstract and full-text reading, 46 articles were selected for analysis. The rate of discrepancy varied from 0.4 to 22% depending on study setting. Double reading by a sub-specialist, in general, led to high rates of changed reports.

Conclusions

The systematic review found rather low discrepancy rates. The benefit of double reading must be balanced by the considerable number of working hours a systematic double-reading scheme requires. A more profitable scheme might be to use systematic double reading for selected, high-risk examination types. A second conclusion is that there seems to be a value of sub-specialisation for increased report quality. A consequent implementation of this would have far-reaching organisational effects.

Key Points

• In double reading, two or more radiologists read the same images.

• A systematic literature review was performed.

• The discrepancy rates varied from 0.4 to 22% in various studies.

• Double reading by sub-specialists found high discrepancy rates.

Electronic supplementary material

The online version of this article (10.1007/s13244-018-0599-0) contains supplementary material, which is available to authorised users.

Inter-radiologist agreement for CT scoring of pediatric splenic injuries and effect on an established clinical practice guideline

BACKGROUND

The American Pediatric Surgical Association (APSA) advocates for the use of a clinical practice guideline to direct management of hemodynamically stable pediatric spleen injuries. The clinical practice guideline is based on the CT score of the spleen injury according to the American Association for the Surgery of Trauma (AAST) CT scoring system.

OBJECTIVE

To determine the potential effect of radiologist agreement for CT scoring of pediatric spleen injuries on an established APSA clinical practice guideline.

MATERIALS AND METHODS

We retrospectively analyzed blunt splenic injuries occurring in children from January 2007 to January 2012 at a single level 1 trauma center (n = 90). Abdominal CT exams performed at clinical presentation were reviewed by four radiologists who documented the following: (1) splenic injury grade (AAST system), (2) arterial extravasation and (3) pseudoaneurysm. Inter-rater agreement for AAST injury grade was assessed using the multi-rater Fleiss kappa and Kendall coefficient of concordance. Inter-rater agreement was assessed using weighted (AAST injury grade) or prevalence-adjusted bias-adjusted (binary measures) kappa statistics; 95% confidence intervals were calculated. We evaluated the hypothetical effect of radiologist disagreement on an established APSA clinical practice guideline.

RESULTS

Inter-rater agreement was good for absolute AAST injury grade (kappa: 0.64 [0.59–0.69]) and excellent for relative AAST injury grade (Kendall w: 0.90). All radiologists agreed on the AAST grade in 52% of cases. Based on an established clinical practice guideline, radiologist disagreement could have changed the decision for intensive care management in 11% (10/90) of children, changed the length of hospital stay in 44% (40/90), and changed the time to return to normal activity in 44% (40/90).

CONCLUSION

Radiologist agreement when assigning splenic AAST injury grades is less than perfect, and disagreements have the potential to change management in a substantial number of pediatric patients.

Scanning and War: Utility of FAST and CT in the Assessment of Battlefield Abdominal Trauma

OBJECTIVE

To determine utilization and accuracy of focused assessment with sonography for trauma (FAST) and computed tomography (CT) in a mature military trauma system to inform service provision for future conflicts.

BACKGROUND

FAST and CT scans undertaken by attending radiologists contribute to surgical decision making for battlefield casualties at the Joint Force, Role 3 Medical Treatment Facility at Camp Bastion (R3), Afghanistan.

METHODS

Registry data for abdominally injured casualties treated at R3 from July to November 2012 were matched to radiological and surgical records to determine diagnostic accuracy for FAST and CT and their influence on casualty management.

RESULTS

A total of 468 casualties met inclusion criteria, of whom 85.0% underwent FAST and 86.1% abdominal CT; 159 (34.0%) had abdominal injuries. For detection of intra-abdominal injury, FAST sensitivity (Sn) was 0.56, specificity (Sp) 0.98, positive predictive value (PPV) 0.87, negative predictive value (NPV) 0.90, and accuracy (Acc) 0.89. For CT, Sn was 0.99, Sp 0.99, PPV 0.96, NPV 1.00, and Acc 0.99. Forty-six solid organ injuries were identified in 38 patients by CT; 17 were managed nonoperatively. A further 61 patients avoided laparotomy after CT confirmed extra-abdominal wounds only. The negative laparotomy rate was 3.9%.

CONCLUSIONS

FAST and CT contribute to triage, guide surgical management, and reduce nontherapeutic laparotomy. When imaging is available, these data challenge current doctrine about inadvisability of nonoperative management of abdominal injury after combat trauma.

The definition of polytrauma: variable interrater versus intrarater agreement--a prospective international study among trauma surgeons

BACKGROUND

The international trauma community has recognized the lack of a validated consensus definition of "polytrauma." We hypothesized that using a subjective definition, trauma surgeons will not have substantial agreement; thus, an objective definition is needed.

METHODS

A prospective observational study was conducted between December 2010 and June 2011 (John Hunter Hospital, Level I trauma center). Inclusion criteria were all trauma call patients with subsequent intensive care unit admission. The study was composed of four stages as follows: (1) four trauma surgeons assessed patients until 24 hours, then coded as either "yes" or "no" for polytrauma, and results compared for agreement; (2) eight trauma surgeons representing the United States, Germany, and the Netherlands graded the same prospectively assessed patients and coded as either "yes" or "no" for polytrauma; (3) 12 months later, the original four trauma surgeons repeated assessment via data sheets to test intrarater variability; and (4) individual subjective definitions were compared with three anatomic scores, namely, (a) Injury Severity Score (ISS) of greater than 15, (b) ISS of greater 17, and (c) Abbreviated Injury Scale (AIS) score of greater than 2 in at least two ISS body regions.

RESULTS

A total of 52 trauma patients were included. Results for each stage were as follows: (1) κ score of 0.50, moderate agreement; (2) κ score of 0.41, moderate agreement; (3) Rater 1 had moderate intrarater agreement (κ score, 0.59), while Raters 2, 3, 4 had substantial intrarater agreement (κ scores, 0.75, 0.66, and 0.71, respectively); and (4) none had most agreement with ISS of greater than 15 (κ score, 0.16), while both definitions ISS greater than 17 and Abbreviated Injury Scale (AIS) score of greater than 2 in at least two ISS body regions had on average fair agreement (κ scores, 0.27 and 0.39, respectively).

CONCLUSION

Based on subjective assessments, trauma surgeons do not agree on the definition of polytrauma, with the subjective definition differing both within and across institutions.

Solid Organ Injury Grading in Trauma: Accuracy of Grading by Surgical Residents

The American Association for the Surgery of Trauma developed an Organ Injury Scale for management of patients with splenic, kidney, or liver injuries. Despite widespread use of the guidelines, the person who determines the injury grade varies among institutions. Our purpose was to determine the accuracy and interobserver agreement between surgical residents and a radiologist in grading solid organ injuries. We retrospectively reviewed patients with solid organ injuries from January 2009 to May 2010 and compared the grade of solid organ injuries by a single resident with grades by a single blinded radiologist using a paired t test, analysis of variance, or Kruskal-Wallis. Computed tomography scans of 58 patients with splenic injuries, 43 with liver injuries, and 16 with kidney injuries were reviewed. Average grades for splenic injuries were 2.5 and 2.4 (radiologist/resident); liver injuries, 2.6 and 2.1; and kidney injuries, 2.7 and 2.8. There were no significant differences in grading by the radiologist and resident for splenic and kidney injuries; however, equal values were only achieved in 43 and 38 per cent, respectively. There was a significant difference (average rating difference 0.54, P = 0.0002) in grading between the radiologist and resident for liver injuries with only 35 per cent having equal values and the radiologist grading on average 0.5 points higher than the resident. No demographic, injury, or outcome variables were significantly associated with interobserver variability ( P > 0.05). Despite a significant difference for liver injury grading, interobserver agreement between residents and a single radiologist was low. Clinical implications and the impact on outcomes related to interobserver variations require further study.