Correlation of operative and pathological injury grade with computed tomographic grade in the failed nonoperative management of blunt splenic trauma

The three-dimensional weakly supervised deep learning algorithm for traumatic splenic injury detection and sequential localization: an experimental study

BACKGROUND

Splenic injury is the most common solid visceral injury in blunt abdominal trauma, and high-resolution abdominal computed tomography (CT) can adequately detect the injury. However, these lethal injuries sometimes have been overlooked in current practice. Deep learning (DL) algorithms have proven their capabilities in detecting abnormal findings in medical images. The aim of this study is to develop a three-dimensional, weakly supervised DL algorithm for detecting splenic injury on abdominal CT using a sequential localization and classification approach.

MATERIAL AND METHODS

The dataset was collected in a tertiary trauma center on 600 patients who underwent abdominal CT between 2008 and 2018, half of whom had splenic injuries. The images were split into development and test datasets at a 4 : 1 ratio. A two-step DL algorithm, including localization and classification models, was constructed to identify the splenic injury. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Grad-CAM (Gradient-weighted Class Activation Mapping) heatmaps from the test set were visually assessed. To validate the algorithm, we also collected images from another hospital to serve as external validation data.

RESULTS

A total of 480 patients, 50% of whom had spleen injuries, were included in the development dataset, and the rest were included in the test dataset. All patients underwent contrast-enhanced abdominal CT in the emergency room. The automatic two-step EfficientNet model detected splenic injury with an AUROC of 0.901 (95% CI: 0.836-0.953). At the maximum Youden index, the accuracy, sensitivity, specificity, PPV, and NPV were 0.88, 0.81, 0.92, 0.91, and 0.83, respectively. The heatmap identified 96.3% of splenic injury sites in true positive cases. The algorithm achieved a sensitivity of 0.92 for detecting trauma in the external validation cohort, with an acceptable accuracy of 0.80.

CONCLUSIONS

The DL model can identify splenic injury on CT, and further application in trauma scenarios is possible.

Analysis of Need for Intervention in Low-Grade Traumatic Splenic Injury

BACKGROUND

Blunt splenic injuries are common traumatic injuries. Severe injuries may require blood transfusion, procedural, or operative intervention. Conversely, patients with low-grade injuries and normal vital signs frequently do not require intervention. The level and duration of monitoring required to safely manage these patients are unclear. We hypothesize that low-grade splenic trauma has a low rate of intervention and may not require acute hospitalization.

METHODS

This retrospective descriptive analysis included patients admitted to a level I trauma center with low injury burden (injury severity score <15) and The American Association for the Surgery of Trauma (AAST) grade 1 (G1) and 2 (G2) splenic injuries between January 2017 and December 2019 using the Trauma Registry of the American College of Surgeons (TRACS). The primary outcome was the need for any intervention. Secondary outcomes included time to intervention and length of stay.

RESULTS

107 patients met inclusion criteria. 87.9% required no intervention . 9.4% required blood products, with a median time to transfusion of 7.4 hours from arrival. All patients receiving blood products had extenuating circumstances such as bleeding from other injuries, anticoagulant use, or medical comorbidities. 2 patients required splenic artery embolization, one presenting with return precautions 9 days post-injury and 1 with significant comorbidities. One patient with concomitant bowel injury required splenectomy.

CONCLUSIONS

Low-grade blunt splenic trauma has a low rate of intervention, which typically occurs within the first 12 hours of presentation. This suggests that outpatient management with return precautions may be appropriate for select patients after a short interval of observation.

Delayed splenic rupture after a minor blunt trauma: A case report and literature review

Delayed Splenic Rupture (DSR) is a rare but well-known manifestation of Blunt Splenic Injury (BSI), which most commonly occurs following a car accident, a fall from a great height, or a direct blow to the left thorax or abdomen. If the history of trauma is remote or unknown, the diagnosis can be difficult or missed, and a high index of suspicion is not warranted. Regardless of the time and mechanism of the inciting event, DSR should be considered in the differential diagnosis of an acute surgical abdomen. We present a case of DSR in an 81-year-old woman caused by a remote minor blunt abdominal trauma four weeks prior to her admission to our emergency department for acute abdominal pain and hemorrhagic shock (ATLS CLASS III). Starting with this case report, we conducted a literature review on the subject in order to raise awareness, knowledge, and understanding of DSR among emergency clinicians.

Liver trauma: WSES 2020 guidelines

Liver injuries represent one of the most frequent life-threatening injuries in trauma patients. In determining the optimal management strategy, the anatomic injury, the hemodynamic status, and the associated injuries should be taken into consideration. Liver trauma approach may require non-operative or operative management with the intent to restore the homeostasis and the normal physiology. The management of liver trauma should be multidisciplinary including trauma surgeons, interventional radiologists, and emergency and ICU physicians. The aim of this paper is to present the World Society of Emergency Surgery (WSES) liver trauma management guidelines.

Delayed Rupture of a Normal Appearing Spleen After Trauma: Is Our Knowledge Enough? Two Case Reports

BACKGROUND Non-operative management is considered the gold standard for hemodynamically stable patients with splenic injuries. Delayed splenic rupture is a well-known complication of non-operative management in splenic trauma, with a relevant impact on mortality and morbidity. Most of the reported cases of delayed splenic rupture presented splenic injury at admission imaging or no imaging investigations were performed. We report 2 cases of delayed splenic rupture after blunt trauma, in which multidetector computed tomography (CT) scan at admission did not show any splenic injury.   CASE REPORT Two patients were admitted to our emergency surgery unit after abdominal trauma with left rib fractures, but no solid organ injuries were detected at CT scan. Some days after the trauma, both patients suddenly developed hemorrhagic shock due to splenic rupture and required emergency splenectomy. CONCLUSIONS Trauma patients' management and follow-up remains challenging for surgeons, because of sudden clinical changes that can occur. Delayed splenic rupture with inconspicuous admission CT scan is a rare event. In some cases, it seems to be related to a poor CT quality, but this explanation cannot be adopted in all cases. Moreover, there is no standardization for imaging follow-up in the case of a normal CT scan at admission, in order to prevent delayed hemorrhage. In this context, every element that can identify patients with higher risk of delayed splenic rupture is of great importance. We suggest that lower left rib fractures can be associated with delayed splenic rupture, and we propose some explaining hypothesis.

Splenic trauma in the twenty-first century: changing trends in management

Over the past three decades, management of blunt splenic trauma has changed radically. Use of improved diagnostic techniques and proper understanding of disease pathology has led to nonoperative management being chosen as the standard of care in patients who are haemodynamically stable. This review was undertaken to assess available literature regarding changing trends of management of blunt splenic trauma, and to identify the existing lacunae in nonoperative management. The PubMed database was searched for studies published between January 1987 and August 2017, using the keywords 'blunt splenic trauma' and 'nonoperative management'. One hundred and fifty-three articles were reviewed, of which 82 free full texts and free abstracts were used in the current review. There is clear evidence in published literature of the greater success of nonoperative over operative management in patients who are haemodynamically stable and the increasing utility of adjunctive therapies like angiography with embolisation. However, the review revealed a lack of universal guidelines for patient selection criteria and diagnostic and grading procedures needed for nonoperative management. Indications for splenic artery embolisation, the current role of splenectomy and spleen-preserving surgeries, together with the place of minimal access surgery in blunt splenic trauma remain grey areas. Moreover, parameters affecting the outcomes of nonoperative management and its failure and management need to be defined. This shows a need for future studies focused on these shortcomings with the ultimate aim being the formulation and implementation of universally accepted guidelines for safe and efficient management of blunt splenic trauma.

Splenic trauma: WSES classification and guidelines for adult and pediatric patients

Spleen injuries are among the most frequent trauma-related injuries. At present, they are classified according to the anatomy of the injury. The optimal treatment strategy, however, should keep into consideration the hemodynamic status, the anatomic derangement, and the associated injuries. The management of splenic trauma patients aims to restore the homeostasis and the normal physiopathology especially considering the modern tools for bleeding management. Thus, the management of splenic trauma should be ultimately multidisciplinary and based on the physiology of the patient, the anatomy of the injury, and the associated lesions. Lastly, as the management of adults and children must be different, children should always be treated in dedicated pediatric trauma centers. In fact, the vast majority of pediatric patients with blunt splenic trauma can be managed non-operatively. This paper presents the World Society of Emergency Surgery (WSES) classification of splenic trauma and the management guidelines.