Blunt splenic injury in adults: Association between volumetric quantitative CT parameters and intervention

Dreizin, David; Champ, Kathryn; Dattwyler, Matthew; Bodanapally, Uttam K.; Smith, Elana B.; Li, Guang; Singh, Rohan; Wang, Ze; Liang, Yuanyuan

doi:10.1097/ta.0000000000003684

Cited by 5 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their study was more focused on the diagnostic modality of the splenic injury. They concluded in their study that CT volumetry is a more successful technique to model intervention in patients with splenic injury [13]. Guinto et al studied a comparison of total splenectomy and splenic angioembolization.…”

Section: Discussionmentioning

confidence: 99%

Prevalence of Splenic Injury in the Blunt Abdomen Trauma: A Cross- Sectional Study

Arshad¹,

Khan²,

Bhatti³

et al. 2023

PJMHS

View full text Add to dashboard Cite

Background: Blunt trauma to the abdomen most commonly leads to injury of the spleen. Patients usually presents with left hypochondriac pain or generalized abdominal pain which may radiate to the left shoulder. There can be associated left lower rib fractures. Diagnosis is made on contrast enhanced computed tomography (CT) of the abdomen. Surgical management is warranted in the cases according to AAST Grade of injury. Missed or delayed presentation of injury can lead to mortality hence careful evaluation of mode of injury, complete examination, appropriate investigation and monitoring are vital for patient management. Objective: The present study aims at the determination of incidence and causes of splenic injury after blunt trauma to the abdomen. Study design: A cross-sectional study Place and Duration: This study was conducted at Rawalpindi Medical University from November 2020 to November 2022 Methodology: A total of 195 patients were included in the study. The lowest age limit was 15 years and patients of both genders were considered. The patients with abdominal trauma were received in the emergency department. A detailed history of the event was taken from all the patients with simultaneous resuscitation. After that, a thorough clinical examination was performed on all the patients. The patients were sent for a FAST SCAN and CCET abdomen to diagnose and assess the extent of the injury. The type of trauma that lead to the injury of the spleen, such as road traffic accident (RTA), assault, and fall from height was recorded of each patient. Patients with AAST grade I and II were managed conservatively except in cases where exploration was required for concomitant abdominal injuries however patients with Grade III, IV and V underwent exploration, spleenoraphy or splenectomy respectivelyThe data was collected and analyzed in the IBM SPSS version 26. Result: A total of 195 patients were studied, out of which 48 (24.61%) were female and 147 (75.38%) were male. The mean age of the patients was 30.45±2.12 years. Overall 12 (6.15%) were detected with splenic injury. A total of 5 (41.67%) had an RTA, 4 (33.33%) had a fall from height, 2 (16.67%) assault, and 1 (8.33%) had sports injury. Conclusion: The most common type of blunt trauma to the abdomen which resulted in a splenic injury was road traffic accidents followed by fall from height. Early diagnosis is helpful in the proper management of the patient and increasing the survival rate. Keywords: Splenic injury, road traffic accident, blunt trauma

show abstract

Section: Discussionmentioning

confidence: 99%

Prevalence of Splenic Injury in the Blunt Abdomen Trauma: A Cross- Sectional Study

Arshad¹,

Khan²,

Bhatti³

et al. 2023

PJMHS

View full text Add to dashboard Cite

show abstract

“…Exsanguination remains a leading cause of preventable death, but clinical indices such as the shock index (SI) or Assessment of Blood Consumption (ABC) score are only modestly predictive and insensitive for life-threatening blood loss (47)(48)(49). The ability to predict outcomes or personalize treatment based on granular measurements of hemorrhage-related pathology on CT is a major precision medicine and personalized treatmentrelated value proposition of automated segmentation tools in the trauma domain (25,30,31,(34)(35)(36)(50)(51)(52)(53), but large scale out-ofsample studies are required to confirm proof-of-principle.…”

Section: Figure 3bmentioning

confidence: 99%

“…Despite the perceived unmet need for hemorrhage-related quantitative visualization tools (32), due to challenges unique to the torsonamely small target to total volume ratios and complex pathologydeep learning (DL) algorithms yielding meaningful visual results for the chest, abdomen, and pelvis, have been late-comers in medical image analysis (33). A limited number of studies using small datasets have demonstrated an association between intracavitary torso hemorrhage volumes and clinical outcomes (25,29,(34)(35)(36), with comparable or improved prediction compared to existing categorical grading systems. In 2021, Isensee et al, introduced nnUnet (37), an out-of-the-box self-configuring data-driven method which incorporates a 3D coarse-to-fine multiscale approach that has shown state-of-the-art performance on numerous public medical imaging datasets over bespoke multiscale methods.…”

Section: Introductionmentioning

confidence: 99%

Accelerating voxelwise annotation of cross-sectional imaging through AI collaborative labeling with quality assurance and bias mitigation

et al. 2023

Self Cite

View full text Add to dashboard Cite

Backgroundprecision-medicine quantitative tools for cross-sectional imaging require painstaking labeling of targets that vary considerably in volume, prohibiting scaling of data annotation efforts and supervised training to large datasets for robust and generalizable clinical performance. A straight-forward time-saving strategy involves manual editing of AI-generated labels, which we call AI-collaborative labeling (AICL). Factors affecting the efficacy and utility of such an approach are unknown. Reduction in time effort is not well documented. Further, edited AI labels may be prone to automation bias.PurposeIn this pilot, using a cohort of CTs with intracavitary hemorrhage, we evaluate both time savings and AICL label quality and propose criteria that must be met for using AICL annotations as a high-throughput, high-quality ground truth.Methods57 CT scans of patients with traumatic intracavitary hemorrhage were included. No participant recruited for this study had previously interpreted the scans. nnU-net models trained on small existing datasets for each feature (hemothorax/hemoperitoneum/pelvic hematoma; n = 77–253) were used in inference. Two common scenarios served as baseline comparison- de novo expert manual labeling, and expert edits of trained staff labels. Parameters included time effort and image quality graded by a blinded independent expert using a 9-point scale. The observer also attempted to discriminate AICL and expert labels in a random subset (n = 18). Data were compared with ANOVA and post-hoc paired signed rank tests with Bonferroni correction.ResultsAICL reduced time effort 2.8-fold compared to staff label editing, and 8.7-fold compared to expert labeling (corrected p < 0.0006). Mean Likert grades for AICL (8.4, SD:0.6) were significantly higher than for expert labels (7.8, SD:0.9) and edited staff labels (7.7, SD:0.8) (corrected p < 0.0006). The independent observer failed to correctly discriminate AI and human labels.ConclusionFor our use case and annotators, AICL facilitates rapid large-scale curation of high-quality ground truth. The proposed quality control regime can be employed by other investigators prior to embarking on AICL for segmentation tasks in large datasets.

show abstract

A pilot study of deep learning-based CT volumetry for traumatic hemothorax

Dreizin

Nixon

et al. 2022

Emerg Radiol

View full text Add to dashboard Cite

Blunt splenic injury in adults: Association between volumetric quantitative CT parameters and intervention

Abstract: CT volumetry of blunt splenic injury-related features predicts splenectomy and angioembolization in adults and identifies clinically important target features for computer vision and automation research.

Cited by 5 publications

References 45 publications

Prevalence of Splenic Injury in the Blunt Abdomen Trauma: A Cross- Sectional Study

Prevalence of Splenic Injury in the Blunt Abdomen Trauma: A Cross- Sectional Study

Accelerating voxelwise annotation of cross-sectional imaging through AI collaborative labeling with quality assurance and bias mitigation

A pilot study of deep learning-based CT volumetry for traumatic hemothorax

Contact Info

Product

Resources

About