Blunt splenic injury: Assessment of follow-up CT utility using quantitative volumetry

Incidence of pseudoaneurysm after follow-up computed tomography for nonoperatively managed splenic injury: Systematic review

BACKGROUND

The aim of this systematic review was to assess the estimated incidence of pseudoaneurysm (PSA) with follow-up computed tomography (CT) for adult splenic injury with nonoperative management (NOM).

METHODS

A systematic literature search was conducted in MEDLINE, Central, CINAHL, Clinical Trials, and ICTRP databases between January 1, 2010, and December 31, 2023. Quality assessment was performed using the Risk of Bias in Non-randomized Studies of Exposures (ROBINS-E) tool. Adult splenic injury patients who were initially managed with NOM and followed-up by protocolized CT were included. The primary outcome was the incidence of delayed PSA. Secondary outcome measures were delayed angiography and delayed splenectomy. Subgroup analyses were performed between NOM patients without initial splenic angioembolization (SAE) and NOM patients with initial SAE.

RESULTS

Twelve studies were enrolled, including 11 retrospective studies and one prospective study, with 1746 patients in total. The follow-up CT rate in the included patients was 94.9%. The estimated incidence of PSA was 14% (95% confidence interval (CI), 8%-21%). The estimated delayed angiography and delayed splenectomy incidence rates were 7% (95% CI, 4%-12%) and 2% (95% CI, 1%-6%), respectively. Subgroup analyses showed that the estimated PSA incidence was 12% in NOM patients without initial SAE (95% CI, 7%-20%) and was also 12% in NOM patients with SAE (95% CI, 5%-24%).

CONCLUSIONS

The estimated incidence of delayed PSA after follow-up CT for adult splenic injury with NOM was 14%. The estimated incidence of PSA in NOM with initial SAE was similar to that in NOM without initial SAE.

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

Background

precision-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.

Purpose

In 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.

Methods

57 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.

Results

AICL 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.

Conclusion

For 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.

Toward automated interpretable AAST grading for blunt splenic injury

BACKGROUND

The American Association for the Surgery of Trauma (AAST) splenic organ injury scale (OIS) is the most frequently used CT-based grading system for blunt splenic trauma. However, reported inter-rater agreement is modest, and an algorithm that objectively automates grading based on transparent and verifiable criteria could serve as a high-trust diagnostic aid.

PURPOSE

To pilot the development of an automated interpretable multi-stage deep learning-based system to predict AAST grade from admission trauma CT.

METHODS

Our pipeline includes 4 parts: (1) automated splenic localization, (2) Faster R-CNN-based detection of pseudoaneurysms (PSA) and active bleeds (AB), (3) nnU-Net segmentation and quantification of splenic parenchymal disruption (SPD), and (4) a directed graph that infers AAST grades from detection and segmentation results. Training and validation is performed on a dataset of adult patients (age ≥ 18) with voxelwise labeling, consensus AAST grading, and hemorrhage-related outcome data (n = 174).

RESULTS

AAST classification agreement (weighted κ) between automated and consensus AAST grades was substantial (0.79). High-grade (IV and V) injuries were predicted with accuracy, positive predictive value, and negative predictive value of 92%, 95%, and 89%. The area under the curve for predicting hemorrhage control intervention was comparable between expert consensus and automated AAST grading (0.83 vs 0.88). The mean combined inference time for the pipeline was 96.9 s.

CONCLUSIONS

The results of our method were rapid and verifiable, with high agreement between automated and expert consensus grades. Diagnosis of high-grade lesions and prediction of hemorrhage control intervention produced accurate results in adult patients.