Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis

Abstract

Background: Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking.

Materials and methods: PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively.

Results: A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P =0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P =0.001).

Conclusion: This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.

Figure 1

Flowchart of the study selection process.

Figure 2

Summary of overall quality assessment for included studies. Green means ‘low risk’; Blue ‘means unclear’; Orange means ‘high risk’.

Figure 3

Results of raw diagnostic accuracy data: (Ai) Forest plots of pooled sensitivity (Aii) Forest plots of pooled specificity; (B) SROC showed average sensitivity and specificity estimate of the study results with 95% confidence region. The 95% prediction region represents the confidence region for a forecast of the true sensitivity and specificity in a future study; (C) Fagan’s line diagram; (D) LR dot plot. LLQ, left lower quadrant; LRN, likelihood ratio negative; LRP, likelihood ratio positive; LUQ, left upper quadrant; RLQ, right lower quadrant; RUQ, right upper quadrant; SROC, summary receiver operating characteristic.

Figure 4

Forest plots of (A) bleeding volume; (B) process time demonstrated that there was no significant difference in bleeding volume between manual labeling and deep learning model. DL, deep learning; MD, mean difference; WMD, weight mean difference.