<p>Systematic review summary table.</p>

The highest reported Dice Similarity Coefficient (DSC) for cardiac structures segmentation was achieved utilising an advanced hybrid ResNet-based model (Aorta, DSC = 0.945). Well documented areas include the training approach (12 studies) and model description (all). Only two studies performed external validation, and two assessed inter- and intra-rater variability.

No studies reported sample size determination and handing of missing data. Small vascular structures consistently underperformed compared to whole heart segmentation.</p> <p>Conclusion</p><p>Deep learning models show strong potential for CHD CT segmentation but remain limited by small datasets, inconsistent reporting and lack of clinical evaluation. Advancing this field requires multidisciplinary collaboration, standardised reporting, and integration of clinical co- design.

As the first comprehensive review in this area, we provide a strong baseline for evaluating future studies.</p></div>