Clinical validation pipeline of a deep learning model for segmenting and quantifying intracranial and ventricular volumes on computed tomography.

The field of radiology is experiencing a surge in demand due to advances in medical imaging, particularly in techniques such as magnetic resonance imaging and computed tomography (CT). However, the interpretation of these scans relies heavily on the availability of experts, which is challenging in resource-limited regions. Recent advances in artificial intelligence and deep learning offer promising solutions by assisting radiologists in image interpretation and diagnosis. This study focuses on validating DeepCTE3D (Deep Convolutional Neural Network for Computed Tomography Extraction 3D), a deep learning-based model based on 3D architecture for segmenting and quantifying intracranial volume (ICV) and lateral ventricular volume (LVV) in CT scans. The model's performance was evaluated using a real-world dataset comprising diverse patient demographics and various scanner models, including normal and pathological scans. The evaluation process involved developing a streamlined pipeline to generate ground-truth results and comparing them to the model's outputs. DeepCTE3D achieved high similarity scores for both ICV and LVV. Secondary analyses revealed differences in LVV and ICV between patient sexes and scanner models, although these differences were not clinically significant. This study highlights the potential of DeepCTE3D in enhancing clinical triage and advancing neuroimaging applications, especially in scenarios where MRI is not feasible.