Miguel Monteiro, MSc, Virginia F J Newcombe, PhD, Francois Mathieu, MD, Krishma Adatia, MD, Konstantinos Kamnitsas, PhD, Enzo Ferrante, PhD, Tilak Das, PhD, Daniel Whitehouse, MD, Prof Daniel Rueckert, PhD, Prof David K Menon, PhD, Ben Glocker, PhD (2020). Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study The Lancet, 14 May 2020. DOI:https://doi.org/10.1016/S2589-7500(20)30085-6
Background:
CT is the most common imaging modality in traumatic brain injury (TBI). However, its conventional use requires expert clinical interpretation and does not provide detailed quantitative outputs, which may have prognostic importance. We aimed to use deep learning to reliably and efficiently quantify and detect different lesion types.
Methods:
Patients were recruited between Dec 9, 2014, and Dec 17, 2017, in 60 centres across Europe. We trained and validated an initial convolutional neural network (CNN) on expert manual segmentations (dataset 1). This CNN was used to automatically segment a new dataset of scans, which we then corrected manually (dataset 2). From this dataset, we used a subset of scans to train a final CNN for multiclass, voxel-wise segmentation of lesion types. The performance of this CNN was evaluated on a test subset. Performance was measured for lesion volume quantification, lesion progression, and lesion detection and lesion volume classification. For lesion detection, external validation was done on an independent set of 500 patients from India.
Findings:
After the two baseline surveys, we followed up random subsets of 1213–1736 adults at each timepoint. Probable depression was 98 scans from one centre were included in dataset 1. Dataset 2 comprised 839 scans from 38 centres: 184 scans were used in the training subset and 655 in the test subset. Compared with manual reference, CNN-derived lesion volumes showed a mean difference of 0·86 mL (95% CI −5·23 to 6·94) for intraparenchymal haemorrhage, 1·83 mL (−12·01 to 15·66) for extra-axial haemorrhage, 2·09 mL (−9·38 to 13·56) for perilesional oedema, and 0·07 mL (−1·00 to 1·13) for intraventricular haemorrhage.
Interpretation:
We show the ability of a CNN to separately segment, quantify, and detect multiclass haemorrhagic lesions and perilesional oedema. These volumetric lesion estimates allow clinically relevant quantification of lesion burden and progression, with potential applications for personalised treatment strategies and clinical research in TBI.