Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors

Abstract

Purpose: Despite the potential usefulness, no automatic detector is available for brain metastases on contrast-enhanced CT (CECT). The study aims to develop and investigate deep learning-based detectors for brain metastases detection on CECT.

Method: The study included 127 CECTs from 127 patients (65.5 years±11.1; 87 men). The ground-truth annotation was performed semi-automatically by applying connected-component analysis to the binarized dataset by three radiologists. Single-shot detector (SSD) algorithms, with and without a feature-fusion module, were developed and trained using 97 scans. The performance was evaluated at the detector's 50 % confidence threshold with the remaining 30 scans using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR).

Results: Feature-fused SSD achieved an overall sensitivity of 88.1 % (95 % confidence interval [CI]: [85.2 %,88.6 %]; 214/243) and PPV of 36.0 % (95 % CI: [33.7 %,37.1 %]; 233/648), with 13.8 FPR (95 % CI: [12.7,15.0]). Lesions < 3 mm had a sensitivity of 23.1 % (95 % CI: [21.2 %,40.0 %]; 3/13), with 0.2 FPR (95 % CI: [0.23,0.65]). Lesions measuring 3-6 mm had a sensitivity of 80.0 % (95 % CI: [76.0 %,79.8 %]); 60/75) with 5.8 FPR (95 % CI: [5.0,6.2]). Lesions > 6 mm had a sensitivity of 97.4 % (95 % CI: [94.1 %,97.4 %]); 151/155) with 7.9 FPR (95 % CI: [7.2,8.5]). Feature-fused SSD had a significantly higher overall sensitivity (p = 0.03, t = 2.75) or sensitivity for lesions < 3 mm (p = 0.002, t = 4.49) than baseline SSD, while the overall PPV was similar (p = 0.96, t = -0.02).

Conclusions: The SSD algorithm identified brain metastases on CECT with reasonable accuracy for lesions > 3 mm without pre/post-processing.

Keywords: Brain tumors; Computed tomography; Deep learning.