Feature-fusion improves MRI single-shot deep learning detection of small brain metastases

BACKGROUND AND PURPOSE

To examine whether feature-fusion (FF) method improves single-shot detector's (SSD's) detection of small brain metastases on contrast-enhanced (CE) T1-weighted MRI.

METHODS

The study included 234 MRI scans from 234 patients (64.3 years±12.0; 126 men). The ground-truth annotation was performed semiautomatically. SSDs with and without an FF module were developed and trained using 178 scans. The detection performance was evaluated at the SSDs' 50% confidence threshold using sensitivity, positive-predictive value (PPV), and the false-positive (FP) per scan with the remaining 56 scans.

RESULTS

FF-SSD achieved an overall sensitivity of 86.0% (95% confidence interval [CI]: [83.0%, 85.6%]; 196/228) and 46.8% PPV (95% CI: [42.0%, 46.3%]; 196/434), with 4.3 FP (95% CI: [4.3, 4.9]). Lesions smaller than 3 mm had 45.8% sensitivity (95% CI: [36.1%, 45.5%]; 22/48) with 2.0 FP (95% CI: [1.9, 2.1]). Lesions measuring 3-6 mm had 92.3% sensitivity (95% CI: [86.5%, 92.0%]; 48/52) with 1.8 FP (95% CI: [1.7, 2.2]). Lesions larger than 6 mm had 98.4% sensitivity (95% CI: [97.8%, 99.4%]; 126/128) 0.5 FP (95% CI: [0.5, 0.8]) per scan. FF-SSD had a significantly higher sensitivity for lesions < 3 mm (p = 0.008, t = 3.53) than the baseline SSD, while the overall PPV was similar (p = 0.06, t = -2.16). A similar trend was observed even when the detector's confidence threshold was varied as low as 0.2, for which the FF-SSD's sensitivity was 91.2% and the FP was 9.5.

CONCLUSIONS

The FF-SSD algorithm identified brain metastases on CE T1-weighted MRI with high accuracy.

Intelligent Image-Based Railway Inspection System Using Deep Learning-Based Object Detection and Weber Contrast-Based Image Comparison

For sustainable operation and maintenance of urban railway infrastructure, intelligent visual inspection of the railway infrastructure attracts increasing attention to avoid unreliable, manual observation by humans at night, while trains do not operate. Although various automatic approaches were proposed using image processing and computer vision techniques, most of them are focused only on railway tracks. In this paper, we present a novel railway inspection system using facility detection based on deep convolutional neural network and computer vision-based image comparison approach. The proposed system aims to automatically detect wears and cracks by comparing a pair of corresponding image sets acquired at different times. We installed line scan camera on the roof of the train. Unlike an area-based camera, the line scan camera quickly acquires images with a wide field of view. The proposed system consists of three main modules: (i) image reconstruction for registration of facility positions, (ii) facility detection using an improved single shot detector, and (iii) deformed region detection using image processing and computer vision techniques. In experiments, we demonstrate that the proposed system accurately finds facilities and detects their potential defects. For that reason, the proposed system can provide various advantages such as cost reduction for maintenance and accident prevention.