Abstract
Background
Errors have seldom been evaluated in computer-aided detection on brain metastases. This study aimed to analyze false negatives (FNs) and false positives (FPs) generated by a brain metastasis detection system (BMDS) and by readers.
Methods
A deep learning-based BMDS was developed and prospectively validated in a multicenter, multireader study. Ad hoc secondary analysis was restricted to the prospective participants (148 with 1,066 brain metastases and 152 normal controls). Three trainees and three experienced radiologists read the MRI images without and with the BMDS. The number of FNs and FPs per patient, jackknife alternative free-response receiver operating characteristic figure of merit (FOM), and lesion features associated with FNs were analyzed for the BMDS and readers using binary logistic regression.
Results
The FNs, FPs, and the FOM of the stand-alone BMDS were 0.49, 0.38, and 0.97, respectively. Com pared with independent reading, BMDS-assisted reading generated 79% fewer FNs (1.98 vs. 0.42,
P <0.001); 41% more FPs (0.17 vs. 0.24,
P <0.001) but 125% more FPs for trainees (
P <0.001); and higher FOM (0.87 vs. 0.98,
P <0.001). Lesions with small size, greater number, irregular shape, lower signal intensity, and located on non-brain surface were associated with FNs for readers. Small, irregular, and necrotic lesions were more frequently found in FNs for BMDS. The FPs mainly resulted from small blood vessels for the BMDS and the readers.
Conclusions
Despite the improvement detection performance, attention should be paid to FPs and small lesions with lower enhancement for radiologists, especially for less-experienced radiologists.
