PT  - JOURNAL ARTICLE
AU  - Pennig, L.
AU  - Shahzad, R.
AU  - Caldeira, L.
AU  - Lennartz, S.
AU  - Thiele, F.
AU  - Goertz, L.
AU  - Zopfs, D.
AU  - Meißner, A.-K.
AU  - Fürtjes, G.
AU  - Perkuhn, M.
AU  - Kabbasch, C.
AU  - Grau, S.
AU  - Borggrefe, J.
AU  - Laukamp, K.R.
TI  - Automated Detection and Segmentation of Brain Metastases in Malignant Melanoma: Evaluation of a Dedicated Deep Learning Model
AID  - 10.3174/ajnr.A6982
DP  - 2021 Apr 01
TA  - American Journal of Neuroradiology
PG  - 655--662
VI  - 42
IP  - 4
4099  - http://www.ajnr.org/content/42/4/655.short
4100  - http://www.ajnr.org/content/42/4/655.full
SO  - Am. J. Neuroradiol.2021 Apr 01; 42
AB  - BACKGROUND AND PURPOSE: Malignant melanoma is an aggressive skin cancer in which brain metastases are common. Our aim was to establish and evaluate a deep learning model for fully automated detection and segmentation of brain metastases in patients with malignant melanoma using clinical routine MR imaging.MATERIALS AND METHODS: Sixty-nine patients with melanoma with a total of 135 brain metastases at initial diagnosis and available multiparametric MR imaging datasets (T1-/T2-weighted, T1-weighted gadolinium contrast-enhanced, FLAIR) were included. A previously established deep learning model architecture (3D convolutional neural network; DeepMedic) simultaneously operating on the aforementioned MR images was trained on a cohort of 55 patients with 103 metastases using 5-fold cross-validation. The efficacy of the deep learning model was evaluated using an independent test set consisting of 14 patients with 32 metastases. Manual segmentations of metastases in a voxelwise manner (T1-weighted gadolinium contrast-enhanced imaging) performed by 2 radiologists in consensus served as the ground truth.RESULTS: After training, the deep learning model detected 28 of 32 brain metastases (mean volume, 1.0 [SD, 2.4] cm3) in the test cohort correctly (sensitivity of 88%), while false-positive findings of 0.71 per scan were observed. Compared with the ground truth, automated segmentations achieved a median Dice similarity coefficient of 0.75.CONCLUSIONS: Deep learning–based automated detection and segmentation of brain metastases in malignant melanoma yields high detection and segmentation accuracy with false-positive findings of <1 per scan.CNNconvolutional neural networkDLMdeep learning modelGTground truth