Sammendrag
Purpose: Automatic and consistent meningioma segmentation in T1-weighted magnetic resonance (MR) imaging volumes and corresponding volumetric assessment is of use for diagnosis, treatment planning, and tumor growth evaluation. We optimized the segmentation and processing speed performances using a large number of both surgically treated meningiomas and untreated meningiomas followed at the outpatient clinic.
Approach: We studied two different three-dimensional (3D) neural network architectures: (i) a simple encoder-decoder similar to a 3D U-Net, and (ii) a lightweight multi-scale architecture [Pulmonary Lobe Segmentation Network (PLS-Net)]. In addition, we studied the impact of different training schemes. For the validation studies, we used 698 T1-weighted MR volumes from St. Olav University Hospital, Trondheim, Norway. The models were evaluated in terms of detection accuracy, segmentation accuracy, and training/inference speed.
Results: While both architectures reached a similar Dice score of 70% on average, the PLS-Net was more accurate with an F1-score of up to 88%. The highest accuracy was achieved for the largest meningiomas. Speed-wise, the PLS-Net architecture tended to converge in about 50 h while 130 h were necessary for U-Net. Inference with PLS-Net takes less than a second on GPU and about 15 s on CPU.
Conclusions: Overall, with the use of mixed precision training, it was possible to train competitive segmentation models in a relatively short amount of time using the lightweight PLS-Net architecture. In the future, the focus should be brought toward the segmentation of small meningiomas (<2 ml) to improve clinical relevance for automatic and early diagnosis and speed of growth estimates.
Approach: We studied two different three-dimensional (3D) neural network architectures: (i) a simple encoder-decoder similar to a 3D U-Net, and (ii) a lightweight multi-scale architecture [Pulmonary Lobe Segmentation Network (PLS-Net)]. In addition, we studied the impact of different training schemes. For the validation studies, we used 698 T1-weighted MR volumes from St. Olav University Hospital, Trondheim, Norway. The models were evaluated in terms of detection accuracy, segmentation accuracy, and training/inference speed.
Results: While both architectures reached a similar Dice score of 70% on average, the PLS-Net was more accurate with an F1-score of up to 88%. The highest accuracy was achieved for the largest meningiomas. Speed-wise, the PLS-Net architecture tended to converge in about 50 h while 130 h were necessary for U-Net. Inference with PLS-Net takes less than a second on GPU and about 15 s on CPU.
Conclusions: Overall, with the use of mixed precision training, it was possible to train competitive segmentation models in a relatively short amount of time using the lightweight PLS-Net architecture. In the future, the focus should be brought toward the segmentation of small meningiomas (<2 ml) to improve clinical relevance for automatic and early diagnosis and speed of growth estimates.