2.5D and 3D segmentation of brain metastases with deep learning on multinational MRI data.

Autor:	Ottesen JA; CRAI, Division of Radiology and Nuclear Medicine, Department of Physics and Computational Radiology, Oslo University Hospital, Oslo, Norway.; Department of Physics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway., Yi D; Department of Ophthalmology, University of Illinois, Chicago, IL, United States., Tong E; Department of Radiology, Stanford University, Stanford, CA, United States., Iv M; Department of Radiology, Stanford University, Stanford, CA, United States., Latysheva A; Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway., Saxhaug C; Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway., Jacobsen KD; Department of Oncology, Oslo University Hospital, Oslo, Norway., Helland Å; Department of Oncology, Oslo University Hospital, Oslo, Norway., Emblem KE; Division of Radiology and Nuclear Medicine, Department of Physics and Computational Radiology, Oslo University Hospital, Oslo, Norway., Rubin DL; Department of Biomedical Data Science, Stanford University, Stanford, CA, United States., Bjørnerud A; CRAI, Division of Radiology and Nuclear Medicine, Department of Physics and Computational Radiology, Oslo University Hospital, Oslo, Norway.; Department of Physics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway., Zaharchuk G; Department of Radiology, Stanford University, Stanford, CA, United States., Grøvik E; Department of Radiology, Ålesund Hospital, Møre og Romsdal Hospital Trust, Ålesund, Norway.; Department of Physics, Norwegian University of Science and Technology, Trondheim, Norway.
Jazyk:	angličtina
Zdroj:	Frontiers in neuroinformatics [Front Neuroinform] 2023 Jan 18; Vol. 16, pp. 1056068. Date of Electronic Publication: 2023 Jan 18 (Print Publication: 2022).
DOI:	10.3389/fninf.2022.1056068
Abstrakt:	Introduction: Management of patients with brain metastases is often based on manual lesion detection and segmentation by an expert reader. This is a time- and labor-intensive process, and to that end, this work proposes an end-to-end deep learning segmentation network for a varying number of available MRI available sequences. Methods: We adapt and evaluate a 2.5D and a 3D convolution neural network trained and tested on a retrospective multinational study from two independent centers, in addition, nnU-Net was adapted as a comparative benchmark. Segmentation and detection performance was evaluated by: (1) the dice similarity coefficient, (2) a per-metastases and the average detection sensitivity, and (3) the number of false positives. Results: The 2.5D and 3D models achieved similar results, albeit the 2.5D model had better detection rate, whereas the 3D model had fewer false positive predictions, and nnU-Net had fewest false positives, but with the lowest detection rate. On MRI data from center 1, the 2.5D, 3D, and nnU-Net detected 79%, 71%, and 65% of all metastases; had an average per patient sensitivity of 0.88, 0.84, and 0.76; and had on average 6.2, 3.2, and 1.7 false positive predictions per patient, respectively. For center 2, the 2.5D, 3D, and nnU-Net detected 88%, 86%, and 78% of all metastases; had an average per patient sensitivity of 0.92, 0.91, and 0.85; and had on average 1.0, 0.4, and 0.1 false positive predictions per patient, respectively. Discussion/conclusion: Our results show that deep learning can yield highly accurate segmentations of brain metastases with few false positives in multinational data, but the accuracy degrades for metastases with an area smaller than 0.4 cm 2 . Competing Interests: EG and KE have intellectual property rights at NordicNeuroLab AS, Bergen, Norway. AB is shareholder in NordicNeuroLab AS, Bergen, Norway. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2023 Ottesen, Yi, Tong, Iv, Latysheva, Saxhaug, Jacobsen, Helland, Emblem, Rubin, Bjørnerud, Zaharchuk and Grøvik.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu