Localisation of the subthalamic nucleus in MRI via convolutional neural networks for deep brain stimulation planning

Baxter, Jamie; Maguet, Enora; Jannin, Pierre

doi:10.1117/12.2548420

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method uses a deep convolutional neural network inspired by multiresolution architectures such as U-Nets [15] expanding on our previous work in localising points in volumetric images for the purpose of small region segmentation. [3] This work compared a traditional neural network approach for localising a single point, treated as an image-to-vector regression problem, with an earlier multi-resolution approach, motivating our network structure. The network architecture is shown in Figure 1.…”

Section: Multi-resolution Convolutional Neural Network Architecturementioning

confidence: 99%

Automatic cortical target point localisation in MRI for transcranial magnetic stimulation via a multi-resolution convolutional neural network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Transcranial Magnetic Stimulation (TMS) is a growing therapy for a variety of psychiatric and neurological disorders that arise from or are modulated by cortical regions of the brain represented by singular 3D target points. These target points are often determined manually with assistance from a pre-operative T1-weighted MRI, although there is growing interest in automatic target point localisation using an atlas. However, both approaches can be time-consuming which has an effect on the clinical workflow and the latter does not take into account patient variability such as the varying number of cortical gyri where these targets are located. Methods: This paper proposes a multi-resolution convolutional neural network for point localisation in MR images for a priori defined points in increasingly finely resolved versions of the input image. This approach is both fast and highly memory efficient, allowing it to run in high-throughput centres, and has the capability of distinguishing between patients with high levels of anatomical variability. Results: Preliminary experiments have found the accuracy of this network to be 7.26 ± 5.30 mm, compared to 9.39 ± 4.63 mm for deformable registration and 6.94 ± 5.10 mm for a human expert. For most treatment points, the human expert and proposed CNN statistically significantly outperform registration, but neither statistically significantly outperforms the other, suggesting that the proposed network has human-level performance. Conclusions: The

show abstract

Section: Multi-resolution Convolutional Neural Network Architecturementioning

confidence: 99%