Deep learning segmentation results in precise delineation of the putamen in multiple system atrophy

Abstract

Objectives The precise segmentation of atrophic structures remains challenging in neurodegenerative diseases. We determined the performance of a Deep Neural Patchwork (DNP) in comparison to established segmentation algorithms regarding the ability to delineate the putamen in multiple system atrophy (MSA), Parkinson’s disease (PD), and healthy controls. Methods We retrospectively included patients with MSA and PD as well as healthy controls. A DNP was trained on manual segmentations of the putamen as ground truth. For this, the cohort was randomly split into a training (N = 131) and test set (N = 120). The DNP’s performance was compared with putaminal segmentations as derived by Automatic Anatomic Labelling, Freesurfer and Fastsurfer. For validation, we assessed the diagnostic accuracy of the resulting segmentations in the delineation of MSA vs. PD and healthy controls. Results A total of 251 subjects (61 patients with MSA, 158 patients with PD, and 32 healthy controls; mean age of 61.5 ± 8.8 years) were included. Compared to the dice-coefficient of the DNP (0.96), we noted significantly weaker performance for AAL3 (0.72; p < .001), Freesurfer (0.82; p < .001), and Fastsurfer (0.84, p < .001). This was corroborated by the superior diagnostic performance of MSA vs. PD and HC of the DNP (AUC 0.93) versus the AUC of 0.88 for AAL3 (p = 0.02), 0.86 for Freesurfer (p = 0.048), and 0.85 for Fastsurfer (p = 0.04). Conclusion By utilization of a DNP, accurate segmentations of the putamen can be obtained even if substantial atrophy is present. This allows for more precise extraction of imaging parameters or shape features from the putamen in relevant patient cohorts. Clinical relevance statement Deep learning-based segmentation of the putamen was superior to currently available algorithms and is beneficial for the diagnosis of multiple system atrophy. Key Points • A Deep Neural Patchwork precisely delineates the putamen and performs equal to human labeling in multiple system atrophy, even when pronounced putaminal volume loss is present. • The Deep Neural Patchwork–based segmentation was more capable to differentiate between multiple system atrophy and Parkinson’s disease than the AAL3 atlas, Freesurfer, or Fastsurfer.

3D-CAM: a novel context-aware feature extraction framework for neurological disease classification

“…Some researchers have attempted to diagnose PD and MSA through deep learning methods, such as Huseyn (2020) and Rau et al (2023) . Among them, Huseyn (2020) proposed an innovative deep learning model, achieving an accuracy of about 88% in the classification task of PD and MSA, slightly higher than our proposed model’s accuracy of 85.71%.…”

“…For example, Huseyn (2020) utilized Magnetic Resonance Imaging (MRI) with an improved AlexNet network structure to diagnose Parkinson’s disease, multiple system atrophy, and healthy individuals. Rau et al (2023) proposed a deep learning algorithm capable of precisely segmenting the nucleus and shell, applying it to the diagnosis of PD and MSA. Compared to the aforementioned machine learning algorithms, although the features extracted by these methods are no longer limited to a fixed set of features, they still need to rely on manually selecting key feature slices and segmenting regions of interest, which does not allow for fully automated classification and diagnosis of diseases.…”

Accuracy of automated segmentation and volumetry of acute intracerebral hemorrhage following minimally invasive surgery using a patch-based convolutional neural network in a small dataset

“…However, these studies required large datasets of 300, 600 and 1732 scans respectively [ 9 – 11 ]. In contrast, hierarchical, patch-based CNN architectures, trained on smaller datasets, enable segmentation in large 3D images, exhibiting encouraging results in complex segmentation tasks [ 12 – 14 ].…”