Fully automated segmentation of substantia nigra toward longitudinal analysis of Parkinson’s disease - Takeaways - MDSpire

Fully automated segmentation of substantia nigra toward longitudinal analysis of Parkinson’s disease

  • By

  • Tao Hu

  • Hayato Itoh

  • Masahiro Oda

  • Shinji Saiki

  • Koji Kamagata

  • Kei-ichi Ishikawa

  • Wataru Sako

  • Nobutaka Hattori

  • Shigeki Aoki

  • Kensaku Mori

  • October 6, 2025

  • 0 min

Share

  • 1

    Parkinson's disease affects 4 million people today, projected to reach 9.3 million in the next decade, emphasizing the need for early diagnosis and treatment.

  • 2

    The substantia nigra experiences significant dopaminergic neuron loss, making its accurate segmentation from MRI crucial for understanding Parkinson's disease.

  • 3

    Current segmentation methods for the substantia nigra are often semi-automated or require manual input, highlighting the need for fully automated solutions.

  • 4

    The proposed single-stage fully convolutional network (FCN) improves segmentation accuracy and reduces computational complexity compared to existing methods.

  • 5

    The new segmentation pipeline demonstrates competitive performance in identifying Parkinson's disease, aligning closely with physician assessments.

Original Source(s)

Fully automated segmentation of substantia nigra toward longitudinal analysis of Parkinson’s disease

  • by Tao Hu, Hayato Itoh, Masahiro Oda, Shinji Saiki, Koji Kamagata, Kei-ichi Ishikawa, Wataru Sako, Nobutaka Hattori, Shigeki Aoki, Kensaku Mori

  • October 6, 2025

Related Content

Hypothalamus and intracranial volume segmentation at the group level by use of a Gradio-CNN framework

IJCARS: BVM 2021 special issue

Utility of diffusion tensor imaging and generalized q-sampling imaging for predicting short-term clinical effect of deep brain stimulation in Parkinson’s disease