Quantifying axonal features of human superficial white matter from three-dimensional multibeam serial electron microscopy data assisted by deep learning
Qiyuan Tian, Chanon Ngamsombat, Hong‐Hsi Lee, Daniel R. Berger, Yuelong Wu, Qiuyun Fan, Berkin Bilgic̦, Ziyu Li, Dmitry S. Novikov, Els Fieremans, Bruce R. Rosen, Jeff W. Lichtman, Susie Y. Huang
Abstract
• Large, high-resolution 3D EM data of human superficial white matter was segmented. • Segmentation results using deep learning were highly accurate. • 128,285 myelinated axons were delineated, with 2102 longer than 100 μm. • Local variations in diameter (beading) and direction (undulation) were observed. • Axons had inner diameters ∼0.5 µm, outer diameters ∼1 µm, and g-ratios ∼0.5. Short-range association fibers located in the superficial white matter play an important role in mediating higher-order cognitive function in humans. Detailed morphological characterization of short-range association fibers at the microscopic level promises to yield important insights into the axonal features driving cortico-cortical connectivity in the human brain yet has been difficult to achieve to date due to the challenges of imaging at nanometer-scale resolution over large tissue volumes. This work presents results from multi-beam scanning electron microscopy (EM) data acquired at 4 × 4 × 33 nm 3 resolution in a volume of human superficial white matter measuring 200 × 200 × 112 μm 3 , leveraging automated analysis methods. Myelin and myelinated axons were automatically segmented using deep convolutional neural networks (CNNs), assisted by transfer learning and dropout regularization techniques. A total of 128,285 myelinated axons were segmented, of which 70,321 and 2102 were longer than 10 and 100 μm, respectively. Marked local variations in diameter (i.e., beading) and direction (i.e., undulation) were observed along the length of individual axons. Myelinated axons longer than 10 μm had inner diameters around 0.5 µm, outer diameters around 1 µm, and g-ratios around 0.5. This work fills a gap in knowledge of axonal morphometry in the superficial white matter and provides a large 3D human EM dataset and accurate segmentation results for a variety of future studies in different fields.