Large-scale automatic reconstruction of neuronal processes from electron microscopy images.
Med Image Anal
; 22(1): 77-88, 2015 May.
Article
en En
| MEDLINE
| ID: mdl-25791436
ABSTRACT
Automated sample preparation and electron microscopy enables acquisition of very large image data sets. These technical advances are of special importance to the field of neuroanatomy, as 3D reconstructions of neuronal processes at the nm scale can provide new insight into the fine grained structure of the brain. Segmentation of large-scale electron microscopy data is the main bottleneck in the analysis of these data sets. In this paper we present a pipeline that provides state-of-the art reconstruction performance while scaling to data sets in the GB-TB range. First, we train a random forest classifier on interactive sparse user annotations. The classifier output is combined with an anisotropic smoothing prior in a Conditional Random Field framework to generate multiple segmentation hypotheses per image. These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion. We provide qualitative and quantitative evaluation of the automatic segmentation and demonstrate large-scale 3D reconstructions of neuronal processes from a 27,000 µm(3) volume of brain tissue over a cube of 30 µm in each dimension corresponding to 1000 consecutive image sections. We also introduce Mojo, a proofreading tool including semi-automated correction of merge errors based on sparse user scribbles.
Palabras clave
Texto completo:
1
Base de datos:
MEDLINE
Asunto principal:
Encéfalo
/
Reconocimiento de Normas Patrones Automatizadas
/
Microscopía Electrónica
/
Interpretación de Imagen Asistida por Computador
/
Imagenología Tridimensional
/
Neuronas
Tipo de estudio:
Diagnostic_studies
/
Qualitative_research
Idioma:
En
Revista:
Med Image Anal
Asunto de la revista:
DIAGNOSTICO POR IMAGEM
Año:
2015
Tipo del documento:
Article