Fully automatic 3D reconstruction of histological images

  title={Fully automatic 3D reconstruction of histological images},
  author={Ulas Bagci and Li Bai},
  journal={2008 IEEE 16th Signal Processing, Communication and Applications Conference},
  • U. Bagci, L. Bai
  • Published 14 May 2008
  • Computer Science
  • 2008 IEEE 16th Signal Processing, Communication and Applications Conference
A computational framework for 3D volume reconstruction from 2D histological slices using registration algorithms in feature space is proposed. To improve the quality of reconstructed 3D volume, first, intensity variations in images are corrected by an intensity standardization process which maps image intensity scale to a standard scale where similar intensities correspond to similar tissues. Second, a subvolume approach is proposed for 3D reconstruction by dividing standardized slices into… 
Kohonen SOM for Image Slides Sequencing
A modified SOM Kohonen networks with open chain topology is proposed for true sequence estimation based on based on 2-D image features invariant to section image translation and rotation, but sensitive to a scale of an object on the slide.
Cellular mechanisms of morphogenesis in palate development
This paper aims to provide a chronology of the events leading up to and including the publication of this book and some of the key events that led to its publication.


Registration of standardized histological images in feature space
  • U. Bagci, L. Bai
  • Computer Science, Engineering
    SPIE Medical Imaging
  • 2008
An automatic best reference slice selection algorithm is proposed that improves reconstruction quality based on both image entropy and mean square error of the registration process and demonstrates that the choice of reference slice has a significant impact on registration error, standardization, feature space and entropy information.
Reconstructing a 3D structure from serial histological sections
The method is based on a block-matching strategy that allows us to compute local displacements between the sections and can reach sub-pixel accuracy, and some results are shown of aligning histological sections from a rat's brain and a rhesus monkey's brain.
3D volume reconstruction of a mouse brain from histological sections using warp filtering
A novel image warping algorithm based on dynamic programming that extends Dynamic Time Warping in 1D speech recognition to compute pairwise warps between high-resolution 2D images that efficiently computes a restricted class of 2D local deformations that are characteristic between successive tissue sections.
Fusion of autoradiographs with an MR volume using 2-D and 3-D linear transformations
This work aims to fuse post-mortem autoradiographic data with a pre-mortem anatomical MR image, and demonstrates that this fusion can be achieved by using only simple global transformations (rigid and/or affine, 2-D and 3-D), while yielding very satisfactory results.
Numerical tissue characterization in MS via standardization of the MR image intensity scale
Numerical tissue characterizability of different tissues in MS achieved by standardization offers a fixed tissue‐specific meaning for the numerical values and can significantly facilitate image segmentation and analysis.
Multiresolution Elastic Medical Image Registration in Standard Intensity Scale
  • U. Bagci, L. Bai
  • Computer Science
    XX Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2007)
  • 2007
A new multiresolution elastic image registration method is described that transforms image intensities into a standard intensity scale, which allows highly accurate registration of medical images.
Elastic registration in the presence of intensity variations
A general-purpose registration algorithm for medical images and volumes that models the transformation between images as locally affine but globally smooth, and is highly effective across a broad range of synthetic and clinical medical images.
Advances in elastic matching theory and its implementation
These developments in atlas-based localization of neuroanatomy has progressed toward statistical approaches that subsume the original elastic matching while retaining its practical flavor are reviewed and methods on MRI data are demonstrated, including the computation of interval estimates.
Hardware-Assisted Point-Based Volume Rendering of Tetrahedral Meshes
This paper presents a novel method of approximating these irregular elements with point-based primitives amenable to existing hardware acceleration techniques, and uses a well-known quantitative metric to analyze the image quality achieved by the final rendering.
Affine Registration with Feature Space Mutual Information
This paper introduces two important issues of image registration: the very general definition of mutual information that allows the choice of various feature spaces to perform image registration and the problem of finding the global maximum in an arbitrary feature space.