Anatomical variability of organs via principal factor analysis from the construction of an abdominal probabilistic atlas

Abstract

Extensive recent work has taken place on the construction of probabilistic atlases of anatomical organ. We propose a probabilistic atlas of ten major abdominal organs which retains structural variability by using a size-preserving affine registration, and normalizes the physical organ locations to an anatomical landmark. Restricting the degrees of freedom in the transformation, the bias from the reference data is minimized, in terms of organ shape, size and position. Additionally, we present a scheme for the study of anatomical variability within the abdomen, including the clusterization of the modes of variation. The analysis of deformation fields showed a strong correlation with anatomical landmarks and known mechanical deformations in the abdomen. The atlas and its dependencies represent a potentially important research tool for abdominal diagnosis, modeling and soft tissue interventions.

Automatic multi-resolution shape modeling of multi-organ structures

“…According to the original works presented by Reyes et al (2009, 2010), the analysis of deformation fields showed correlation with existing anatomical landmarks and known anatomical deformations of abdominal organs. The subdivision of organs into anatomically significant components defined by clusters may be of great utility in the study and analysis of the anatomical variability of organs and inter-organs relations, an important research tool for diagnosis, modeling, and soft tissue intervention.…”

“…In this section we introduce a new landmark clustering approach that allows us to automatically define the division of landmarks into separate clusters at each resolution. The clustering process was initially inspired by the work presented by Roy et al (2006), which was originally conducted for vector field segmentation of moving objects in 2D videos, and extended to 3D objects by Reyes et al (2009) to study the anatomical variability of single organs via principal factor analysis. Here we propose a more general approach based on the agglomerative hierarchical clustering method presented by Ward (1963).…”

Toward a Common Coordinate Framework for the Human Body

“…Similar efforts have been applied across abdominal tissues (Reyes et al, 2009), multiple brain regions (Mazziotta et al, 2001;Habas et al, 2010;Pauli et al, 2018), and the lung (Hame et al, 2014;Yang et al, 2017). However, the examination of different measures of variability for current human atlas efforts provides an opportunity to relate morphological and molecular variation.…”

Improved Semantic Segmentation of Tuberculosis—Consistent Findings in Chest X-rays Using Augmented Training of Modality-Specific U-Net Models with Weak Localizations

“…It is a difficult task considering a high degree of variability in medical image quality to include penetration and positioning [ 2 ]. To overcome such variety, typical approaches in medical image segmentation develop solutions that are specific to the medical imaging modality, body part, or disease being studied [ 3 ]. This results in the limited direct use of segmentation models commonly trained on natural images for medical image segmentation [ 4 ].…”