A Marked Poisson Process Driven Latent Shape Model for 3D Segmentation of Reflectance Confocal Microscopy Image Stacks of Human Skin

Segmenting objects of interest from 3D data sets is a common problem encountered in biological data. Small field of view and intrinsic biological variability combined with optically subtle changes of intensity, resolution, and low contrast in images make the task of segmentation difficult, especially for microscopy of unstained living or freshly excised thick tissues. Incorporating shape information in addition to the appearance of the object of interest can often help improve segmentation performance. However, the shapes of objects in tissue can be highly variable and design of a flexible shape model that encompasses these variations is challenging. To address such complex segmentation problems, we propose a unified probabilistic framework that can incorporate the uncertainty associated with complex shapes, variable appearance, and unknown locations. The driving application that inspired the development of this framework is a biologically important segmentation problem: the task of automatically detecting and segmenting the dermal-epidermal junction (DEJ) in 3D reflectance confocal microscopy (RCM) images of human skin. RCM imaging allows noninvasive observation of cellular, nuclear, and morphological detail. The DEJ is an important morphological feature as it is where disorder, disease, and cancer usually start. Detecting the DEJ is challenging, because it is a 2D surface in a 3D volume which has strong but highly variable number of irregularly spaced and variably shaped “peaks and valleys.” In addition, RCM imaging resolution, contrast, and intensity vary with depth. Thus, a prior model needs to incorporate the intrinsic structure while allowing variability in essentially all its parameters. We propose a model which can incorporate objects of interest with complex shapes and variable appearance in an unsupervised setting by utilizing domain knowledge to build appropriate priors of the model. Our novel strategy to model this structure combines a spatial Poisson process with shape priors and performs inference using Gibbs sampling. Experimental results show that the proposed unsupervised model is able to automatically detect the DEJ with physiologically relevant accuracy in the range 10-20 μm.

[1]  R. Burgeson,et al.  The dermal-epidermal junction. , 1997, Current opinion in cell biology.

[2]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[3]  Alessandro Sarti,et al.  A geometric model for 3D confocal microscope image analysis , 1998 .

[4]  D. Pinkel,et al.  Segmentation of confocal microscope images of cell nuclei in thick tissue sections , 1999, Journal of microscopy.

[5]  Radford M. Neal Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[6]  Alessandro Sarti,et al.  A geometric model for 3-D confocal image analysis , 1998, IEEE Transactions on Biomedical Engineering.

[7]  S. González,et al.  Sensitivity and specificity of reflectance-mode confocal microscopy for in vivo diagnosis of basal cell carcinoma: a multicenter study. , 2004, Journal of the American Academy of Dermatology.

[8]  Adrian Baddeley,et al.  Spatial Point Processes and their Applications , 2007 .

[9]  W. Coleman,et al.  Fitzpatrickʼs Dermatology in General Medicine , 2008 .

[10]  Xue-Cheng Tai,et al.  A study on continuous max-flow and min-cut approaches , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  David Weedon,et al.  Lentigines, nevi, and melanomas , 2010 .

[12]  David Vere-Jones,et al.  Point Processes , 2011, International Encyclopedia of Statistical Science.

[13]  Jennifer G. Dy,et al.  Pilot study of semiautomated localization of the dermal/epidermal junction in reflectance confocal microscopy images of skin. , 2011, Journal of biomedical optics.

[14]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[15]  W. Marsden I and J , 2012 .

[16]  Christophe Lauze,et al.  In vivo quantification of epidermis pigmentation and dermis papilla density with reflectance confocal microscopy: variations with age and skin phototype , 2012, Experimental dermatology.

[17]  C. Longo,et al.  In vivo confocal microscopy for diagnosis of melanoma and basal cell carcinoma using a two-step method: analysis of 710 consecutive clinically equivocal cases. , 2012, The Journal of investigative dermatology.

[18]  Daniel Racoceanu,et al.  Nuclei extraction from histopathological images using a marked point process approach , 2012, Medical Imaging.

[19]  B. Rao,et al.  In vivo confocal microscopy in clinical practice: comparison of bedside diagnostic accuracy of a trained physician and distant diagnosis of an expert reader. , 2013, Journal of American Academy of Dermatology.

[20]  Christophe Avenel,et al.  Marked point processes with simple and complex shape objects for cell nuclei extraction from breast cancer H&E images , 2013, Medical Imaging.

[21]  Petr Dokládal,et al.  Automatic 3D segmentation of multiphoton images: a key step for the quantification of human skin , 2013, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[22]  Susan Mallett,et al.  Systematic review of diagnostic accuracy of reflectance confocal microscopy for melanoma diagnosis in patients with clinically equivocal skin lesions , 2013, Dermatology practical & conceptual.

[23]  Anan Li,et al.  Automatic detection and quantitative analysis of cells in the mouse primary motor cortex , 2014, Other Conferences.

[24]  R. Hofmann-Wellenhof,et al.  Impact of in vivo reflectance confocal microscopy on the number needed to treat melanoma in doubtful lesions , 2014 .

[25]  C. Longo,et al.  Non‐invasive in vivo dermatopathology: identification of reflectance confocal microscopic correlates to specific histological features seen in melanocytic neoplasms , 2014, Journal of the European Academy of Dermatology and Venereology : JEADV.

[26]  K Takahashi,et al.  Changes in dermal papilla structures due to aging in the facial cheek region , 2015, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[27]  Jennifer G. Dy,et al.  Automated delineation of dermal-epidermal junction in reflectance confocal microscopy image stacks of human skin. , 2015, The Journal of investigative dermatology.