Topological image modification for object detection and topological image processing of skin lesions

We propose a new method based on Topological Data Analysis (TDA) consisting of Topological Image Modification (TIM) and Topological Image Processing (TIP) for object detection. Through this newly introduced method, we artificially destruct irrelevant objects, and construct new objects with known topological properties in irrelevant regions of an image. This ensures that we are able to identify the important objects in relevant regions of the image. We do this by means of persistent homology, which allows us to simultaneously select appropriate thresholds, as well as the objects corresponding to these thresholds, and separate them from the noisy background of an image. This leads to a new image, processed in a completely unsupervised manner, from which one may more efficiently extract important objects. We demonstrate the usefulness of this proposed method for topological image processing through a case-study of unsupervised segmentation of the ISIC 2018 skin lesion images. Code for this project is available on https://bitbucket.org/ghentdatascience/topimgprocess.

[1]  Herbert Edelsbrunner,et al.  Computational Topology - an Introduction , 2009 .

[2]  Hengrui Luo,et al.  Combining Geometric and Topological Information in Image Segmentation , 2019, ArXiv.

[3]  R. Novoa,et al.  Artificial intelligence and dermatology: opportunities, challenges, and future directions. , 2019, Seminars in cutaneous medicine and surgery.

[4]  R. Ho.  Algebraic Topology , 2022 .

[5]  Leonidas J. Guibas,et al.  Persistence-Based Clustering in Riemannian Manifolds , 2013, JACM.

[6]  Tony F. Chan,et al.  An Active Contour Model without Edges , 1999, Scale-Space.

[7]  Gunnar E. Carlsson,et al.  Topological pattern recognition for point cloud data* , 2014, Acta Numerica.

[8]  R. Ghrist.  Barcodes: The persistent topology of data , 2007 .

[9]  Heike Leitte,et al.  Agreement Analysis of Quality Measures for Dimensionality Reduction , 2015 .

[10]  Wolf Byttner.  Classifying RGB Images with multi-colour Persistent Homology , 2019 .

[11]  J. S. Marron,et al.  Topological Descriptors of Histology Images , 2014, MLMI.

[12]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Frédo Durand,et al.  A Topological Approach to Hierarchical Segmentation using Mean Shift , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Christopher J. Tralie,et al.  Ripser.py: A Lean Persistent Homology Library for Python , 2018, J. Open Source Softw..

[15]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[16]  Clifford Smyth,et al.  TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification , 2019, ArXiv.

[17]  J. C. Dooley.  Two-dimensional interpolation of irregularly spaced data using polynomial splines , 1976 .

[18]  Flavio R. Dias Velasco,et al.  Thresholding Using the Isodata Clustering Algorithm , 1979 .

[19]  Valeriu Vrabie,et al.  Persistent homology for object segmentation in multidimensional grayscale images , 2018, Pattern Recognit. Lett..

[20]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[21]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[23]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[24]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[25]  Steve Oudot,et al.  Persistence Theory - From Quiver Representations to Data Analysis , 2015, Mathematical surveys and monographs.

[26]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[27]  R. Novoa,et al.  Marking the Path Toward Artificial Intelligence-Based Image Classification in Dermatology. , 2019, JAMA dermatology.

[28]  Gunnar E. Carlsson,et al.  Topology and data , 2009 .

[29]  Y. Sundblad.  The Ackermann function. a theoretical, computational, and formula manipulative study , 1971 .

[30]  Noel C. F. Codella,et al.  Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC) , 2019, ArXiv.

[31]  Cristina Masoller,et al.  Topological data analysis of high resolution diabetic retinopathy images , 2019, PloS one.

[32]  Tamal K. Dey,et al.  Improved Image Classification using Topological Persistence , 2017, VMV.

[33]  Donald G. Bailey,et al.  An Efficient Euclidean Distance Transform , 2004, IWCIA.