Automated Analysis of Microscopic Images of Isolated Pancreatic Islets

Clinical islet transplantation programs rely on the capacities of individual centers to quantify isolated islets. Current computer-assisted methods require input from human operators. Here we describe two machine learning algorithms for islet quantification: the trainable islet algorithm (TIA) and the nontrainable purity algorithm (NPA). These algorithms automatically segment pancreatic islets and exocrine tissue on microscopic images in order to count individual islets and calculate islet volume and purity. References for islet counts and volumes were generated by the fully manual segmentation (FMS) method, which was validated against the internal DNA standard. References for islet purity were generated via the expert visual assessment (EVA) method, which was validated against the FMS method. The TIA is intended to automatically evaluate micrographs of isolated islets from future donors after being trained on micrographs from a limited number of past donors. Its training ability was first evaluated on 46 images from four donors. The pixel-to-pixel comparison, binary statistics, and islet DNA concentration indicated that the TIA was successfully trained, regardless of the color differences of the original images. Next, the TIA trained on the four donors was validated on an additional 36 images from nine independent donors. The TIA was fast (67 s/image), correlated very well with the FMS method (R 2 = 1.00 and 0.92 for islet volume and islet count, respectively), and had small REs (0.06 and 0.07 for islet volume and islet count, respectively). Validation of the NPA against the EVA method using 70 images from 12 donors revealed that the NPA had a reasonable speed (69 s/image), had an acceptable RE (0.14), and correlated well with the EVA method (R 2 = 0.88). Our results demonstrate that a fully automated analysis of clinical-grade micrographs of isolated pancreatic islets is feasible. The algorithms described herein will be freely available as a Fiji platform plugin.

[1]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Han-Hung Huang,et al.  A replacement for islet equivalents with improved reliability and validity , 2012, Acta Diabetologica.

[3]  Peter Buchwald,et al.  Quantification of the Islet Product: Presentation of a Standardized Current Good Manufacturing Practices Compliant System With Minimal Variability , 2011, Transplantation.

[4]  T J Fetterhoff,et al.  Morphologic analysis of pancreatic islets automated image analysis. , 1994, Transplantation proceedings.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Peter Girman,et al.  Digital imaging as a possible approach in evaluation of islet yield. , 2003, Cell transplantation.

[8]  L. Karasová,et al.  Increased glucagon-stimulated insulin secretion of cryopreserved rat islets transplanted into nude mice , 1999, Journal of Molecular Medicine.

[9]  M. Tyers,et al.  BoxPlotR: a web tool for generation of box plots , 2014, Nature Methods.

[10]  Jan Švihlík,et al.  Color normalization for robust evaluation of microscopy images , 2015, SPIE Optical Engineering + Applications.

[11]  Massimiliano Pontil,et al.  Leave One Out Error, Stability, and Generalization of Voting Combinations of Classifiers , 2004, Machine Learning.

[12]  Clark K. Colton,et al.  Enumeration of islets by nuclei counting and light microscopic analysis , 2010, Laboratory Investigation.

[13]  Ames,et al.  Islet Transplantation in Seven Patients with Type 1 Diabetes Mellitus Using a Glucocorticoid-Free Immunosuppressive Regimen , 2000 .

[14]  D. Mason,et al.  Standardization of Insulin Secretion from Pancreatic Islets: Validation of a DNA Assay , 1985, Hormone and metabolic research = Hormon- und Stoffwechselforschung = Hormones et metabolisme.

[15]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[16]  Peter J. Morris,et al.  Islet isolation assessment in man and large animals , 1990, Acta diabetologia latina.

[17]  T J Fetterhoff,et al.  Quantitation of isolated pancreatic islets using imaging technology. , 1994, Transplantation proceedings.

[18]  Julien Thevenet,et al.  Automated Digital Image Analysis of Islet Cell Mass Using Nikon's Inverted Eclipse Ti Microscope and Software to Improve Engraftment may Help to Advance the Therapeutic Efficacy and Accessibility of Islet Transplantation across Centers. , 2015, Cell transplantation.

[19]  Peter Girman,et al.  Digital Imaging as a Possible Approach in Evaluation of Islet Yield , 2003, Cell transplantation.

[20]  Jan Kybic,et al.  Classification of microscopy images of Langerhans islets , 2014, Medical Imaging.

[21]  A. Naji,et al.  Validation of methodologies for quantifying isolated human islets: an islet cell resources study , 2010, Clinical transplantation.

[22]  J J O'Neil,et al.  Improved assessment of isolated islet tissue volume using digital image analysis. , 1998, Cell transplantation.

[23]  José Costa,et al.  PicoGreen quantitation of DNA: effective evaluation of samples pre- or post-PCR , 1996, Nucleic Acids Res..

[24]  Philippe Morel,et al.  Computer-Assisted Digital Image Analysis to Quantify the Mass and Purity of Isolated Human Islets Before Transplantation , 2008, Transplantation.

[25]  E. Ryan,et al.  Islet transplantation in seven patients with type 1 diabetes mellitus using a glucocorticoid-free immunosuppressive regimen. , 2000, The New England journal of medicine.

[26]  Jan Kybic,et al.  Automated separation of merged Langerhans islets , 2016, SPIE Medical Imaging.

[27]  P. Lacy,et al.  Automated Islet Isolation From Human Pancreas , 1989, Diabetes.

[28]  Jan Kybic,et al.  Comparison of volume estimation methods for pancreatic islet cells , 2016, SPIE Medical Imaging.

[29]  Robert W Solomon,et al.  Free and open source software for the manipulation of digital images. , 2009, AJR. American journal of roentgenology.

[30]  B. Hering,et al.  2008 Update From the Collaborative Islet Transplant Registry , 2008, Transplantation.

[31]  José Antonio Lozano,et al.  A general framework for the statistical analysis of the sources of variance for classification error estimators , 2013, Pattern Recognit..