Computerized Image Analysis in Digital Pathology with Histological and Cytological Virtual Slides

Recent advances in technological solutions for automated high-speed and high-resolution whole slide imaging (converting glass slides into digital slides) have set the basis for a digital revolution in microscopy. By digitizing the images that pathologists normally view through a microscope, digital slide technology is changing the ways in which pathologists have been practicing disease diagnosis and prognosis for more than hundred years. This has opened the way to Digital pathology: a digital environment for managing and interpreting pathology information generated from a digital slide. However, even within a digital pathology environment, pathologists are faced with an ever-increasing amount of digital slides to analyze. Daily routine interpretation of digital slides is still reduced mainly to virtual microscopy (viewing and sharing digital slides over networks) with very few quantitative analysis. Since performing manually segmentations of digital slides is infeasible for a human observer in clinical setting due to the time constraints, quantitative and highly automated analysis methods must be developed. Our goal is to help to enhance the efficiency of pathologists as well as improving diagnostic confidence by developing image processing and analysis techniques to assist pathologists in interpreting digital slides. We present several developments and applications of digital slide image analysis in histopathology and cytology we have led in the Image Team of the GREYC Laboratory, University of Caen, France:

• Mitosis extraction in breast cancer histological digital slides,
• Tendon structure analysis in histological digital slides of equine tendinopathy,
• High-content screening in cytological digital slides for early diagnosis of mesothelioma in serous samples.

Joint work with Abderrahim Elmoataz, Hubert Elie, Michel Lecluse and Fabrice Audigie.

Biography

Olivier LEZORAY (http://www.info.unicaen.fr/lezoray) received his B.Sc. in mathematics and computer science, M.Sc. and Ph.D. degrees from the Department of Computer Science, University of Caen, France, in 1992, 1996, and 2000, respectively. From September 1999 to August 2000, he was an assistant professor with the Department of Computer Science at the University of Caen. From September 2000 to August 2009, he was an associate professor at the Cherbourg Institute of Technology of the University of Caen, in the Communication Networks and Services Department. In July 2008, he was a visiting research fellow at the University of Sydney. Since September 2009, he has been a full professor at the Cherbourg Institute of Technology of the University of Caen, in the Communication Networks and Services Department. He also serves as Chair of the Institute Research Committee. In 2011 he cofounded Datexim and is a member of the scientic board of the company, which brought state-of-art image and data processing to market with applications in digital pathology. His research focuses on discrete models on graphs for image processing and analysis, image data classification by machine learning, and computer-aided diagnosis. He is a contributor to four books, and he has published over 100 papers in refereed journals and conference proceedings in the areas of image processing and machine learning. In 2008, he
received the IBM Best Paper Student Award at ICIP 2008 with V-T. Ta and A. Elmoataz. Dr. Lezoray is a member and Local Liaison Officer of the European Association for Signal, Speech and Image Processing (EURASIP), the IEEE Signal Processing Society's, the IEEE Communication
Society Multimedia Communications Technical Committee, and the International Association for Pattern Recognition (IAPR). He was the program cochair of the International Conference on Image and Signal Processing (ICISP) in 2008, 2010, and 2012. He was a guest coeditor of the EURASIP Journal on Advances in Signal Processing for a special issue on Machine Learning in Image Processing, of Signal Processing for a special issue on the Processing and Analysis of High-Dimensional Masses of Image and Signal Data, and of Computerized Medical Imaging and Graphics for a special issue on Whole Slide Microscopic Image Processing. He serves as a reviewer for various scientific international journals.