Special Issue of the Journal “Pattern Recognition Letters”

Executable Thematic Special Issue of Pattern Recognition Letters


Pattern Recognition Techniques for Indirect Immunofluorescence Images Analysis

Call for Papers

In the recent years we have assisted to a progressively growing number of applicative areas of Pattern Recognition, mainly devoted to the exploitation of cutting edge scientific methodologies for the solution of problems of relevant interest to civil society. This trend is generating new communities, as aggregation of scientist having as common aim the development of systems more or less prompt to be transformed into real working prototypes. In the field of medical image analysis this trend has been even more evident than in others, as the availability of assisted diagnosis tools would allow the medical community to increase their productivity jointly with an improvement of the quality and precision of the diagnostic act.

Among all, rather novel interests are concentrating on the indirect immunofluorescence images (IIF), i.e. images obtained by making biological tissue interacting with special sources of light, so as to generate fluorescent image responses; these revealed especially suited for searching antibodies in the patient serum, so revealing the presence of autoimmune diseases. Due to its effectiveness, diagnostic tests for systemic autoimmune diseases are now becoming more and more interesting to both academic and industrial communities. Nevertheless, today IIF is still a subjective method too dependent on the experience and expertise of the physician.  As a consequence of this limitation, there is a strong demand for a complete automation of the procedure, that would result in increased test repeatability and reliability, easier and faster result reporting, and lower costs.

These issues have been addressed by an increasing number of research groups that in the last few years have provided innovative contributions to the different aspects of the analysis of IIF images as image acquisition, pre-processing, segmentation, pattern classification. Such interest has been also boosted by a series of benchmarking activities on IIF cells and specimen classification held at ICPR 2012, ICIP 2013 and ICPR 2014 that in all cases received a large participation of the scientific community, overall collecting more than 65 distinct software submissions.

Comforted by the success of the above mentioned initiatives, we propose to dedicate a Special Issue aimed to promote “reproducible research” by collecting the most relevant contributions in this area and comparing them on the same datasets used for the “Performance Evaluation of Indirect Immunofluorescence Image Analysis Systems” competition @ ICPR 2014. In particular, the participants are requested to propose a method for facing one or both the following classification tasks regarding the design and implementation of a pattern recognition system able to classify:

  • TASK 1: the pre-segmented cells belonging to IIF images according to one of six different staining pattern classes;
  • TASK 2: the pre-segmented IIF specimen images according to one of six different staining pattern classes.

More information about the dataset can be found here, while at the following link you can download it.

Information for Authors

The special issue is open to all the research community, including those groups that participated to the benchmarking activities held at ICPR 2012, ICIP 2013 and ICPR 2014.

The Special Issue is organized in two phases:

  • Phase 1 – Software submission and evaluation: all participants have to submit a software implementation of the proposed method, together with all the parameterizations required to execute the software and a 1-page description of the proposal. The organizers will evaluate performance of the submissions on the private part of the dataset.
  • Phase 2 – Paper submission: a subset of the best performing and innovative submissions will be invited to submit a paper that thoroughly describes the method. Paper submissions to the special issue must include original and technically sound research and must be written in English. Submitted papers will undergo blind peer review.

The authors of the accepted papers formally agree on the fact that their software submissions will be made publicly available to the scientific community.

Important Dates

Phase 1: Software submission and evaluation
Software submission deadline: November 30, 2014 January 15, 2015
Notification of the results: January 15, 2015 March 1, 2015
Phase 2: Paper submission
Manuscript submission deadline: March 15, 2015 May 31, 2015
First notification: May 31, 2015 July 15, 2015
Revised manuscript submission: June 30, 2015 August 31, 2015
Notification of final decision: July 31, 2015 September 30, 2015
Tentative publication date of special issue: First quarter 2016

Guest Editors

Mehrtash Harandi1, Brian C. Lovell1, Gennaro Percannella2, Alessia Saggese2, Mario Vento2, Arnold Wiliem1

1: The University of Queensland, Australia
2: University of Salerno, Italy