دانلود کتاب چالش ISBI 2019 C-NMC: طبقه بندی در تصویربرداری سلول سرطانی

This book contains proceedings of the medical image classification challenge, titled “C-NMC challenge: Classification of Normal versus Malignant Cells in B-ALL White Blood Cancer Microscopic Image” organized by researchers of SBILab, IIIT-Delhi (http://sbilab.iiitd.edu.in/), and AIIMS, New Delhi, India, as part of the IEEE International Symposium on Biomedical Imaging (IEEE-ISBI 2019) conference held in Venice, Italy, from April 8 to 11, 2019. Cell classification via image processing has recently gained interest from the point of view of building computer-assisted diagnostic tools for blood disorders such as leukemia. In order to arrive at a conclusive decision on disease diagnosis and degree of progression, it is very important to identify malignant cells with high accuracy. Computer-assisted tools can be very helpful in automating the process of cell segmentation and identification because morphologically both cell types appear similar. This challenge was run on a curated dataset of more than 15000 cell images of very good quality. The challenge had participants from many countries. The training data was provided to 251 teams, and the number of submissions on the preliminary test data and the final test data on the challenge leaderboard was 60 and 25, respectively. The challenge was opened on November 10, 2018, at CodaLab, and the results were declared on March 18, 2019. The results of the challenge on the test set predictions are available at the challenge leaderboard (http://sbilab.iiitd.edu.in/resources.html). The challenge concluded with a workshop at IEEE-ISBI 2019 conference on April 11, 2019, wherein three top performing teams and five other teams presented their work. The challenge was technically co-sponsored by IBM India Pvt. Ltd. On behalf of IBM India, Dr. Mani Madhukar, Program Manager, University Relations, IBM India Pvt. Ltd, attended the workshop, delivered a lecture on IBM Watson, and also distributed the prizes to the top three teams as well as to the other participants of the challenge. The dataset provided for this challenge, named C-NMC 2019 Dataset, was prepared at Laboratory Oncology, AIIMS, New Delhi, India. A waiver for written informed consent was obtained from the Ethics Committee of AIIMS, New Delhi, on this dataset for research purposes. It consisted of white blood cell images with labels (normal versus cancer) that were provided to train machine learning-based classifier to identify normal cells from leukemic blasts (malignant/cancer cells). This dataset is now publicly available at The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/tcia.2019. dc64i46r). Data is prepared at the subject level and is split into the training set and testing set. Training set consists of 12528 cell images collected from the data of 60 cancer subjects and 41 healthy subjects. Test data consists of 2586 cell images collected from 9 cancer subjects and 8 healthy subjects. The size of the total dataset is 15114 cell images. Researchers can evaluate their results on the test set by submitting results at the leaderboard (https://competitions.codalab.org/competitions/20395#results). We gratefully acknowledge the research funding support (Grant: EMR/2016/ 006183) from the Department of Science and Technology, Govt. of India, and Grant: 1 (7)/2014-ME\&HI from the Ministry of Communication and IT, Govt. of India, for this research work. The funder had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. We acknowledge the support of IBM India Pvt. Limited for being the technical co-sponsor of this challenge. We are grateful to the Technical Program Committee, who devoted their valuable time in reviewing the submitted papers and provided constructive feedback to the authors. Each paper was reviewed by three independent reviewers. We thank all the workshop attendees who presented their work at the workshop in Venice. In particular, we would like to thank Shiv Gehlot, PhD Scholar, SBILab, Department of ECE, IIIT-Delhi, for handling the work related to challenge from start to the end. He helped participants with all their queries, maintained the challenge portal, helped participants evaluate the performance of their codes, and provided support for the publication of this challenge proceedings. Last but not least, we would like to thank the students and staff of SBILab, IIIT-Delhi, and Laboratory Oncology, AIIMS, New Delhi, for their support for the smooth conduct of this challenge and publications of the proceedings.