Challenge session
- Pancreatic Cancer Survival Prediction Challenge
- Combined Imaging and Digital Pathology Brain Tumor Classification Challenge
- Digital Pathology Nuclei Segmentation Challenge
- FDG-PET Radiomics in Head and Neck Cancers
Challenges my be accessed through the CPM Challenge website
Please note important dates in the chart to the right of this page.
Preliminary agenda for challenge sessions at MICCAI follows:
CPM Challenges on Sept 16, at the VIP Room of the Conference Center
Pancreatic Cancer Survival Prediction Challenge
3:00 – 3:10 pm Introduction (A. Simpson, Memorial Sloan Kettering Cancer Center, U.S.A.)
3:10 – 3:25 pm Survival prediction (H. Muhammad, Weill Cornell Medical College and Memorial Sloan Kettering Cancer Center, U.S.A.)
3:25 – 3:40 pm Multimodal feature extraction for Pancreatic Cancer and Survival Prediction using Random Survival Forests (S. Shankaranarayana, S. Vinodhkumar, Zasti.ai, India)
3:40 – 3:55 pm Radiomics-based pancreatic cancer survival prediction on CT (S. Park, Y. Zhou, A.L. Yuille, E. Fishman, Johns Hopkins University, U.S.A.)
3:55 – 4:10 pm 3D network-based pancreatic cancer survival prediction from CT scans (Y. Zhoua, S. Park, E. Fishman, A.L. Yuill, Johns Hopkins University, U.S.A.)
4:10 – 4:25 pm A multi-task approach to survival prediction in pancreatic cancer (U. Bharadwaj)
4:30 pm – 5:00 pm Coffee Break
Imaging and Pathology Brain Tumor Classification Challenge
5:00 – 5:10 pm Introduction (T. Kurc, Stony Brook Cancer Center, U.S.A.)
5:10 – 5:25 pm Multi-modal image classification of brain tumor based on deep learning (Q. Qi, Y. Zhang, Y. Huang, and X. Ding, Xiamen University, China)
5:25 – 5:40 pm Dropout-Enabled Ensemble Learning for Multi-Scale Biomedical Data (A. Momeni, M. Thibault, O. Gevaert, Stanford University, U.S.A.)
5:40 – 5:55 A Combined Radio-Histological Approach for Classification of Low Grade Gliomas (A. Bagari, A. Kumar, A. Kori, M. Khened and G. Krishnamurthi, Indian Institute of Technology, India)
Digital Pathology Nuclei Segmentation Challenge
6:00 – 6:10 pm Introduction (T. Kurc, Stony Brook Cancer Center)
6:10 – 6:25 pm Mask-RCNN for Cell Instance Segmentation (S. Zhou, X. Ren, D. Shen and Q. Wang, University of North Carolina at Chapel Hill, U.S.A., and Shanghai Jiao Tong University, China)
6:25 – 6:40 pm Nuclei segmentation with histopathology images in digital pathology (Y. Zhang, Z. Zeng and W. Xie, Pvmed Inc, and Sun Yat-sen University, China)
6:40 – 6:55 pm Nuclei Segmentation via FCN-based Coarse-to-fine Semantic Segmentation (Z. Wu, C. Shen, A. van den Hengel and J. Zhang, University of Adelaide, Australia)
6:55 pm Adjournment
Organizing Committee |
---|
|
Challenge sessions
The Test phase of challenges will be held online, Sept 1-7. On Oct 9th, three afternoon sessions will be dedicated to presentations by the top three teams ranked in each challenge competition.
Challenge 1: Segmentation of Nuclei in Digital Pathology Images
The characteristics of cancer nuclei are central components in many aspects of pathology classification and nuclear features, combined with “omics” have been shown by many research groups to be linked to patient outcome. Although there are many important and predictive features but characteristics of cancer nuclei are overall the most important. Virtually without exception, all commercial systems and academic groups in the digital Pathology area make use of nuclear segmentation algorithms. Given this, ability to segment and then classify nuclei is a key task and a very appropriate challenge topic.
The reference standard will be pathologist generated nuclear segmentation on select regions of TCGA Glioma whole slide images for the challenge.
The contestants will be tasked with applying their segmentation algorithms, previously trained on the training data, to segment all nuclei in a tile region. Their results will be submitted online and compared with consensus pathologist segmented sub regions. Winners will be ranked based on their nuclei segmentation best matching the reference standards.
Visit http://miccai.cloudapp.net/competitions/ to access data and evaluation platform for this challenge.
Challenge 2: Combined Imaging and Digital Pathology Primary Tumor Classification
This challenge will help bring expertise in image processing in digital pathology and radiology closer by working on a single task of tumor classification. In the long term thistype of collaboration will help reduce discordance and increase diagnostic accuracy of brain tumors. In addition, by computationally encompassing both digital pathology and clinical brain tumor MRI as resources in this Challenge it may generate a result that could contradict present-day classification orthodoxies of tumor stage and aggressiveness that have to date been primarily based on subjective histopathology observations.Contestants will be allowed to use algorithms of their choice to classify brain tumors into low grade II and low grade III gliomas. They may choose to perform segmentation to extract relevant information from pathology and imaging data. The reference standards will be the result of segmentations performed by expert neuro radiologist and neuropathologist. Winners will be ranked based on the most number of correct tumor classifications derived.
Visit http://miccai.cloudapp.net/competitions/ to access data and evaluation platform for this challenge.
Challenge 3: Guess the Primary
The overall objective of this challenge is to study imaging phenotypes of metastatic disease originating from different primary cancers in the body. We challenge the image segmentation community to determine if primary cancers create distinct imaging signatures that can be automatically detected with segmentation algorithms. The impact of successfully predicting the histology of the primary tumor based on features of the brain metastasis would be to provide a biological insight into brain tumor imaging and segmentation that could result in improved clinical treatment decisions.
Through this exercise, we will develop algorithms that will advance segmentation methods for metastatic cancer in the brain. Using one or more of these algorithms, we hope to gain insight into the underlying biology and growth patterns of metastatic lesions and perhaps, their proclivity to seed and grow differently based on the inherent phenotype they carry with them from the primary cancer organ/site. An additional objective will be to develop image processing algorithms that segment, process and analyze MRI sequences for brain metastasis.
Visit https://www.synapse.org/#!Synapse:syn4112414/wiki/ to access further information for this challenge.
Abstract Submission [Deadline extended]: Workshop speakers and participants in challenges are asked to provide abstracts of their presentations (1 page) or computational algorithms (up to 4 pages) by Aug 10. PDF submissions (free formatted, journal style, and double-spaced) should be sent to farahani@nih.gov
Challenge participants will have an opportunity to revise their abstracts by Sept 18, following the completion of the Test Phase.
Organizing Committee |
---|
|