Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation

@inproceedings{Ionescu2018OverviewOI,
  title={Overview of ImageCLEF 2018: Challenges, Datasets and Evaluation},
  author={Bogdan Ionescu and Henning M{\"u}ller and Mauricio Villegas and Alba Garc{\'i}a Seco de Herrera and Carsten Eickhoff and Vincent Andrearczyk and Yashin Dicente Cid and Vitali Liauchuk and Vassili A. Kovalev and Sadid A. Hasan and Yuan Ling and Oladimeji Farri and Joey Liu and Matthew P. Lungren and Duc-Tien Dang-Nguyen and Luca Piras and M. Riegler and Liting Zhou and Mathias Lux and Cathal Gurrin},
  booktitle={CLEF},
  year={2018}
}
This paper presents an overview of the ImageCLEF 2018 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) Labs 2018. ImageCLEF is an ongoing initiative (it started in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval with the aim of providing information access to collections of images in various usage scenarios and domains. In 2018, the 16th edition of ImageCLEF ran three main tasks and a… 
ImageCLEF 2019: Multimedia Retrieval in Medicine, Lifelogging, Security and Nature
TLDR
An overview of the ImageCLEF 2019 lab is presented, organized as part of the Conference and Labs of the Evaluation Forum - CLEF Labs 2019, and shows an important interest in this benchmark campaign.
ImageCLEF 2019: Multimedia Retrieval in Lifelogging, Medical, Nature, and Security Applications
TLDR
This paper presents an overview of the foreseen ImageCLEF 2019 lab that will be organized as part of the Conference and Labs of the Evaluation Forum - CLEF Labs 2019, and expects the new tasks to attract at least as many researchers for 2019.
ImageCLEF 2020: Multimedia Retrieval in Lifelogging, Medical, Nature, and Internet Applications
TLDR
An overview of the 2020 ImageCLEF lab is presented that will be organized as part of the Conference and Labs of the Evaluation Forum—CLEF Labs 2020 in Thessaloniki, Greece.
Overview of ImageCLEF 2018 Medical Domain Visual Question Answering Task
TLDR
This paper presents an overview of the inaugural edition of the ImageCLEF 2018 Medical Domain Visual Question Answering (VQA-Med) task, a pilot task proposed this year to focus on visual question answering in the medical domain.
Overview of the ImageCLEF 2018 Caption Prediction Tasks
TLDR
Results show that this is a difficult task but that large amounts of training data can make it possible to detect the general topics of an image from the biomedical literature and that providing more coherent training data or larger quantities can help to learn such complex models.
Overview of ImageCLEFtuberculosis 2019 - Automatic CT-based Report Generation and Tuberculosis Severity Assessment
TLDR
In this second edition of the SVR subtask the results support the assessment of a severity score based on the CT scan with up to 0.79 area under the curve (AUC) and 74% accuracy, so very good results.
NLM at ImageCLEF 2018 Visual Question Answering in the Medical Domain
TLDR
This paper describes the participation of the U.S. National Library of Medicine in the Visual Question Answering task (VQAMed) of ImageCLEF 2018, and describes four areas of improvements dedicated to medical VQA.
Overview of ImageCLEFtuberculosis 2020 Automatic CT-based Report Generation
TLDR
This year’s edition of ImageCLEF was dedicated to the automatic generation of a lung-wise CT report (CTR) based on three relevant CT findings, similar to the CTR (CT Report) subtask from the previous year.
UMass at ImageCLEF Medical Visual Question Answering(Med-VQA) 2018 Task
TLDR
A co-attention based deep learning framework where residual networks is used to extract visual features from image that interact with the long-short term memory(LSTM) based question representation providing fine-grained contextual information for answer derivation.
ImageCLEF 2021: Deep categorizing tuberculosis cases using normalization and pseudo-color CT image
TLDR
This paper proposes an image processing and fine-tuning deep neural network model that uses inputs from convolutional neural network features and approaches for applying normalization and pseudo-color to the extracted 2D images, and for extracting a set of 2D projection images based on the 3D chest CT data.
...
...

References

SHOWING 1-10 OF 49 REFERENCES
Overview of ImageCLEF 2017: Information Extraction from Images
TLDR
An overview of the ImageCLEF 2017 evaluation campaign, an event that was organized as part of the CLEF (Conference and Labs of the Evaluation Forum) labs 2017, shows the interest in this benchmarking campaign despite the fact that all four tasks were new and had to create their own community.
General Overview of ImageCLEF at the CLEF 2015 Labs
TLDR
The x-ray task was the only fully novel task this year, although the other three tasks introduced modifications to keep up relevancy of the proposed challenges.
Overview of ImageCLEFcaption 2017 - Image Caption Prediction and Concept Detection for Biomedical Images
TLDR
Some surprisingly good results of the difficult caption tasks are noted with a quality that could be beneficial for health applications by better exploiting the visual content of biomedical figures.
Overview of ImageCLEF 2018 Medical Domain Visual Question Answering Task
TLDR
This paper presents an overview of the inaugural edition of the ImageCLEF 2018 Medical Domain Visual Question Answering (VQA-Med) task, a pilot task proposed this year to focus on visual question answering in the medical domain.
Overview of the ImageCLEF 2018 Caption Prediction Tasks
TLDR
Results show that this is a difficult task but that large amounts of training data can make it possible to detect the general topics of an image from the biomedical literature and that providing more coherent training data or larger quantities can help to learn such complex models.
Overview of ImageCLEFlifelog 2017: Lifelog Retrieval and Summarization
TLDR
The first ImageCLEF 2017 LifeLog task aims to be a comparative evaluation framework for information access and retrieval systems operating over personal lifelog data and there are interesting insights into these very relevant challenges.
Overview of ImageCLEFlifelog 2018: Daily Living Understanding and Lifelog Moment Retrieval
TLDR
The ImageCLEFlifelog 2018 tries to overcome problems and make the task accessible for an even broader audience (eg, pre-extracted features are provided) and is divided into two subtasks (challenges) which are lifelogging moment retrieval (LMRT) and the Activities of Daily Living understanding (ADLT).
A Cross Modal Deep Learning Based Approach for Caption Prediction and Concept Detection by CS Morgan State
TLDR
The participation of the Computer Science Department of Morgan State University, Baltimore, Maryland, USA in the ImageCLEFcaption 2018 uses the merge architectures for the encoder-decoder recurrent neural network (RNN) due to it’s success over inject for caption generation.
UMass at ImageCLEF Caption Prediction 2018 Task
TLDR
An encoder-decoder framework was explored and implemented to generate caption given a medical image and two variations of convolutional neural networks were compared: ResNet-152 and VGG-19, and the long short term memory (LSTM) recurrent neural network.
IPL at ImageCLEF 2018: A kNN-based Concept Detection Approach
TLDR
A k-NN based concept detection algorithm was used in order to automatically predict multiple concepts in medical images and the visual representation of images was based on the bagof-visual-words and bag-of-colors models.
...
...