IEEE ICASSP 2023: AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Competition (AI-MIA-COV19D)

The “AI-enabled Medical Image Analysis  Workshop and  Covid-19 Diagnosis Competition” will be held on June 10, 2023, 08.30-12.00 EET, in conjunction with IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) 2023 in Rhodes Island, Greece (‘Salon Des Roses A’, Rodos Palace Luxury Convention Resort).

For any requests or enquiries, please contactstefanos@cs.ntua.gr

Organizers

  • Stefanos Kollias (National Technical University of Athens)
  • Xujiong Ye ( University of Lincoln )                                                xye@lincoln.ac.uk 
  • Francesco Rundo ( STMicroelectronics ADG—Central R&D )    francesco.rundo@st.com 
  • Dimitrios Kollias ( Queen Mary University London )                   d.kollias@qmul.ac.uk 

Data Chairs

  • Anastasios Arsenos ( National Technical University of Athens )
  • Paraskevi Theofilou (National Technical University of Athens )
  • Manos Seferis ( National Technical University of Athens )
  • James Wingate ( University of Lincoln )

Description

There are two activities in the IEEE ICASSP 2023 AI-MIA-COV19D Workshop:

A. AI-enabled Medical Image Analysis (AI-MIA) Workshop

A1. Scope

AI-enabled Medical Image Analysis (MIA) Workshop is devoted to medical image analysis, with emphasis on pathology and radiology fields for diagnosis of diseases. Our focus is placed on Artificial Intelligence (AI), Machine and Deep Learning (ML, DL) approaches that target effective and adaptive diagnosis; we also have a particular interest in approaches that enforce trustworthiness and automatically generate explanations, or justifications of the decision making process.

A2. Call for Participation

Technologies and topics to be addressed include, but are not limited to:

– Supervised, unsupervised, self-supervised AI/ML models  for medical diagnosis
– Sensing “salient features” of AI/ML models related to decision-making, in spatial (images), temporal (video), volumetric (3-D) data
– In temporal and 3-D data: explanation of which features and at what time, or slice, or respective intervals, are the most prominent for the provided decision
– In multimodal data: how predictions in data streams are correlated and explain each other
– Global and local models for prediction or classification
– Attention & self-attention mechanisms in DL/AI approaches
– Interpretability at training time through adversarial regularization
– Learning new data (from multiple sources) by leveraging knowledge already extracted and codified, through domain adaptation
– Generalizable DL methods when the training medical image datasets are small
– Generalizable DL methods in cases of images with potential domain shift
– Uncertainty estimation and quantification, self training
– Zero/one shot learning, avoidance of catastrophic forgetting.

A3. Important Dates

For the papers to be submitted to the Workshop (not including the Competition) the timeline will be as follows:

  • March 30, 2023: Paper submission deadline (AoE) *; Start of review period
  • April 14, 2023: Review decisions sent to authors; Notification of acceptance
  • April 28, 2023: Camera ready version deadline

* “The paper formatting guidelines can be found in: https://2023.ieeeicassp.org/paper-submission-guidelines/. Specifically, as stated there, the ICASSP spconf.sty should be followed, and not the generic IEEE conference style. Note that papers should be 4 pages or 4+1 pages long (in the latter case, only references are allowed in the 5th page). Finally, remember to enter all paper authors in CMT with the same order as the one appearing in the paper pdf.”

A4. Submission Information

The peer review process for the papers will be single blind, including at least two distinct reviews per submission, and will follow IEEE ICASSP standards and policies. The accepted papers will be part of the ICASSP 2023 conference proceedings. All paper submissions must adhere to the IEEE ICASSP 2023 paper submission style, format, and length restrictions.

For creating a submission, please go here  and press “GO TO SUBMISSION PLATFORM”. This will direct you to CMT, where you will need to create a new submission and select our Workshop from the drop-down list.

A5. Invited Talk by Professor Dimitris Metaxas (Rutgers University, USA) at the AI-MIA-COV19D Workshop in ICASSP 2023 (NEW!)

Robust, Scalable and Explainable Analytics for Biomedical Applications: Over the last 30 years, we have been developing a general, scalable, computational learning and AI framework that combines principles of computational learning, neural nets, sparse methods, mixed norms, dictionary learning, and deformable modeling methods.  This framework has been used for resolution of complex large scale problems in biomedical image analysis and collaborations with the pharmaceutical industry. Our learning methods allow the discovery of complex features, shapes, relationships, disease diagnosis  for many types of clinical and preclinical applications. We will present segmentation, registration, tracking  and disease recognition methods and their applications to cardiac analytics,  cancer diagnosis, body fat estimation and cell tracking. Finally, we will show novel AI methods that offer explainability in machine learning to provide further insights into learning-based decision making and diagnosis.

Short CV: Dr. Dimitris Metaxas is a Distinguished Professor and Chair of the Computer Science Department at Rutgers University. He is director of the Center for Computational Biomedicine, Imaging and Modeling (CBIM). From September 1992 to September 2001 he was a tenured faculty member in the Computer and Information Science Department of the University of Pennsylvania and Director of the VAST Lab. Prof. Metaxas received a Diploma in Electrical Engineering from the National Technical University of Athens Greece in 1986, an M.Sc. in Computer Science from the University of Maryland, College Park in 1988, and a Ph.D. in Computer Science from the University of Toronto in 1992. Dr. Metaxas has been conducting research towards the development of formal methods to advance medical imaging, computer vision, computer graphics, and understanding of multimodal aspects of human language.  His research emphasizes the development of formal models in shape representation, deterministic and statistical object modeling and tracking, sparse learning methods for segmentation and restoration, and organ motion analysis.   Dr. Metaxas has published over 700 research articles in these areas and has graduated 65 PhD students. The above research has been funded by NSF, NIH, ONR, AFOSR, DARPA, HSARPA and the ARO. Dr. Metaxas has received several best paper awards, and he has 9 patents. He was awarded a Fulbright Fellowship in 1986, is a recipient of an NSF Research Initiation and Career awards, an ONR YIP, and is a Fellow of the MICCAI Society, a Fellow the American Institute of Medical and Biological Engineers and a Fellow of IEEE. He has been involved with the organization of several major conferences in vision and medical image analysis, including ICCV, CVPR, and MICCAI.

A6. AI-MIA-COV19D Workshop Program at ICASSP-2023   (NEW!)

(Saturday, June 10, 2023, Rodos Palace “Salon Des Roses A”)

Time (EEST) Presenter Presentation Title
08.25 – 08.30 Stefanos Kollias Introduction – Start of Workshop
08.30 – 09.00 Dimitris Metaxas Invited Talk: Robust, Scalable and Explainable Analytics for Biomedical Applications
09.00 – 09.15 Angelo Genovese All-idb patches: Whole Slide Imaging for Acute Lymphoblastic Leukemia Detection using Deep Learning
09.15 – 09.30 David Anglada-Rotger Color Deconvolution applied to Domain Adaptation in HER2 histopathological images
09.30 – 09.45 Anastasis Arsenos Data-driven COVID-19 Detection through Medical Imaging
09.45 – 10.00 Vassilis Cutsuridis Deep CNNs with Transfer Learning for Bone Fracture Recognition using Small Exemplar Image Datasets
10.00 – 10.20 Coffee Break
10.00 – 10.20 Robert Turnbull Poster: Lung segmentation enhances COVID-19 Detection (Poster area WP-D)
10.20 – 10.35 Dimitrios Kollias AI-enabled Analysis of 3-D CT Scans for Diagnosis of COVID-19 & its Severity
10.35 – 10.50 Chih-Chung Hsu Bag of Tricks of Hybrid Network for COVID-19 Detection of CT Scans
10.50 – 11.05 Alessia Rondinella Attention-Based Convolutional Neural Network for CT Scan COVID-19 Detection
11.05 – 11.20 Fares Bougourzi Deep-Covid-Sev: Ensemble 2D & 3D CNN-Based approach for COVID-19 Severity Prediction from 3D CT-scans
11.20 – 11.35 Helio Pedrini MIA-3DCNN: A 3D CNN for COVID-19 Detection and Severity Classification
11.35 – 11.50 Anand Thyagachandran Ensemble Methods for Enhanced COVID-19 CT scan severity analysis
11.50 – 12.05 Georgios Alexandridis Adversarial Attacks & Detection on a Deep Learning-based Digital Pathology Model
12.05 – 12.20 Paraskevi-Antonia Theofilou COVID-19 Detection from X-ray Images using Deep Learning Methods
12.20 – 12.35 Mohib Ullah Glove-ing Attention: A Multi-modal Neural Learning Approach to Image Captioning
12.35 – 12.40 Stefanos Kollias Conclusions – End of Workshop

A7. SPONSORS (NEW!)  

– Greek National Infrastructures for Research & Technology (GRNET)

– Digital Environment Research Institute (DERI) of Queen Mary University London

——————————————————————————————————————————-

B. 3rd COV19D Competition

B1. Scope

The 3rd COV19D Competition follows the 1st and 2nd Competitions held in the framework of  ICCV 2021 and ECCV 2022 Conferences respectively . It includes two Challenges: i) Covid-19 Detection Challenge and ii) Covid-19 Severity Detection Challenge.

Both Challenges are  based on an extended version of the database used in the 1st and 2nd COV19D Competitions, including  chest CT scan series. Each chest CT scan series consists of a sequence of 2-D CT slices, the number of which is between 50 and 700.

I. Covid-19 Detection Challenge

Each CT scan is manually annotated with respect to Covid-19 and non-Covid-19 categories. The database is split into training, validation and test partitions. The training and validation sets along with their corresponding annotations will be provided to the Competition participating teams to develop AI/ML/DL models for Covid-19 and non-Covid-19 prediction. Performance of the different approaches will be evaluated on the test set in terms of the ‘macro’ F1 score.

II. Covid-19 Severity Detection Challenge

Extended part of the database has been annotated in terms of Covid-19 severity into four categories, i.e., mild, moderate, severe and critical. The database is split into training, validation and test partitions. The training and validation sets along with their corresponding annotations will be provided to the Competition participating teams to develop AI/ML/DL models for Covid-19 severity prediction. Performance of the different approaches will be evaluated on the test set in terms of the ‘macro’ F1 score.

B2. Call for Participation

The participating teams are invited to participate in at least one of these Challenges. In the end, they will submit their Covid-19 predictions and/or Covid-19 severity predictions for the respective test datasets. The winners of the Competitions will be selected based on the achieved performance, in terms of the ‘macro’ F1 score, on the test sets.

There will be one winning team for each Competition. The top-3 performing teams are expected to contribute a paper describing their approach, methodology and results to our “AI-enabled Medical Image Analysis  Workshop and  Covid-19 Diagnosis Competition” ICASSP 2023 Workshop. All other teams will be able to submit a paper describing their solutions and final results to the Workshop. The accepted papers will be part of the IEEE ICASSP 2023 proceedings. 

The research groups will be able to use any publicly available datasets as long as they report it in their submitted final paper. We will provide a white paper describing the Competitions, the databases used, as well as baseline models and their results for comparison purposes.

B3. General Information

In order to participate in the Competitions, teams will need to register. At the end of the Competitions, each team will have to send us: i) their predictions on the test set, ii) a link to a Github repository where their solution/source code will be stored, and iii) a link to an ArXiv paper with 2-8 pages describing their proposed methodology, data used and results. After that, the winner of each Competition will be announced and a leaderboard will be published. The winner and the two runner-ups in each Competition will be asked to also share their trained models so as to check out the validity of the approach.

B4. Participation Information

In order to participate, teams will have to register; the lead researcher should send an email from their official address (no personal emails will be accepted) to d.kollias@qmul.ac.uk with:

i) subject “3rd COV19D Competition: Team Registration”;
ii)  this EULA filled in, signed and attached;
iii) the lead researcher’s official academic/industrial website; please note that the lead researcher cannot be a student (UG/PG/Ph.D.);
iv) the emails of each team member
v) the team’s name
vi) the point of contact name and email address (which member of the team will be the main point of contact for future communications, data access etc.)

There is a maximum number of 8 participants in each team.

As a reply, you will receive access to the dataset’s images and annotations.

B5. Final Paper Submission Information

The peer review process for the papers will be single blind, including at least two distinct reviews per submission, and will follow IEEE ICASSP standards and policies. The accepted papers will be part of IEEE ICASSP 2023 conference proceedings. All paper submissions must adhere to the ICASSP 2023 paper submission style, format, and length restrictions.

For creating a submission, please go here  and press “GO TO SUBMISSION PLATFORM”. This will direct you to CMT, where you will need to create a new submission and select our Workshop from the drop-down list.

B6. Important Dates

The timeline for the competitions will be as follows:

  • December 16, 2022: Opening of the Competition; start of registration of research groups;  provision of training and validation datasets, of respective annotations and of the baseline approach will follow
  • March 18, 2023: Final submission of results deadline (Results, Code and ArXiv paper sent to d.kollias@qmul.ac.uk)
  • March 19, 2023: Winners announcement
  • March 30, 2023: Paper submission deadline (AoE)*; Start of review period
  • April 14, 2023: Review decisions sent to authors; Notification of acceptance
  • April 28, 2023: Camera ready version deadline

* “The paper formatting guidelines can be found in: https://2023.ieeeicassp.org/paper-submission-guidelines/. Specifically, as stated there, the ICASSP spconf.sty should be followed, and not the generic IEEE conference style. Note that papers should be 4 pages or 4+1 pages long (in the latter case, only references are allowed in the 5th page). Finally, remember to enter all paper authors in CMT with the same order as the one appearing in the paper pdf.”

B7. Competition Results

18 Teams participated in the 3rd COV19D Competition (COVID19 Detection Challenge and COVID19 Severity Detection Challenge).

10 Teams submitted their results to the (3rd) COVID19 Detection Challenge; 9 Teams submitted their results to the (2nd) COVID19 Severity Detection Challenge.

5 and 4 Teams scored higher than the baseline and made valid submissions, respectively; their results are shown in the leaderboards below.

———————————————————————————————————————————–

The winner of the (3rd) COVID19 Detection Challenge is the team ACVLab consisting of: Chih-Chung Hsu, Chi-Han Tasi, Chih-Yu Jian, Chia-Ming Lee, Sheng-Chieh Dai  (National Cheng Kung University, Taiwan).

The runner-up is team MDAP consisting of: Robert Turnbull (University of Melbourne, Australia).

The team that ranked third is COV-UNICAMP consisting of:  Helio Pedrini, Giovanna Vendramini, Igor Kenzo Ishikawa Oshiro Nakashima (University of Campinas, Brazil).

The leaderboard can be found  here

———————————————————————————————————————————–

The winner of the (2nd) COVID19 Severity Detection Challenge is team MDAP consisting of: Robert Turnbull (University of Melbourne, Australia).

The runner-up is team Deep-Covid-Sev consisting of: Bougourzi Fares, Fadi Dornaika, Abdelmalik Taleb-Ahmed, Cosimo Distante (University Paris-Est Créteil).

The team that ranked third is IITM CSE consisting of: Hema A. Murthy, Anand T. (Indian Institute of Technology).

The leaderboard can be found  here

———————————————————————————————————————————–

Congratulations to you all, winning and non-winning teams! Thank you very much for participating in our Competition.

All teams are invited to submit their methodologies-papers (please see B5 above). All accepted papers will be part of the IEEE ICASSP 2023 proceedings.

We are looking forward to receiving your submissions!

References

If you want to reference the 3rd COV19D Competition or if you want to use the Competition datasets you must cite all following papers:

  • D. Kollias, et. al.: “AI-Enabled Analysis of 3-D CT Scans for Diagnosis of COVID-19 & its Severity“, 2023

@inproceedings{kollias2023ai, title={AI-Enabled Analysis of 3-D CT Scans for Diagnosis of COVID-19 \& its Severity}, author={Kollias, Dimitrios and Arsenos, Anastasios and Kollias, Stefanos}, booktitle={2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, pages={1–5}, year={2023}, organization={IEEE}}

  • A. Arsenos, et. al.: “Data-Driven Covid-19 Detection Through Medical Imaging“, 2023

@inproceedings{arsenos2023data, title={Data-Driven Covid-19 Detection Through Medical Imaging}, author={Arsenos, Anastasios and Davidhi, Andjoli and Kollias, Dimitrios and Prassopoulos, Panos and Kollias, Stefanos}, booktitle={2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)}, pages={1–5}, year={2023}, organization={IEEE}}

  • D. Kollias, et. al.: “A deep neural architecture for harmonizing 3-D input data analysis and decision making in medical imaging“, 2023

@article{kollias2023deep,title={A deep neural architecture for harmonizing 3-D input data analysis and decision making in medical imaging}, author={Kollias, Dimitrios and Arsenos, Anastasios and Kollias, Stefanos}, journal={Neurocomputing}, volume={542}, pages={126244}, year={2023}, publisher={Elsevier}}

  • D. Kollias, et. al.: “AI-MIA: COVID-19 Detection & Severity Analysis through Medical Imaging“, 2022

@inproceedings{kollias2022ai, title={Ai-mia: Covid-19 detection and severity analysis through medical imaging}, author={Kollias, Dimitrios and Arsenos, Anastasios and Kollias, Stefanos}, booktitle={European Conference on Computer Vision}, pages={677–690}, year={2022}, organization={Springer}}

  •     A. Arsenos, et. al.: “A Large Imaging Database and Novel Deep Neural Architecture for Covid-19 Diagnosis“, 2022

@inproceedings{arsenos2022large, title={A Large Imaging Database and Novel Deep Neural Architecture for Covid-19 Diagnosis}, author={Arsenos, Anastasios and Kollias, Dimitrios and Kollias, Stefanos}, booktitle={2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)}, pages={1–5}, year={2022}, organization={IEEE} }

  •      D. Kollias, et. al.: “MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysis“, 2021

@inproceedings{kollias2021mia, title={Mia-cov19d: Covid-19 detection through 3-d chest ct image analysis}, author={Kollias, Dimitrios and Arsenos, Anastasios and Soukissian, Levon and Kollias, Stefanos}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={537–544}, year={2021} }

  •      D. Kollias, et. al.: “Deep transparent prediction through latent representation analysis”, 2020

@article{kollias2020deep, title={Deep transparent prediction through latent representation analysis}, author={Kollias, Dimitrios and Bouas, N and Vlaxos, Y and Brillakis, V and Seferis, M and Kollia, Ilianna and Sukissian, Levon and Wingate, James and Kollias, S}, journal={arXiv preprint arXiv:2009.07044}, year={2020}}

  •  D. Kollias, et. al.: “Transparent Adaptation in Deep Medical Image Diagnosis”, 2020

@inproceedings{kollias2020transparent, title={Transparent Adaptation in Deep Medical Image Diagnosis.}, author={Kollias, Dimitris and Vlaxos, Y and Seferis, M and Kollia, Ilianna and Sukissian, Levon and Wingate, James and Kollias, Stefanos D}, booktitle={TAILOR}, pages={251–267}, year={2020}}

  •  D. Kollias, et. al.: “Deep neural architectures for prediction in healthcare”, 2018

@article{kollias2018deep, title={Deep neural architectures for prediction in healthcare}, author={Kollias, Dimitrios and Tagaris, Athanasios and Stafylopatis, Andreas and Kollias, Stefanos and Tagaris, Georgios}, journal={Complex \& Intelligent Systems}, volume={4}, number={2}, pages={119–131}, year={2018}, publisher={Springer}}