| layout | title | description | permalink | bibliography | toc | _styles | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
distill |
TFM4MedIA |
Transferring Foundation Models for Multi-center Real-World Medical Image Analysis |
/track1/ |
reference.bib |
|
d-article {
contain: layout style;
overflow-x: hidden;
border-top: 1px solid rgba(0, 0, 0, 0.1);
padding-top: 2rem;
color: rgba(0, 0, 0, 0.8);
}
d-article > * {
grid-column: text;
}
|
{% include figure.liquid loading="eager" path="/assets/img/tfm4media.png" class="img-fluid" zoomable=true caption="Figure 1." %}
While foundation models like the Segment Anything Model (SAM) have demonstrated efficacy in various medical image analysis tasks, their performance on real-world data remains underexplored. Specifically, these models are typically trained for normal and large targets such as the liver and lungs, yet real-world data often originates from different centers with diverse modalities. Furthermore, the application of foundation models to complicated Regions of Interest (ROIs), like lesions or scars, poses additional challenges due to their small size and irregular shapes. Hence, developing effective and efficient transfer learning approaches to fully utilize those foundation models for real world medical image segmentation is of great values.
In this track, we encourage participants to design effective transfer learning approaches to exploit the knowledge from existed foundation models efficiently and make them more effective in four segmentation tasks, including Myocardial Pathology Segmentation in MyoPS++ track, Liver Segmentation in LiQA track, Whole Heart Segmentation in WHS++ track and Left Atrial and Scar Segmentation in LAScarQS++ track.
Note: To address this task, participants are encouraged to leverage external data.
Multi-center datasets are provided for four sub-tasks. More detailed data information can be found here for Myocardial Pathology Segmentation, Liver Segmentation, Whole Heart Segmentation and Left Atrial and Scar Segmentation.
1). Myocardial Pathology Segmentation
| Center | Num. patients | Sequences | Manual labels |
|---|---|---|---|
| 1 | 81 | LGE | Scar, left ventricle and myocardium |
| 2 | 50 | LGE, T2 and bSSFP | Scar, edema, left ventricle, myocardium and right ventricle |
| 3 | 45 | LGE, T2 and bSSFP | Scar, edema, left ventricle, myocardium and right ventricle |
| 5 | 07 | LGE and bSSFP | Scar, left ventricle, myocardium and and right ventricle |
| 6 | 09 | LGE and bSSFP | Scar, left ventricle, myocardium and and right ventricle |
| 7 | 08 | LGE and bSSFP | Scar, left ventricle, myocardium and and right ventricle |
| Vendor | Center | Num. studies | Num. Annotations |
|---|---|---|---|
| A | A | 100 | 10 |
| B | B1 | 100 | 10 |
| B | B2 | 50 | 10 |
| Center | Num. patients | Modalities |
|---|---|---|
| A | 20 | CT |
| B | 20 | CT |
| C/D | 20 | MRI |
| E | 26 | MRI |
4). Left Atrial and Scar Segmentation
| Center | Modality | Num. task1 | Num. task2 |
|---|---|---|---|
| A | LGE MRI | 60 | 130 |
1). Myocardial Pathology Segmentation
| Center | Num. patients | Sequences | Manual labels |
|---|---|---|---|
| 4 | 25 | LGE, T2 and bSSFP | Scar, edema, left ventricle, myocardium and right ventricle |
| Vendor | Center | Num. studies | Num. Annotations |
|---|---|---|---|
| A | A | 10 | 10 |
| B | B1 | 10 | 10 |
| B | B2 | 10 | 10 |
| Center | Num. patients | Modalities |
|---|---|---|
| A | 20 | CT |
| B | 10 | CT |
| C/D | 20 | MRI |
4). Left Atrial and Scar Segmentation
| Center | Modality | Num. task1 | Num. task2 |
|---|---|---|---|
| A | LGE MRI | 10 | 10 |
| C | LGE MRI | 0 | 10 |
1). Myocardial Pathology Segmentation
| Center | Num. patients | Sequences | Manual labels |
|---|---|---|---|
| 4 | 25 | LGE, T2 and bSSFP | Scar, edema, left ventricle, myocardium and right ventricle |
The 160 test cases corresponded to 120 new cases from the vendors provided in the training set and 40 additional cases from a third unseen center, that were tested for model generalizability.
| Vendor | Center | Num. studies |
|---|---|---|
| A | A | 40 |
| B | B1 | 40 |
| B | B2 | 40 |
| C (new) | C | 40 |
| Center | Num. patients | Modalities |
|---|---|---|
| A | 20 | CT |
| B | 14 | CT |
| C/D | 20 | MRI |
| F | 16 | MRI |
4). Left Atrial and Scar Segmentation
| Center | Modality | Num. task1 | Num. task2 |
|---|---|---|---|
| A | LGE MRI | 24 | 14 |
| B | LGE MRI | 0 | 20 |
| C | LGE MRI | 0 | 10 |
- Only points or bounding boxes are acceptable as prompts. Participants can generate prompts based on the segmentation ground truth by themselves for the training dataset.
- For validation and testing testing, no more than 5 points and 1 bounding box are provided by organizers for each class as prompts. An example can be seen in the Figure 2.
Dice Similarity Coefficient (DSC), Hausdorff Distance (HD).
The overall performance across all sub-tasks are considered for ranking:
- Firstly, for each sub-task, the results will be ranked according to the Dice score on in-distribution (seen centre) and out-of-distribution (OOD, unseen centre) dataset, respectively.
- Then the ranking results of all sub-tasks are averaged as the final rank.
This ranking approach encourage the participants to develop methods from foundation models to be consistently effective across all tasks as well as on OOD datasets.
- Publicly available data and pretrained model are allowed.
Please register here to participate in the challenge and get access to the dataset!
After registration, we will assign participants an account to login into our TFM4MedIA evaluation platform. Participants can directly upload your predictions on the validation data (in nifty format) via the website. Note that evaluation of validation data will be allowed up to 10 times for each task per team. For fair comparison, the test dataset will remain unseen. Participants need to submit their docker models for testing.
You should submit using the Conference Management Toolkit (CMT) website.
- Upon accessing the submission platform, please select the TFM4MedIA track after clicking the Create new submission button.
- Papers must be submitted electronically in searchable pdf format following the guidelines for authors and LaTeX and MS Word templates available at Lecture Notes in Computer Science.
- We recommend that manuscripts be structured to include up to 8 pages of content (text, figures, and tables), plus up to 2 pages for references. To provide flexibility, the submission may be extended up to a maximum of 12 pages, including both content and references.
The schedule for this track is as follows. All deadlines(DDLs) are on 23:59 in Pacific Standard Time.
| Training Data Release | May 10, 2024 |
|---|---|
| Validation Phase | |
| Test Phase | |
| Abstract Submission | |
| Paper Submission | August 15, 2024 (DDL) |
| Notification | September 15, 2024 |
| Camera Ready | September 25, 2024 (DDL) |
| Workshop (Half-Day) | October 10, 2024 |
Please cite these papers when you use the data for publications:
@article{Wu2023SemiSL,
author={Wu, Fuping and Zhuang, Xiahai},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Minimizing Estimated Risks on Unlabeled Data: A New Formulation for Semi-Supervised Medical Image Segmentation},
year={2023},
volume={45},
number={5},
pages={6021-6036},
}
@article{GAO2023BayeSeg,
title = {BayeSeg: Bayesian modeling for medical image segmentation with interpretable generalizability},
journal = {Medical Image Analysis},
volume = {89},
pages = {102889},
year = {2023},
author = {Shangqi Gao and Hangqi Zhou and Yibo Gao and Xiahai Zhuang},
}If you have any problems about this track, please contact Dr. Fuping Wu or Dr. Shangqi Gao.