/MMAC_LaTIM_Solution

LaTIM Labs' solution in the MMAC2023 Challenge. 8th place in Task 1, 2nd place in Task 2, and 1st place in Task 3.

Primary LanguagePythonApache License 2.0Apache-2.0

MMAC_LaTIM_Solution

Here's the LaTIM team's solution in the MICCAI MMAC 2023 Challenge.

We are the TOP 8 of the Task 1-Classification of myopic maculopathy, the TOP 2 of the Task 2-Segmentation of myopic maculopathy plus lesions, and the TOP 1 of the Task 3-Prediction of spherical equivalent.

If you use our code, please cite: Automated Detection of Myopic Maculopathy in MMAC 2023: Achievements in Classification, Segmentation, and Spherical Equivalent Prediction.


Training

This table provides a brief description of our operators and detailed parameters for training. Unless otherwise specified, all experiments are conducted using reported configurations and parameters.

image

image

image

Inference

Submissions and weights for the validation and testing phases (four versions per task): Submissions_MMAC_LaTIM

Task 1 - Classification of myopic maculopathy

image

Task 2 - Segmentation of myopic maculopathy plus lesions

image

Task 3 - Prediction of spherical equivalent

image