Explainable Weakly-Supervised Cell Nuclei Segmentation by Canonical Shape Learning and Transformation

Pedro Costa, Alex Gaudio, Aurélio Campilho, Jaime S Cardoso

Show abstract - Show schedule - Proceedings - PDF - Reviews

Microscopy images have been increasingly analyzed quantitatively in biomedical research. Segmenting individual cell nucleus is an important step as many research studies involve counting cells and analysing their shape. We propose a novel weakly supervised instance segmentation method that is trained with image segmentation masks only. Our system is composed of 2 models: an implicit shape Multi-Layer Perceptron (MLP) that learns the shape of the nuclei in canonical coordinates; and 2) an encoder that predicts the parameters of the affine transformation to deform the canonical shape into the correct location, scale and orientation in the image. Our system is explainable, as the implicit shape MLP learns that the canonical shape of the cell nuclei is a circle, and interpretable as the output of the encoder are parameters of affine transformations. We obtain image segmentation performance close to DeepLabV3 and, additionally, obtain an F1-score$_{IoU=0.5}$ of $68.47\%$ at the instance segmentation task, even though the system was trained with image segmentations.
Hide abstract

Thursday 7th July
Poster Session 2.1 - onsite 15:20 - 16:20, virtual 11:00 - 12:00 (UTC+2)
Hide schedule