Papers › Training on Polar Image Transformations Improves Biomedical Image Segmentation

Training on Polar Image Transformations Improves Biomedical Image Segmentation

29 Sep 2021IEEE Access 2021 9archive 2025-07-28

Marin Benčević, Irena Galić, Marija Habijan, Danilo Babin

A key step in medical image-based diagnosis is image segmentation. A common use case for medical image segmentation is the identification of single structures of an elliptical shape. Most organs like the heart and kidneys fall into this category, as well as skin lesions, polyps, and other types of abnormalities. Neural networks have dramatically improved medical image segmentation results, but still require large amounts of training data and long training times to converge. In this paper, we propose a general way to improve neural network segmentation performance and data efficiency on medical imaging segmentation tasks where the goal is to segment a single roughly elliptically distributed object. We propose training a neural network on polar transformations of the original dataset, such that the polar origin for the transformation is the center point of the object. This results in a reduction of dimensionality as well as a separation of segmentation and localization tasks, allowing the network to more easily converge. Additionally, we propose two different approaches to obtaining an optimal polar origin: (1) estimation via a segmentation trained on non-polar images and (2) estimation via a model trained to predict the optimal origin. We evaluate our method on the tasks of liver, polyp, skin lesion, and epicardial adipose tissue segmentation. We show that our method produces state-of-the-art results for lesion, liver, and polyp segmentation and performs better than most common neural network architectures for biomedical image segmentation. Additionally, when used as a pre-processing step, our method generally improves data efficiency across datasets and neural network architectures.

Paper PDF Code

Code

marinbenc/medical-polar-training pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Segmentation Lesion Segmentation Liver Segmentation Medical Image Segmentation Segmentation Semantic Segmentation Skin Cancer Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Lesion Segmentation	ISIC 2018	Polar Res-U-Net++	mean Dice	0.9253	#1 of 17	Archive leaderboard	report
Liver Segmentation	LiTS2017	Polar U-Net	Dice	93.02	#1 of 9	Archive leaderboard	report
Liver Segmentation	LiTS2017	Polar U-Net	IoU	89.85	#1 of 9	Archive leaderboard	report
Medical Image Segmentation	CVC-ClinicDB	Polar U-Net	mIoU	0.8977	#24 of 48	Archive leaderboard	report
Medical Image Segmentation	CVC-ClinicDB	Polar U-Net	mean Dice	0.9374	#24 of 48	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections