Papers › From Semantic Segmentation of Natural Images to Medical Image Segmentation Using...

From Semantic Segmentation of Natural Images to Medical Image Segmentation Using ViT-Based Architectures

31 Jan 2025Structural, Syntactic, and Statistical Pattern Recognition 2025 1archive 2025-07-28

Alexandru Valentin Patrascu, Ciprian-Mihai Ceausescu, and Bogdan Alexe

We address the problem of medical image segmentation in the context of limited training data. Our approach builds on the capabilities of the Vision Transformer (ViT) and the recent Segmenter model, adapting them for the task of medical image segmentation. By leveraging Segmenter models pre-trained on moderately-sized datasets like ADE20K, we demonstrate their effectiveness when fine-tuned on smaller and scarce medical imaging datasets, specifically those for skin lesions and polyps. Employing our proposed training strategy, the adapted Segmenter model both matches and surpasses the current state-of-the-art on three key medical image datasets: ISIC2018 for skin lesions, and CVCClinicDB and ETIS-LaribPolypDB for polyps, while maintaining competitive performance on Kvasir-SEG and CVC ColonDB.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Image SegmentationLesion SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 SegMed Mean IoU 0.841 #6 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 SegMed mean Dice 0.911 #6 of 17 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB SegMed mIoU 0.902 #10 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB SegMed mean Dice 0.948 #10 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB SegMed mIoU 0.854 #4 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB SegMed mean Dice 0.921 #4 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB SegMed mIoU 0.879 #2 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB SegMed mean Dice 0.936 #2 of 25 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG SegMed mIoU 0.899 #4 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG SegMed mean Dice 0.947 #4 of 58 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.

Methods

Absolute Position EncodingsAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionSoftmaxTransformerVision Transformer

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