Explainable Continuous-Time Mask Refinement with Local Self-Similarity Priors for Medical Image Segmentation

Rajdeep Chatterjee; Sudip Chakrabarty; Trishaani Acharjee

cs.CVFeb 28, 2026

Explainable Continuous-Time Mask Refinement with Local Self-Similarity Priors for Medical Image Segmentation

Authors: Rajdeep Chatterjee, Sudip Chakrabarty, Trishaani Acharjee

Organizations: School of Computer Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, India · AmygdalaAI-India Lab, Bhubaneswar, India

Abstract

Accurate semantic segmentation of foot ulcers is essential for automated wound monitoring, yet boundary delineation remains challenging due to tissue heterogeneity and poor contrast with surrounding skin. To overcome the limitations of standard intensity-based networks, we present LSS-LTCNet:an ante-hoc explainable framework synergizing deterministic structural priors with continuous-time neural dynamics. Our architecture departs from traditional black-box models by employing a Local Self-Similarity (LSS) mechanism that extracts dense, illumination-invariant texture descriptors to explicitly disentangle necrotic tissue from background artifacts. To enforce topological precision, we introduce a Liquid Time-Constant (LTC) refinement module that treats boundary evolution as an ODEgoverned dynamic system, iteratively refining masks over continuous time-steps. Comprehensive evaluation on the MICCAI FUSeg dataset demonstrates that LSS-LTCNet achieves state-of-the-art boundary alignment, securing a peak Dice score of 86.96% and an exceptional 95th percentile Hausdorff Distance (HD95) of 8.91 pixels. Requiring merely 25.70M parameters, the model significantly outperforms heavier U-Net and transformer baselines in efficiency. By providing inherent visual audit trails alongside high-fidelity predictions, LSS-LTCNet offers a robust and transparent solution for computer-aided diagnosis in mobile healthcare (mHealth) settings.

Figures & tables

Figure 1: The proposed LSS-LTCNet, illustrating the integration of the ResNet-34 encoder, Additive LSS Fusion, LTC Refinement Loop, and Deep Supervision Decoder.

Figure 2: Clinical samples and corresponding ground truth masks from the dataset.

Method	Params (M)	FLOPs (G)	Dice (%) ( $\uparrow$ )	IoU (%) ( $\uparrow$ )	HD95 ( $\downarrow$ )
VGG16-UNet	69.31	42.19	84.88	77.29	14.72
ViT-UNet	130.22	102.00	80.16	71.32	15.32
UNet	31.78	374.34	84.04	76.23	13.31
Mask R-CNN	90.44	67.13	83.97	76.42	12.89
ResNet101-UNet	267.62	112.79	84.92	77.73	13.03
U2Seg	86.47	88.46	75.85	70.13	16.07

Table 1: Quantitative comparison of the proposed LSS-LTCNet against state-of-the-art (SOTA) methods.

Model Variation	LSS	LTC	BAL	Dice (%)( $\uparrow$ )	IoU (%)( $\uparrow$ )	Params (M)
Baseline (ResNet-34 + U-Net)				$85.22$	$77.56$	24.87
Baseline + LSS	✓			$83.51$	$75.51$	25.12
Baseline + LTC		✓		$83.29$	$75.22$	25.45
LSS-LTCNet (w/o BAL)	✓	✓		$76.18$	$69.74$	25.70
LSS-LTCNet (Proposed)	✓	✓	✓	$\mathbf{86.96}$	$\mathbf{79.54}$	$\mathbf{25.70}$

Table 2: Ablation study progressively adding LSS, LTC, and BAL to the baseline.

Figure 3: Qualitative segmentation results of LSS-LTCNet on the FUSeg validation set. Left to right: input image, ground truth, predicted mask, and prediction overlay (red). The model demonstrates precise boundary delineation across diverse skin tones, lighting conditions, and wound morphologies.

Figure 4: Visualizing inherent explainability: LSS Mean, Max, and Boundary (Std) maps demonstrate how the network identifies tissue homogeneity and sharp perimeter transitions.

Medical Image Segmentation

Medical image segmentation delineates organs, lesions, and other structures in scans to support measurement, diagnosis, treatment planning, and research.

See all 786 papers

LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation
Aug 26, 2026Karen Sanchez, Carlos Hinojosa, Albert A. Ávila +5Medical Image Segmentation Semi-Supervised Medical Image Segmentation
King Abdullah University of Science and Technology (KAUST), Saudi Arabia · Subred Norte E.S.E, Hospital Simón Bolívar, Colombia · Universidad del Rosario, Bogotá, Colombia
Do Diabetic Foot Ulcer Segmentation Models Generalize? A Cross-Dataset Benchmark of CNN and Transformer Architectures
Jun 27, 2026Abderrahmane BenfatahMedical Diagnosis Medical Image Segmentation
King Saud University, Riyadh, Saudi Arabia
MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
Apr 22, 2026Md Maklachur Rahman, Soon Ki Jung, Tracy HammondMamba Multi-Scale Feature Fusion
Texas A&M University, College Station, TX, USA · Kyungpook National University, Daegu, South Korea

Aug 26, 2026J/K move · Enter open · S save

LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation

Karen Sanchez, Carlos Hinojosa, Albert A. Ávila, Andrea C. Riano-Rojas+4

King Abdullah University of Science and Technology (KAUST), Saudi Arabia · Subred Norte E.S.E, Hospital Simón Bolívar, Colombia · Universidad del Rosario, Bogotá, Colombia

Medical Image Segmentation Semi-Supervised Medical Image Segmentation Longitudinal Medical Image Analysis

Open paper AskPDF arXiv

Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guiding treatment decisions. However, pixel-level annotations are costly, and multi-tissue wound datasets remain scarce, particularly for neglected diseases such as leprosy. We introduce LUTSeg, a longitudinal chronic ulcer dataset comprising 141 images from 39 patients with wound masks and five tissue categories annotated by five expert clinicians, including a multi-expert gold-standard subset for inter-rater agreement analysis. To establish an initial benchmark for LUTSeg, we further propose TiSage, a semi-supervised tissue segmentation framework that integrates multi-scale semantic priors from a frozen medical vision-language model within a teacher-student architecture. We evaluate TiSage on LUTSeg and DFUTissue, showing improvements over supervised and semi-supervised baselines in most low-label settings. Code & data: https://github.com/carlosh93/TiSage

Abstract

Medical Image Segmentation

Explore similar work

LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation

Do Diabetic Foot Ulcer Segmentation Models Generalize? A Cross-Dataset Benchmark of CNN and Transformer Architectures

MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation