CortiNet: A Physics-Perception Hybrid Cortical-Inspired Dual-Stream Network for Gallbladder Disease Diagnosis from Ultrasound

2026-02-01

AI Summary

This work addresses the challenges posed by low resolution and speckle noise in ultrasound imaging, which compromise the reliability of gallbladder disease diagnosis, and the impracticality of deploying existing deep models due to their large parameter counts. To this end, the authors propose CortiNet—a lightweight, dual-stream network inspired by the visual cortex—that decouples structural and textural information through physically interpretable multi-scale signal decomposition and perception-driven feature learning, respectively. A cortical-inspired late fusion mechanism integrates complementary cues from both streams. Innovatively embedding physical priors into the architecture enhances interpretability and noise robustness, particularly through a gradient-weighted class activation mapping module in the structural branch. Evaluated on a dataset of 10,692 images spanning nine gallbladder disease classes, CortiNet achieves 98.74% accuracy—significantly outperforming conventional convolutional models—while substantially reducing model parameters.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Ultrasound imaging is the primary diagnostic modality for detecting Gallbladder diseases due to its non-invasive nature, affordability, and wide accessibility. However, the low resolution and speckle noise inherent to ultrasound images hinder diagnostic reliability, prompting the use of large convolutional neural networks that are difficult to deploy in routine clinical settings. In this work, we propose CortiNet, a lightweight, cortical-inspired dual-stream neural architecture for gallbladder disease diagnosis that integrates physically interpretable multi-scale signal decomposition with perception-driven feature learning. Inspired by parallel processing pathways in the human visual cortex, CortiNet explicitly separates low-frequency structural information from high-frequency perceptual details and processes them through specialized encoding streams. By operating directly on structured, frequency-selective representations rather than raw pixel intensities, the architecture embeds strong physics-based inductive bias, enabling efficient feature learning with a significantly reduced parameter footprint. A late-stage cortical-style fusion mechanism integrates complementary structural and textural cues while preserving computational efficiency. Additionally, we propose a structure-aware explainability framework wherein gradient-weighted class activation mapping is only applied to the structural branch of the proposed CortiNet architecture. This choice allows the model to only focus on the structural features, making it robust against speckle noise. We evaluate CortiNet on 10,692 expert-annotated images spanning nine clinically relevant gallbladder disease categories. Experimental results demonstrate that CortiNet achieves high diagnostic accuracy (98.74%) with only a fraction of the parameters required by conventional deep convolutional models.

Problem

• ultrasound imaging
• gallbladder disease diagnosis
• speckle noise
• low resolution
• model deployability

Innovation

• dual-stream network
• physics-perception hybrid
• cortical-inspired architecture
• structure-aware explainability
• frequency-selective representation