Article

SydneyMTL: Interpretable Multi-Task Learning for Complete Sydney System Assessment in Gastric Biopsies

2026-02-18

Abstract excerpt

<h4>Summary</h4> The Updated Sydney System (USS) provides a standardized framework for grading gastritis and stratifying gastric cancer risk. However, subjective observer variability and labor-intensive workflows impede its routine clinical use. To address these challenges, we developed SydneyMTL, a multi-task deep learning framework that uses Multiple Instance Learning (MIL) with task-specific attention pooling...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9a6ebc3a-8a9b-5b4f-8910-738ded8c6610
DOI: 10.64898/2026.02.17.26346304

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

SydneyMTL: Interpretable Multi-Task Learning for Complete Sydney System Assessment in Gastric BiopsiesDOI 10.64898/2026.02.17.26346304Read

Dual-stage AI system for Pathologist-Free Tumor Detection and subtyping in Oral Squamous Cell CarcinomaSemantic proximity Read

Accurate Diagnosis of Colorectal Cancer Based on Histopathology Images Using Artificial IntelligenceSemantic proximity Read

GutCore: An Endoscopy Foundation Model for Whole-Case Gastric Cancer AnalysisSemantic proximity Read

Beyond Binary: Four-Class Risk Stratification from Gastrointestinal Endoscopy Using Asymmetric-Cost Lightweight CNN–Transformer LearningSemantic proximity Read

Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal PathologySemantic proximity Read

A Clinical Benchmark of Foundation Models: Towards Reliable Morphological Subtyping and Cancer Detection on Real-World Barrett’s Esophagus DataSemantic proximity Read

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological imagesSemantic proximity Read

Whole-Case Artificial Intelligence for Diagnostic Escalation in Endoscopically Suspected Borrmann Type IV Gastric CancerSemantic proximity Read

Prediction of <i>TP53</i> biomarkers and survival outcomes from whole slide images using a vision transformer-based multi-instance learning frameworkSemantic proximity Read

Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language AlignmentSemantic proximity Read

Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesionsSemantic proximity Read

A foundation model for generalizable cancer diagnosis and survival prediction from histopathological imagesSemantic proximity Read