Article

Three multimodal large language models fail at clinically actionable breast pathology in three different directions

2026-06-22

Abstract excerpt

<h4>Background</h4> Breast cancer treatment depends on histopathological features, such as grade and receptor-defined subtype; however, specialist pathologist access is constrained when the workforce is limited. Commercial multimodal large language models (MLLMs) accept hematoxylin and eosin (H&E) image tiles through paid interfaces without local hardware or fine-tuning. However, prior pathology evaluations addre...

Topics

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

Identifiers and source

Literature Corpus work: 8a80641a-c5e1-50db-bef6-5681e412506a
DOI: 10.64898/2026.06.18.26355928

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Three multimodal large language models fail at clinically actionable breast pathology in three different directionsDOI 10.64898/2026.06.18.26355928Read

Performance of a Large Language Model in BI-RADS Classification of Ultrasound Based Breast LesionsSemantic proximity Read

Comparative Evaluation the Knowledge of Large Language Models about Response Evaluation Criteria in Solid Tumors?Semantic proximity Read

Employing Consensus-Based Reasoning with Locally Deployed LLMs for Enabling Structured Data Extraction from Surgical Pathology ReportsSemantic proximity Read

Data Extraction from Oncology Imaging Reports by Large Language Models: A Comparative Accuracy StudySemantic proximity Read

Automated ICD-O-3 Coding of Real-World Pathology Reports Using Self-Hosted Large Language ModelsSemantic proximity Read

Automated ACR TI-RADS Classification of Thyroid Nodules from Narrative Ultrasound Reports Using a Fine-Tuned Open-Source Language Model: A Reproducible and Low-Resource FrameworkSemantic proximity Read

Multimodal Fusion of Pathology Free-Text and Clinical Data Enhances Complication-Risk Discrimination After Implant-Based Breast ReconstructionSemantic proximity Read

Reasoning Beyond Accuracy: Expert Evaluation of Large Language Models in Diagnostic PathologySemantic proximity Read

A Retrospective Analysis of a Dermatology-Trained Multimodal Large Language Model's Diagnostic Accuracy in Pigmented Skin LesionsSemantic proximity Read

Leveraging Large Language Models in Gynecologic Oncology: A Systematic Review of Current Applications and ChallengesSemantic proximity Read

Large language models for extracting histopathologic diagnoses of colorectal cancer and dysplasia from electronic health recordsSemantic proximity Read

Learning the Language of Histopathology Images reveals Prognostic Subgroups in Invasive Lung Adenocarcinoma PatientsSemantic proximity Read