Saved in:
Bibliographic Details
Main Authors: Halici, Ahmet, Cebeci, Ece Tugba, Balci, Musa, Cini, Mustafa, Sokmen, Serkan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912911556870144
author Halici, Ahmet
Cebeci, Ece Tugba
Balci, Musa
Cini, Mustafa
Sokmen, Serkan
author_facet Halici, Ahmet
Cebeci, Ece Tugba
Balci, Musa
Cini, Mustafa
Sokmen, Serkan
contents Generating diagnostic text from histopathology whole slide images (WSIs) is challenging due to the gigapixel scale of the input and the requirement for precise, domain specific language. We propose a hierarchical vision language framework that combines a frozen pathology foundation model with a Transformer decoder for report generation. To make WSI processing tractable, we perform multi resolution pyramidal patch selection (downsampling factors 2^3 to 2^6) and remove background and artifacts using Laplacian variance and HSV based criteria. Patch features are extracted with the UNI Vision Transformer and projected to a 6 layer Transformer decoder that generates diagnostic text via cross attention. To better represent biomedical terminology, we tokenize the output using BioGPT. Finally, we add a retrieval based verification step that compares generated reports with a reference corpus using Sentence BERT embeddings; if a high similarity match is found, the generated report is replaced with the retrieved ground truth reference to improve reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16422
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model
Halici, Ahmet
Cebeci, Ece Tugba
Balci, Musa
Cini, Mustafa
Sokmen, Serkan
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Generating diagnostic text from histopathology whole slide images (WSIs) is challenging due to the gigapixel scale of the input and the requirement for precise, domain specific language. We propose a hierarchical vision language framework that combines a frozen pathology foundation model with a Transformer decoder for report generation. To make WSI processing tractable, we perform multi resolution pyramidal patch selection (downsampling factors 2^3 to 2^6) and remove background and artifacts using Laplacian variance and HSV based criteria. Patch features are extracted with the UNI Vision Transformer and projected to a 6 layer Transformer decoder that generates diagnostic text via cross attention. To better represent biomedical terminology, we tokenize the output using BioGPT. Finally, we add a retrieval based verification step that compares generated reports with a reference corpus using Sentence BERT embeddings; if a high similarity match is found, the generated report is replaced with the retrieved ground truth reference to improve reliability.
title Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.16422