Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Oh, Ji-Hun, Falahkheirkhah, Kianoush, Cheville, John, Bhargava, Rohit
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914407336902656
author Oh, Ji-Hun
Falahkheirkhah, Kianoush
Cheville, John
Bhargava, Rohit
author_facet Oh, Ji-Hun
Falahkheirkhah, Kianoush
Cheville, John
Bhargava, Rohit
contents Histopathologic analysis of stained tissue remains central to biomedical research and clinical care. Virtual staining (VS) offers a promising alternative, with potential to reduce costs and streamline workflows, yet hallucinations pose serious risks to clinical reliability. Here, we formalize the problem of hallucination detection in VS and propose a scalable post-hoc method: Neural Hallucination Precursor (NHP), which leverages the generator's latent space to preemptively flag hallucinations. Extensive experiments across diverse VS tasks show NHP is both effective and robust. Critically, we also find that models with fewer hallucinations do not necessarily offer better detectability, exposing a gap in current VS evaluation and underscoring the need for hallucination detection benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15060
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline
Oh, Ji-Hun
Falahkheirkhah, Kianoush
Cheville, John
Bhargava, Rohit
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Histopathologic analysis of stained tissue remains central to biomedical research and clinical care. Virtual staining (VS) offers a promising alternative, with potential to reduce costs and streamline workflows, yet hallucinations pose serious risks to clinical reliability. Here, we formalize the problem of hallucination detection in VS and propose a scalable post-hoc method: Neural Hallucination Precursor (NHP), which leverages the generator's latent space to preemptively flag hallucinations. Extensive experiments across diverse VS tasks show NHP is both effective and robust. Critically, we also find that models with fewer hallucinations do not necessarily offer better detectability, exposing a gap in current VS evaluation and underscoring the need for hallucination detection benchmarks.
title Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.15060