Abstract
Hallucinations are a major concern for the integration of ar-
tificial intelligence into medicine, although less explored in the realm of
medical image processing. Unlike problems in natural text understand-
ing and reasoning therewith, determining whether or not predictions de-
rived from biomedical images and signals is less intuitively clear. This
article suggests that topological errors could constitute hallucinations in
a way that can be more readily measured and thus regulated. Certain
of these properties for certain types of problems, such as biomedical sig-
nal segmentation, can be rephrased as linear temporal logic predicates,
a number of which can be explicitly enforced using probabilistic graph-
ical models. Our simulations show the potential of these explicitly con-
strained predicates for the case of automatic surgical phase recognition in
robot-assisted hysterectomy, improving accuracy by approximately 10%
while removing the vast majority of topological errors, suggesting that
mathematical guarantees of correctness can supplement other empirical
forms of regulating machine learning in medical image computing and
computer-assisted interventions.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/FAIMI-BRIDGE-EPIMI_007.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=450QYYPnpj&nesting=2&sort=date-desc
BibTex
@InProceedings{BaxJoh_Hallucinations_MICCAISAT2026,
author = { Baxter, John S. H. AND Jannin, Pierre},
title = { { Hallucinations and constraints : Regulating surgical workflow recognition beyond accuracy } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17279},
month = {pending},
page = {pending}
}