Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis
This paper introduces Spatially Grounded Concept Bottleneck Models (SG-CBM), which use coarse lesion delineations as weak supervision to encourage anatomically plausible concept evidence in breast ultrasound diagnosis. The model defines two clinically relevant zones from lesion masks: in-lesion region for morphology and posterior acoustic band for posterior phenomena. Results show improved diagnostic AUROC and concept macro-AUROC with better spatial alignment. A Train-corrupt/Test-clean stress test highlights the impact of supervision quality on model trustworthiness.
-->
[Submitted on 22 Jul 2026]
Title:Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis
View a PDF of the paper titled Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis, by Moshiur Rahman Tonmoy and 3 other authors
View PDF HTML (experimental)
Abstract:Concept Bottleneck Models provide interpretable-by-design predictions by mediating diagnosis through human-understandable concepts, but in medical imaging, their trustworthiness is often limited by the quality and granularity of available supervision. In particular, predicted concept activations can be driven by irrelevant regions, leading to spatially unfaithful explanations. We study a data-centric spatially grounded Concept Bottleneck Model (SG-CBM) that leverages coarse lesion delineations as weak supervision to encourage anatomically plausible concept evidence. For breast ultrasound, we derive two clinically motivated zones from each lesion mask: (i) an in-lesion region of interest for morphology-related concepts and (ii) a posterior acoustic band for posterior phenomena. We train concept maps using a grouped spatial grounding objective and preserve semantic faithfulness with a linear bottleneck classifier. Across five-fold stratified group cross-validation, the proposed SG-CBM improves diagnostic AUROC and concept macro-AUROC while markedly increasing spatial alignment of concept evidence. We also perform a Train-corrupt/Test-clean annotation-quality stress test to quantify the impact of supervision quality on diagnosis and spatial faithfulness. Overall, the results underscore the need for data-quality-aware supervision design and systematic trustworthiness validation for deployable healthcare AI systems.
Comments: Accepted to the Workshop on Data Quality Aware, High-Performance, and Trustworthy AI Systems for Healthcare at IEEE/ACM CHASE 2026
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.20691 [cs.CV]
(or arXiv:2607.20691v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.20691
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Moshiur Rahman Tonmoy [view email] [v1] Wed, 22 Jul 2026 19:45:59 UTC (2,411 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis, by Moshiur Rahman Tonmoy and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-07
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)