Minimum Data, Maximum Impact: 20 annotated samples for explainable lung nodule classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913969691688960 |
|---|---|
| author | Gallée, Luisa Lisson, Catharina Silvia Lisson, Christoph Gerhard Drees, Daniela Weig, Felix Vogele, Daniel Beer, Meinrad Götz, Michael |
| author_facet | Gallée, Luisa Lisson, Catharina Silvia Lisson, Christoph Gerhard Drees, Daniela Weig, Felix Vogele, Daniel Beer, Meinrad Götz, Michael |
| contents | Classification models that provide human-interpretable explanations enhance clinicians' trust and usability in medical image diagnosis. One research focus is the integration and prediction of pathology-related visual attributes used by radiologists alongside the diagnosis, aligning AI decision-making with clinical reasoning. Radiologists use attributes like shape and texture as established diagnostic criteria and mirroring these in AI decision-making both enhances transparency and enables explicit validation of model outputs. However, the adoption of such models is limited by the scarcity of large-scale medical image datasets annotated with these attributes. To address this challenge, we propose synthesizing attribute-annotated data using a generative model. We enhance the Diffusion Model with attribute conditioning and train it using only 20 attribute-labeled lung nodule samples from the LIDC-IDRI dataset. Incorporating its generated images into the training of an explainable model boosts performance, increasing attribute prediction accuracy by 13.4% and target prediction accuracy by 1.8% compared to training with only the small real attribute-annotated dataset. This work highlights the potential of synthetic data to overcome dataset limitations, enhancing the applicability of explainable models in medical image analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00639 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Minimum Data, Maximum Impact: 20 annotated samples for explainable lung nodule classification Gallée, Luisa Lisson, Catharina Silvia Lisson, Christoph Gerhard Drees, Daniela Weig, Felix Vogele, Daniel Beer, Meinrad Götz, Michael Computer Vision and Pattern Recognition Classification models that provide human-interpretable explanations enhance clinicians' trust and usability in medical image diagnosis. One research focus is the integration and prediction of pathology-related visual attributes used by radiologists alongside the diagnosis, aligning AI decision-making with clinical reasoning. Radiologists use attributes like shape and texture as established diagnostic criteria and mirroring these in AI decision-making both enhances transparency and enables explicit validation of model outputs. However, the adoption of such models is limited by the scarcity of large-scale medical image datasets annotated with these attributes. To address this challenge, we propose synthesizing attribute-annotated data using a generative model. We enhance the Diffusion Model with attribute conditioning and train it using only 20 attribute-labeled lung nodule samples from the LIDC-IDRI dataset. Incorporating its generated images into the training of an explainable model boosts performance, increasing attribute prediction accuracy by 13.4% and target prediction accuracy by 1.8% compared to training with only the small real attribute-annotated dataset. This work highlights the potential of synthetic data to overcome dataset limitations, enhancing the applicability of explainable models in medical image analysis. |
| title | Minimum Data, Maximum Impact: 20 annotated samples for explainable lung nodule classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00639 |