Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914877712367616 |
|---|---|
| author | Li, Mingjie Lin, Haokun Qiu, Liang Liang, Xiaodan Chen, Ling Elsaddik, Abdulmotaleb Chang, Xiaojun |
| author_facet | Li, Mingjie Lin, Haokun Qiu, Liang Liang, Xiaodan Chen, Ling Elsaddik, Abdulmotaleb Chang, Xiaojun |
| contents | Due to the common content of anatomy, radiology images with their corresponding reports exhibit high similarity. Such inherent data bias can predispose automatic report generation models to learn entangled and spurious representations resulting in misdiagnostic reports. To tackle these, we propose a novel \textbf{Co}unter\textbf{F}actual \textbf{E}xplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking ``what if'' scenarios. By leveraging this concept, CoFE can learn non-spurious visual representations by contrasting the representations between factual and counterfactual images. Specifically, we derive counterfactual images by swapping a patch between positive and negative samples until a predicted diagnosis shift occurs. Here, positive and negative samples are the most semantically similar but have different diagnosis labels. Additionally, CoFE employs a learnable prompt to efficiently fine-tune the pre-trained large language model, encapsulating both factual and counterfactual content to provide a more generalizable prompt representation. Extensive experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports and outperform in terms of language generation and clinical efficacy metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14474 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive Learning with Counterfactual Explanations for Radiology Report Generation Li, Mingjie Lin, Haokun Qiu, Liang Liang, Xiaodan Chen, Ling Elsaddik, Abdulmotaleb Chang, Xiaojun Computer Vision and Pattern Recognition Due to the common content of anatomy, radiology images with their corresponding reports exhibit high similarity. Such inherent data bias can predispose automatic report generation models to learn entangled and spurious representations resulting in misdiagnostic reports. To tackle these, we propose a novel \textbf{Co}unter\textbf{F}actual \textbf{E}xplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking ``what if'' scenarios. By leveraging this concept, CoFE can learn non-spurious visual representations by contrasting the representations between factual and counterfactual images. Specifically, we derive counterfactual images by swapping a patch between positive and negative samples until a predicted diagnosis shift occurs. Here, positive and negative samples are the most semantically similar but have different diagnosis labels. Additionally, CoFE employs a learnable prompt to efficiently fine-tune the pre-trained large language model, encapsulating both factual and counterfactual content to provide a more generalizable prompt representation. Extensive experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports and outperform in terms of language generation and clinical efficacy metrics. |
| title | Contrastive Learning with Counterfactual Explanations for Radiology Report Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.14474 |