Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917714425020416 |
|---|---|
| author | Osorio, Pedro Jimenez-Perez, Guillermo Montalt-Tordera, Javier Hooge, Jens Duran-Ballester, Guillem Singh, Shivam Radbruch, Moritz Bach, Ute Schroeder, Sabrina Siudak, Krystyna Vienenkoetter, Julia Lawrenz, Bettina Mohammadi, Sadegh |
| author_facet | Osorio, Pedro Jimenez-Perez, Guillermo Montalt-Tordera, Javier Hooge, Jens Duran-Ballester, Guillem Singh, Shivam Radbruch, Moritz Bach, Ute Schroeder, Sabrina Siudak, Krystyna Vienenkoetter, Julia Lawrenz, Bettina Mohammadi, Sadegh |
| contents | Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) from 178.8 to 90.2. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively trains AI models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09792 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology Osorio, Pedro Jimenez-Perez, Guillermo Montalt-Tordera, Javier Hooge, Jens Duran-Ballester, Guillem Singh, Shivam Radbruch, Moritz Bach, Ute Schroeder, Sabrina Siudak, Krystyna Vienenkoetter, Julia Lawrenz, Bettina Mohammadi, Sadegh Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) from 178.8 to 90.2. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively trains AI models. |
| title | Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2312.09792 |