Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2308.15618 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913948928835584 |
|---|---|
| author | Choudhary, Anirudh Aouad, Mosbah Saboo, Krishnakant Hwang, Angelina Kechter, Jacob Bordeaux, Blake Bhullar, Puneet DiCaudo, David Nelson, Steven Comfere, Nneka Johnson, Emma Sokumbi, Olayemi Sluzevich, Jason Swanson, Leah Murphree, Dennis Mangold, Aaron Iyer, Ravishankar |
| author_facet | Choudhary, Anirudh Aouad, Mosbah Saboo, Krishnakant Hwang, Angelina Kechter, Jacob Bordeaux, Blake Bhullar, Puneet DiCaudo, David Nelson, Steven Comfere, Nneka Johnson, Emma Sokumbi, Olayemi Sluzevich, Jason Swanson, Leah Murphree, Dennis Mangold, Aaron Iyer, Ravishankar |
| contents | Squamous cell carcinoma (SCC) is the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mortality. SCC grading using whole slide images is inherently challenging due to the lack of a reliable protocol and substantial tissue heterogeneity. We propose RACR-MIL, the first weakly-supervised SCC grading approach achieving robust generalization across multiple anatomies (skin, head and neck, lung). RACR-MIL is an attention-based multiple-instance learning framework that enhances grade-relevant contextual representation learning and addresses tumor heterogeneity through two key innovations: (1) a hybrid WSI graph that captures both local tissue context and non-local phenotypical dependencies between tumor regions, and (2) a rank-ordering constraint in the attention mechanism that consistently prioritizes higher-grade tumor regions, aligning with pathologists diagnostic process. Our model achieves state-of-the-art performance across multiple SCC datasets, achieving 3-9% higher grading accuracy, resilience to class imbalance, and up to 16% improved tumor localization. In a pilot study, pathologists reported that RACR-MIL improved grading efficiency in 60% of cases, underscoring its potential as a clinically viable cancer diagnosis and grading assistant. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_15618 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images Choudhary, Anirudh Aouad, Mosbah Saboo, Krishnakant Hwang, Angelina Kechter, Jacob Bordeaux, Blake Bhullar, Puneet DiCaudo, David Nelson, Steven Comfere, Nneka Johnson, Emma Sokumbi, Olayemi Sluzevich, Jason Swanson, Leah Murphree, Dennis Mangold, Aaron Iyer, Ravishankar Computer Vision and Pattern Recognition Machine Learning Squamous cell carcinoma (SCC) is the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mortality. SCC grading using whole slide images is inherently challenging due to the lack of a reliable protocol and substantial tissue heterogeneity. We propose RACR-MIL, the first weakly-supervised SCC grading approach achieving robust generalization across multiple anatomies (skin, head and neck, lung). RACR-MIL is an attention-based multiple-instance learning framework that enhances grade-relevant contextual representation learning and addresses tumor heterogeneity through two key innovations: (1) a hybrid WSI graph that captures both local tissue context and non-local phenotypical dependencies between tumor regions, and (2) a rank-ordering constraint in the attention mechanism that consistently prioritizes higher-grade tumor regions, aligning with pathologists diagnostic process. Our model achieves state-of-the-art performance across multiple SCC datasets, achieving 3-9% higher grading accuracy, resilience to class imbalance, and up to 16% improved tumor localization. In a pilot study, pathologists reported that RACR-MIL improved grading efficiency in 60% of cases, underscoring its potential as a clinically viable cancer diagnosis and grading assistant. |
| title | RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2308.15618 |