Unraveling a histopathological needle-in-haystack problem: exploring the challenges of detecting tumor budding in colorectal carcinoma histology
Background: In this study focusing on colorectal carcinoma (CRC), we address the imperative task of predicting post-surgery treatment needs by identifying crucial tumor features within whole slide images of solid tumors, analogous to locating a needle in a histological haystack. We evaluate two appr...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
22 January 2024
|
| In: |
Applied Sciences
Year: 2024, Volume: 14, Issue: 2 |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app14020949 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.3390/app14020949 Verlag, kostenfrei, Volltext: https://www.webofscience.com/api/gateway?GWVersion=2&SrcAuth=DOISource&SrcApp=WOS&KeyAID=10.3390%2Fapp14020949&DestApp=DOI&SrcAppSID=EUW1ED0A5BJ6f1gfv6ICbMpdNbFux&SrcJTitle=APPLIED+SCIENCES-BASEL&DestDOIRegistrantName=MDPI+AG 
|
| Author Notes: | Daniel Rusche, Nils Englert, Marlen Runz, Svetlana Hetjens, Cord Langner, Timo Gaiser and Cleo-Aron Weis |
| Summary: | Background: In this study focusing on colorectal carcinoma (CRC), we address the imperative task of predicting post-surgery treatment needs by identifying crucial tumor features within whole slide images of solid tumors, analogous to locating a needle in a histological haystack. We evaluate two approaches to address this challenge using a small CRC dataset. Methods: First, we explore a conventional tile-level training approach, testing various data augmentation methods to mitigate the memorization effect in a noisy label setting. Second, we examine a multi-instance learning (MIL) approach at the case level, adapting data augmentation techniques to prevent over-fitting in the limited data set context. Results: The tile-level approach proves ineffective due to the limited number of informative image tiles per case. Conversely, the MIL approach demonstrates success for the small dataset when coupled with post-feature vector creation data augmentation techniques. In this setting, the MIL model accurately predicts nodal status corresponding to expert-based budding scores for these cases. Conclusions: This study incorporates data augmentation techniques into a MIL approach, highlighting the effectiveness of the MIL method in detecting predictive factors such as tumor budding, despite the constraints of a limited dataset size. |
|---|---|
| Item Description: | Gesehen am 17.10.2024 |
| Physical Description: | Online Resource |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app14020949 |