Marme, Frederik and Krieghoff-Henning, Eva and Gerber, Bernd and Schmitt, Max and Zahm, Dirk -Michael and Bauerschlag, Dirk and Forstbauer, Helmut and Hildebrandt, Guido and Ataseven, Beyhan and Brodkorb, Tobias and Denkert, Carsten and Stachs, Angrit and Krug, David and Heil, Joerg and Golatta, Michael and Kuehn, Thorsten and Nekljudova, Valentina and Gaiser, Timo and Schoenmehl, Rebecca and Brochhausen, Christoph and Loibl, Sibylle and Reimer, Toralf and Brinker, Titus J. (2023) Deep learning to predict breast cancer sentinel lymph node status on INSEMA histological images. EUROPEAN JOURNAL OF CANCER, 195: 113390. ISSN 0959-8049, 1879-0852
Full text not available from this repository. (Request a copy)Abstract
Background: Sentinel lymph node (SLN) status is a clinically important prognostic biomarker in breast cancer and is used to guide therapy, especially for hormone receptor-positive, HER2-negative cases. However, invasive lymph node staging is increasingly omitted before therapy, and studies such as the randomised Intergroup Sentinel Mamma (INSEMA) trial address the potential for further de-escalation of axillary surgery. Therefore, it would be helpful to accurately predict the pretherapeutic sentinel status using medical images.Methods: Using a ResNet 50 architecture pretrained on ImageNet and a previously successful strategy, we trained deep learning (DL)-based image analysis algorithms to predict sentinel status on hematoxylin/eosin-stained images of predominantly luminal, primary breast tumours from the INSEMA trial and three additional, independent cohorts (The Cancer Genome Atlas (TCGA) and cohorts from the University hospitals of Mannheim and Regensburg), and compared their performance with that of a logistic regression using clinical data only. Performance on an INSEMA hold-out set was investigated in a blinded manner.Results: None of the generated image analysis algorithms yielded significantly better than random areas under the receiver operating characteristic curves on the test sets, including the hold-out test set from INSEMA. In contrast, the logistic regression fitted on the Mannheim cohort retained a better than random performance on INSEMA and Regensburg. Including the image analysis model output in the logistic regression did not improve performance further on INSEMA. Conclusions: Employing DL-based image analysis on histological slides, we could not predict SLN status for un-seen cases in the INSEMA trial and other predominantly luminal cohorts.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | ; Sentinel; Lymph node status; Deep learning; Breast cancer; Digital biomarker |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Lehrstuhl für Pathologie |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 30 Jan 2024 10:46 |
| Last Modified: | 30 Jan 2024 10:46 |
| URI: | https://pred.uni-regensburg.de/id/eprint/60774 |
Actions (login required)
 |
View Item |
