Deep transfer learning methods for colon cancer classification in confocal laser microscopy images
Standard
Deep transfer learning methods for colon cancer classification in confocal laser microscopy images. / Gessert, Nils; Bengs, Marcel; Wittig, Lukas; Drömann, Daniel; Keck, Tobias; Schlaefer, Alexander; Ellebrecht, David B.
in: INT J COMPUT ASS RAD, Jahrgang 14, Nr. 11, 11.2019, S. 1837-1845.Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Deep transfer learning methods for colon cancer classification in confocal laser microscopy images
AU - Gessert, Nils
AU - Bengs, Marcel
AU - Wittig, Lukas
AU - Drömann, Daniel
AU - Keck, Tobias
AU - Schlaefer, Alexander
AU - Ellebrecht, David B
PY - 2019/11
Y1 - 2019/11
N2 - PURPOSE: The gold standard for colorectal cancer metastases detection in the peritoneum is histological evaluation of a removed tissue sample. For feedback during interventions, real-time in vivo imaging with confocal laser microscopy has been proposed for differentiation of benign and malignant tissue by manual expert evaluation. Automatic image classification could improve the surgical workflow further by providing immediate feedback.METHODS: We analyze the feasibility of classifying tissue from confocal laser microscopy in the colon and peritoneum. For this purpose, we adopt both classical and state-of-the-art convolutional neural networks to directly learn from the images. As the available dataset is small, we investigate several transfer learning strategies including partial freezing variants and full fine-tuning. We address the distinction of different tissue types, as well as benign and malignant tissue.RESULTS: We present a thorough analysis of transfer learning strategies for colorectal cancer with confocal laser microscopy. In the peritoneum, metastases are classified with an AUC of 97.1, and in the colon the primarius is classified with an AUC of 73.1. In general, transfer learning substantially improves performance over training from scratch. We find that the optimal transfer learning strategy differs for models and classification tasks.CONCLUSIONS: We demonstrate that convolutional neural networks and transfer learning can be used to identify cancer tissue with confocal laser microscopy. We show that there is no generally optimal transfer learning strategy and model as well as task-specific engineering is required. Given the high performance for the peritoneum, even with a small dataset, application for intraoperative decision support could be feasible.
AB - PURPOSE: The gold standard for colorectal cancer metastases detection in the peritoneum is histological evaluation of a removed tissue sample. For feedback during interventions, real-time in vivo imaging with confocal laser microscopy has been proposed for differentiation of benign and malignant tissue by manual expert evaluation. Automatic image classification could improve the surgical workflow further by providing immediate feedback.METHODS: We analyze the feasibility of classifying tissue from confocal laser microscopy in the colon and peritoneum. For this purpose, we adopt both classical and state-of-the-art convolutional neural networks to directly learn from the images. As the available dataset is small, we investigate several transfer learning strategies including partial freezing variants and full fine-tuning. We address the distinction of different tissue types, as well as benign and malignant tissue.RESULTS: We present a thorough analysis of transfer learning strategies for colorectal cancer with confocal laser microscopy. In the peritoneum, metastases are classified with an AUC of 97.1, and in the colon the primarius is classified with an AUC of 73.1. In general, transfer learning substantially improves performance over training from scratch. We find that the optimal transfer learning strategy differs for models and classification tasks.CONCLUSIONS: We demonstrate that convolutional neural networks and transfer learning can be used to identify cancer tissue with confocal laser microscopy. We show that there is no generally optimal transfer learning strategy and model as well as task-specific engineering is required. Given the high performance for the peritoneum, even with a small dataset, application for intraoperative decision support could be feasible.
KW - Colonic Neoplasms/classification
KW - Deep Learning
KW - Feasibility Studies
KW - Humans
KW - Microscopy, Confocal/methods
KW - Neoplasm Metastasis
KW - Neural Networks, Computer
KW - Peritoneal Neoplasms/diagnosis
U2 - 10.1007/s11548-019-02004-1
DO - 10.1007/s11548-019-02004-1
M3 - SCORING: Journal article
C2 - 31129859
VL - 14
SP - 1837
EP - 1845
JO - INT J COMPUT ASS RAD
JF - INT J COMPUT ASS RAD
SN - 1861-6410
IS - 11
ER -