Cover Image

Tumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning

Objectives: The goal of this study is to demonstrate the performance of radiomics and CNN-based classifiers in determining the primary origin of gastrointestinal liver metastases for visually indistinguishable lesions.Methods: In this retrospective, IRB-approved study, 31 pancreatic cancer patients...

Full description

Saved in:
Bibliographic Details
Main Authors: Tharmaseelan, Hishan (Author) , Vellala, Abhinay K. (Author) , Hertel, Alexander (Author) , Tollens, Fabian (Author) , Rotkopf, Lukas Thomas (Author) , Rink, Johann (Author) , Woźnicki, Piotr (Author) , Ayx, Isabelle (Author) , Bartling, Sönke (Author) , Nörenberg, Dominik (Author) , Schönberg, Stefan (Author) , Froelich, Matthias F. (Author)
Format: Article (Journal)
Language:English
Published: 2023
In: Cancer imaging
Year: 2023, Volume: 23, Pages: 1-9
ISSN:1470-7330
DOI:10.1186/s40644-023-00612-4
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s40644-023-00612-4
Get full text
Author Notes:Hishan Tharmaseelan, Abhinay K. Vellala, Alexander Hertel, Fabian Tollens, Lukas T. Rotkopf, Johann Rink, Piotr Woźnicki, Isabelle Ayx, Sönke Bartling, Dominik Nörenberg, Stefan O. Schoenberg and Matthias F. Froelich
Description
Summary:Objectives: The goal of this study is to demonstrate the performance of radiomics and CNN-based classifiers in determining the primary origin of gastrointestinal liver metastases for visually indistinguishable lesions.Methods: In this retrospective, IRB-approved study, 31 pancreatic cancer patients with 861 lesions (median age [IQR]: 65.39 [56.87, 75.08], 48.4% male) and 47 colorectal cancer patients with 435 lesions (median age [IQR]: 65.79 [56.99, 74.62], 63.8% male) were enrolled. A pretrained nnU-Net performed automated segmentation of 1296 liver lesions. Radiomics features for each lesion were extracted using pyradiomics. The performance of several radiomics-based machine-learning classifiers was investigated for the lesions and compared to an image-based deep-learning approach using a DenseNet-121. The performance was evaluated by AUC/ROC analysis. Results: The radiomics-based K-nearest neighbor classifier showed the best performance on an independent test set with AUC values of 0.87 and an accuracy of 0.67. In comparison, the image-based DenseNet-121-classifier reached an AUC of 0.80 and an accuracy of 0.83. Conclusions: CT-based radiomics and deep learning can distinguish the etiology of liver metastases from gastrointestinal primary tumors. Compared to deep learning, radiomics based models showed a varying generalizability in distinguishing liver metastases from colorectal cancer and pancreatic adenocarcinoma.
Item Description:Veröffentlicht: 5. Oktober 2023
Gesehen am 23.11.2023
Physical Description:Online Resource
ISSN:1470-7330
DOI:10.1186/s40644-023-00612-4

Similar Items