Automated lung cancer assessment on 18F-PET/CT using Retina U-Net and anatomical region segmentation

Objectives To develop and test a Retina U-Net algorithm for the detection of primary lung tumors and associated metastases of all stages on FDG-PET/CT. Methods A data set consisting of 364 FDG-PET/CTs of patients with histologically confirmed lung cancer was used for algorithm development and intern...

Full description

Saved in:

Bibliographic Details
Published in:	European radiology Vol. 33; no. 6; pp. 4270 - 4279
Main Authors:	Weikert, T., Jaeger, P. F., Yang, S., Baumgartner, M., Breit, H. C., Winkel, D. J., Sommer, G., Stieltjes, B., Thaiss, W., Bremerich, J., Maier-Hein, K. H., Sauter, A. W.
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01-06-2023 Springer Nature B.V
Subjects:	Algorithms Automation Backbone Bone marrow Computed tomography Correlation Datasets Diagnostic Radiology Fluorodeoxyglucose F18 Humans Image segmentation Imaging Imaging Informatics and Artificial Intelligence Internal Medicine Interventional Radiology Lesions Lung cancer Lung Neoplasms - diagnostic imaging Medicine Medicine & Public Health Metastases Metastasis Neuroradiology Physiology Positron emission tomography Positron Emission Tomography Computed Tomography - methods Radiology Radiopharmaceuticals Retina Sensitivity and Specificity Test sets Tumors Ultrasound Deep learning Neoplasm staging Artificial intelligence Lung neoplasm PET/CT
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Objectives To develop and test a Retina U-Net algorithm for the detection of primary lung tumors and associated metastases of all stages on FDG-PET/CT. Methods A data set consisting of 364 FDG-PET/CTs of patients with histologically confirmed lung cancer was used for algorithm development and internal testing. The data set comprised tumors of all stages. All lung tumors (T), lymphatic metastases (N), and distant metastases (M) were manually segmented as 3D volumes using whole-body PET/CT series. The data set was split into a training ( n = 216), validation ( n = 74), and internal test data set ( n = 74). Detection performance for all lesion types at multiple classifier thresholds was evaluated and false-positive-findings-per-case (FP/c) calculated. Next, detected lesions were assigned to categories T, N, or M using an automated anatomical region segmentation. Furthermore, reasons for FPs were visually assessed and analyzed. Finally, performance was tested on 20 PET/CTs from another institution. Results Sensitivity for T lesions was 86.2% (95% CI: 77.2–92.7) at a FP/c of 2.0 on the internal test set. The anatomical correlate to most FPs was the physiological activity of bone marrow (16.8%). TNM categorization based on the anatomical region approach was correct in 94.3% of lesions. Performance on the external test set confirmed the good performance of the algorithm (overall detection rate = 88.8% (95% CI: 82.5–93.5%) and FP/c = 2.7). Conclusions Retina U-Nets are a valuable tool for tumor detection tasks on PET/CT and can form the backbone of reading assistance tools in this field. FPs have anatomical correlates that can lead the way to further algorithm improvements. The code is publicly available. Key Points • Detection of malignant lesions in PET/CT with Retina U-Net is feasible. • All false-positive findings had anatomical correlates, physiological bone marrow activity being the most prevalent. • Retina U-Nets can build the backbone for tools assisting imaging professionals in lung tumor staging.
ISSN:	1432-1084 0938-7994 1432-1084
DOI:	10.1007/s00330-022-09332-y