Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma

• Published in: Radiology. Artificial intelligence Vol. 2; no. 5; p. e200016
• Main Authors: Weisman, Amy J., Kieler, Minnie W., Perlman, Scott B., Hutchings, Martin, Jeraj, Robert, Kostakoglu, Lale, Bradshaw, Tyler J.
• Format: Journal Article
• Language: English
• Published: United States Radiological Society of North America 01.09.2020
• Subjects: Original Research
• ISSN: 2638-6100; 2638-6100
• DOI: 10.1148/ryai.2020200016

To automatically detect lymph nodes involved in lymphoma on fluorine 18 ( F) fluorodeoxyglucose (FDG) PET/CT images using convolutional neural networks (CNNs). In this retrospective study, baseline disease of 90 patients with lymphoma was segmented on F-FDG PET/CT images (acquired between 2005 and 2011) by a nuclear medicine physician. An ensemble of three-dimensional patch-based, multiresolution pathway CNNs was trained using fivefold cross-validation. Performance was assessed using the true-positive rate (TPR) and number of false-positive (FP) findings. CNN performance was compared with agreement between physicians by comparing the annotations of a second nuclear medicine physician to the first reader in 20 of the patients. Patient TPR was compared using Wilcoxon signed rank tests. Across all 90 patients, a range of 0-61 nodes per patient was detected. At an average of four FP findings per patient, the method achieved a TPR of 85% (923 of 1087 nodes). Performance varied widely across patients (TPR range, 33%-100%; FP range, 0-21 findings). In the 20 patients labeled by both physicians, a range of 1-49 nodes per patient was detected and labeled. The second reader identified 96% (210 of 219) of nodes with an additional 3.7 per patient compared with the first reader. In the same 20 patients, the CNN achieved a 90% (197 of 219) TPR at 3.7 FP findings per patient. An ensemble of three-dimensional CNNs detected lymph nodes at a performance nearly comparable to differences between two physicians' annotations. This preliminary study is a first step toward automated PET/CT assessment for lymphoma.© RSNA, 2020.