Shimpei Kato1, Shiori Amemiya2, Hidemasa Takao1, Hiroshi Yamashita3, Naoya Sakamoto1, Osamu Abe1. 1. Department of Radiology, The Graduate School of Medicine, University of Tokyo, 7‑3‑1 Hongo, Bunkyo‑ku, Tokyo, 113‑8655, Japan. 2. Department of Radiology, The Graduate School of Medicine, University of Tokyo, 7‑3‑1 Hongo, Bunkyo‑ku, Tokyo, 113‑8655, Japan. amemiya-tky@umin.ac.jp. 3. Department of Radiology, Teikyo University Hospital, Mizonokuchi, 5-1-1 Futago, Takatsu-ku, Kawasaki, Kanagawa, 213-8507, Japan.
Abstract
PURPOSE: To develop and investigate deep learning-based detectors for brain metastases detection on non-enhanced (NE) CT. METHODS: The study included 116 NECTs from 116 patients (81 men, age 66.5 ± 10.6 years) to train and test single-shot detector (SSD) models using 89 and 27 cases, respectively. The annotation was performed by three radiologists using bounding-boxes defined on contrast-enhanced CT (CECT) images. NECTs were coregistered and resliced to CECTs. The detection performance was evaluated at the SSD's 50% confidence threshold using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR). For false negatives and true positives, binary logistic regression was used to examine the possible contributing factors. RESULTS: For lesions 6 mm or larger, the SSD achieved a sensitivity of 35.4% (95% confidence interval (CI): [32.3%, 33.5%]); 51/144) with an FPR of 14.9 (95% CI [12.4, 13.9]). The overall sensitivity was 23.8% (95% CI: [21.3%, 22.8%]; 55/231) and PPV was 19.1% (95% CI: [18.5%, 20.4%]; 98/ of 513), with an FPR of 15.4 (95% CI [12.9, 14.5]). Ninety-five percent of the lesions that SSD failed to detect were also undetectable to radiologists (168/176). Twenty-four percent of the lesions (13/50) detected by the SSD were undetectable to radiologists. Logistic regression analysis indicated that density, necrosis, and size contributed to the lesions' visibility for radiologists, while for the SSD, the surrounding edema also enhanced the detection performance. CONCLUSION: The SSD model we developed could detect brain metastases larger than 6 mm to some extent, a quarter of which were even retrospectively unrecognizable to radiologists.
PURPOSE: To develop and investigate deep learning-based detectors for brain metastases detection on non-enhanced (NE) CT. METHODS: The study included 116 NECTs from 116 patients (81 men, age 66.5 ± 10.6 years) to train and test single-shot detector (SSD) models using 89 and 27 cases, respectively. The annotation was performed by three radiologists using bounding-boxes defined on contrast-enhanced CT (CECT) images. NECTs were coregistered and resliced to CECTs. The detection performance was evaluated at the SSD's 50% confidence threshold using sensitivity, positive-predictive value (PPV), and the false-positive rate per scan (FPR). For false negatives and true positives, binary logistic regression was used to examine the possible contributing factors. RESULTS: For lesions 6 mm or larger, the SSD achieved a sensitivity of 35.4% (95% confidence interval (CI): [32.3%, 33.5%]); 51/144) with an FPR of 14.9 (95% CI [12.4, 13.9]). The overall sensitivity was 23.8% (95% CI: [21.3%, 22.8%]; 55/231) and PPV was 19.1% (95% CI: [18.5%, 20.4%]; 98/ of 513), with an FPR of 15.4 (95% CI [12.9, 14.5]). Ninety-five percent of the lesions that SSD failed to detect were also undetectable to radiologists (168/176). Twenty-four percent of the lesions (13/50) detected by the SSD were undetectable to radiologists. Logistic regression analysis indicated that density, necrosis, and size contributed to the lesions' visibility for radiologists, while for the SSD, the surrounding edema also enhanced the detection performance. CONCLUSION: The SSD model we developed could detect brain metastases larger than 6 mm to some extent, a quarter of which were even retrospectively unrecognizable to radiologists.
Entities:
Keywords:
Brain metastases; Computed tomography; Deep learning; Single-shot detectors
Authors: Jill S Barnholtz-Sloan; Andrew E Sloan; Faith G Davis; Fawn D Vigneau; Ping Lai; Raymond E Sawaya Journal: J Clin Oncol Date: 2004-07-15 Impact factor: 44.544
Authors: Mohammad R Arbabshirani; Brandon K Fornwalt; Gino J Mongelluzzo; Jonathan D Suever; Brandon D Geise; Aalpen A Patel; Gregory J Moore Journal: NPJ Digit Med Date: 2018-04-04
Authors: Weicheng Kuo; Christian Hӓne; Pratik Mukherjee; Jitendra Malik; Esther L Yuh Journal: Proc Natl Acad Sci U S A Date: 2019-10-21 Impact factor: 11.205