Jin Li1, Yang Zhou1,2, Peng Wang1, Henan Zhao2, Xinxin Wang2, Na Tang2, Kuan Luan1. 1. College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China. 2. Department of Radiology, Harbin Medical University Cancer Hospital, Harbin, China.
Abstract
BACKGROUND: Lymph node (LN) metastasis is the main prognostic factor for local recurrence and overall survival of patients with rectal cancer. The accurate evaluation of LN status in rectal cancer patients is associated with improved treatment and prognosis. This study aimed to apply deep transfer learning to classify LN status in patients with rectal cancer to improve N staging accuracy. METHODS: The study included 129 patients with 325 rectal cancer screenshots of LN T2-weighted (T2W) images from April 2018 to March 2019. Deep learning was applied through a pre-trained model, Inception-v3, for recognition and detection of LN status. The results were compared to manual identification by experienced radiologists. Two radiologists reviewed images and independently identified their status using various criteria with or without short axial (SA) diameter measurements. The accuracy, positive predictive value (PPV), negative predictive value (NPV), sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) were calculated. RESULTS: When the same radiologist performed the analysis, the AUC was not significantly different in the presence or absence of LN diameter measurements (P>0.05). In the deep transfer learning method, the PPV, NPV, sensitivity, and specificity were 95.2%, 95.3%, 95.3%, and 95.2%, respectively, and the AUC and accuracy were 0.994 and 95.7%, respectively. These results were all higher than that achieved with manual diagnosis by the radiologists. CONCLUSIONS: The internal details of LNs should be used as the main criteria for positive diagnosis when using MRI. Deep transfer learning can improve the MRI diagnosis of positive LN metastasis in patients with rectal cancer. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: Lymph node (LN) metastasis is the main prognostic factor for local recurrence and overall survival of patients with rectal cancer. The accurate evaluation of LN status in rectal cancer patients is associated with improved treatment and prognosis. This study aimed to apply deep transfer learning to classify LN status in patients with rectal cancer to improve N staging accuracy. METHODS: The study included 129 patients with 325 rectal cancer screenshots of LN T2-weighted (T2W) images from April 2018 to March 2019. Deep learning was applied through a pre-trained model, Inception-v3, for recognition and detection of LN status. The results were compared to manual identification by experienced radiologists. Two radiologists reviewed images and independently identified their status using various criteria with or without short axial (SA) diameter measurements. The accuracy, positive predictive value (PPV), negative predictive value (NPV), sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC) were calculated. RESULTS: When the same radiologist performed the analysis, the AUC was not significantly different in the presence or absence of LN diameter measurements (P>0.05). In the deep transfer learning method, the PPV, NPV, sensitivity, and specificity were 95.2%, 95.3%, 95.3%, and 95.2%, respectively, and the AUC and accuracy were 0.994 and 95.7%, respectively. These results were all higher than that achieved with manual diagnosis by the radiologists. CONCLUSIONS: The internal details of LNs should be used as the main criteria for positive diagnosis when using MRI. Deep transfer learning can improve the MRI diagnosis of positive LN metastasis in patients with rectal cancer. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Entities:
Keywords:
Magnetic resonance imaging (MRI); artificial intelligence (AI); lymph nodes (LNs); rectal cancer
Authors: Doenja M J Lambregts; Geerard L Beets; Monique Maas; Alfons G H Kessels; Frans C H Bakers; Vincent C Cappendijk; Sanne M E Engelen; Max J Lahaye; Adriaan P de Bruïne; Guido Lammering; Tim Leiner; Jan L Verwoerd; Joachim E Wildberger; Regina G H Beets-Tan Journal: Ann Surg Date: 2011-03 Impact factor: 12.969
Authors: Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez Journal: Med Image Anal Date: 2017-07-26 Impact factor: 8.545
Authors: O C Shihab; F Taylor; N Bees; H Blake; N Jeyadevan; R Bleehen; L Blomqvist; M Creagh; C George; A Guthrie; H Massouh; D Peppercorn; B J Moran; R J Heald; P Quirke; P Tekkis; G Brown Journal: Br J Surg Date: 2011-09-16 Impact factor: 6.939
Authors: Fiona G M Taylor; Philip Quirke; Richard J Heald; Brendan Moran; Lennart Blomqvist; Ian Swift; David J Sebag-Montefiore; Paris Tekkis; Gina Brown Journal: Ann Surg Date: 2011-04 Impact factor: 12.969
Authors: Jacques Ferlay; Isabelle Soerjomataram; Rajesh Dikshit; Sultan Eser; Colin Mathers; Marise Rebelo; Donald Maxwell Parkin; David Forman; Freddie Bray Journal: Int J Cancer Date: 2014-10-09 Impact factor: 7.396