Abstract
BackgroundPerforming Response Evaluation Criteria in Solid Tumor (RECISTS) measurement is a non-trivial task requiring much expertise and time. A deep learning-based algorithm has the potential to assist with rapid and consistent lesion measurement.PurposeThe aim of this study is to develop and evaluate deep learning (DL) algorithm for semi-automated unidirectional CT measurement of lung lesions.MethodsThis retrospective study included 1617 lung CT images from 8 publicly open datasets. A convolutional neural network was trained using 1373 training and validation images annotated by two radiologists. Performance of the DL algorithm was evaluated 244 test images annotated by one radiologist. DL algorithm’s measurement consistency with human radiologist was evaluated using Intraclass Correlation Coefficient (ICC) and Bland-Altman plotting. Bonferroni’s method was used to analyze difference in their diagnostic behavior, attributed by tumor characteristics. Statistical significance was set at p < 0.05.ResultsThe DL algorithm yielded ICC score of 0.959 with human radiologist. Bland-Altman plotting suggested 240 (98.4 %) measurements realized within the upper and lower limits of agreement (LOA). Some measurements outside the LOA revealed difference in clinical reasoning between DL algorithm and human radiologist. Overall, the algorithm marginally overestimated the size of lesion by 2.97 % compared to human radiologists. Further investigation indicated tumor characteristics may be associated with the DL algorithm’s diagnostic behavior of over or underestimating the lesion size compared to human radiologist.ConclusionsThe DL algorithm for unidirectional measurement of lung tumor size demonstrated excellent agreement with human radiologist.
Highlights
Performing Response Evaluation Criteria in Solid Tumor (RECISTS) measurement is a non-trivial task requiring much expertise and time
We propose a new approach for application of a deep learning (DL) algorithm on semiautomated computed tomography (CT) measurement of lung lesions
CT images were included in this study after applying the following inclusion criteria: (a) selected lesion should be measurable under RECIST 1.1 (b) selected image file contains complete Digital Imaging and Communications in Medicine (DICOM) pixel data with no corruption (c) lesion size should differ by 20 % when compared to the previously selected images if selected from the same patient (d) selected image has at least 5mm spacing to the previously selected images if selected from the same patient
Summary
Performing Response Evaluation Criteria in Solid Tumor (RECISTS) measurement is a non-trivial task requiring much expertise and time. Multiple reports have indicated that the tumor size measurements using computed tomography (CT) scans are subjected to intra- and interobserver variability with various environmental factors causing the variability [5,6,7,8,9,10,11,12] To address these challenges, researchers have attempted to develop systems to assist with consistent lesion measurement through automated lesion segmentation or masking for CT images [13,14,15,16,17,18]. Performing segmentation often takes longer than performing unidirectional measurement by human radiologists; this incurs additional costs on the acquisition of training data for any automated system for measurement
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
