Deep-learning-based model observer for a lung nodule detection task in computed tomography.

Purpose: Task-based image quality assessment using model observers (MOs) is an effective approach to radiation dose and scanning protocol optimization in computed tomography (CT) imaging, once the correlation between MOs and radiologists can be established in well-defined clinically relevant tasks. Conventional MO studies were typically simplified to detection, classification, or localization tasks using tissue-mimicking phantoms, as traditional MOs cannot be readily used in complex anatomical background. However, anatomical variability can affect human diagnostic performance. Approach: To address this challenge, we developed a deep-learning-based MO (DL-MO) for localization tasks and validated in a lung nodule detection task, using previously validated projection-based lesion-/noise-insertion techniques. The DL-MO performance was compared with 4 radiologist readers over 12 experimental conditions, involving varying radiation dose levels, nodule sizes, nodule types, and reconstruction types. Each condition consisted of 100 trials (i.e., 30 images per trial) generated from a patient cohort of 50 cases. DL-MO was trained using small image volume-of-interests extracted across the entire volume of training cases. For each testing trial, the nodule searching of DL-MO was confined to a 3-mm thick volume to improve computational efficiency, and radiologist readers were tasked to review the entire volume. Results: A strong correlation between DL-MO and human readers was observed (Pearson's correlation coefficient: 0.980 with a 95% confidence interval of [0.924, 0.994]). The averaged performance bias between DL-MO and human readers was 0.57%. Conclusion: The experimental results indicated the potential of using the proposed DL-MO for diagnostic image quality assessment in realistic chest CT tasks.

Efficacy of chest computed tomography prediction of the pathological TNM stage of thymic epithelial tumours.

OBJECTIVES: The aim of this study is to evaluate the efficacy of chest computed tomography (CT) to predict the pathological stage of thymic epithelial tumours (TET) using the recently introduced tumour, node and metastasis (TNM) staging with comparison to the modified Masaoka staging. METHODS: Preoperative chest CT examinations in cases of resected TET with sampled lymph nodes (2006-2016) were retrospectively reviewed by 2 thoracic radiologists and radiologically (r) staged using both staging systems. A thoracic pathologist reviewed all cases for the pathological (p) stage. Concordance between r-staging and p-staging was assessed by % agreement and unweighted kappa statistics. Associations between r-stage and p-stage with outcomes were assessed using the Cox proportional hazards regression. RESULTS: Sixty patients with TET were included (47 thymomas, 12 thymic carcinomas and 1 atypical carcinoid tumour). Sixteen patients (26.7%) had received neoadjuvant therapy. Fifty-four patients (90.0%) had complete resection. The overall agreement between the r-stage and p-stage was 66.7% (κ = 0.46) for TNM staging and 46.7% (κ = 0.30) for modified Masaoka staging. Agreement between r-assessment and p-assessment of the T, N and M components of the TNM stage was 61.7% (κ = 0.28), 86.7% (κ = 0.48) and 98.3% (κ = 0.88), respectively. CT overstaged 12 patients (20.0%) for TNM staging and 12 patients (20.0%) for modified Masaoka staging and understaged 8 (13.3%) and 20 (33.3%) patients for TNM staging modified Masaoka staging, respectively. The r-TNM staging accuracy was lower for patients with neoadjuvant therapy (50.0% with vs 72.7% without). During a median follow-up of 2.6 years (range 0.1-10.5 years), 12 patients had metastases and/or recurrence; 11 patients died (4 of disease). The r-TNM stage and modified Masaoka stage were associated with overall survival and progression-free survival (P < 0.001). CONCLUSIONS: Preoperative chest CT is able to accurately predict p-TNM stage in two-thirds of surgically resected TET, with an agreement between radiological staging and pathological staging superior to the modified Masaoka staging.

A virtual clinical trial using projection-based nodule insertion to determine radiologist reader performance in lung cancer screening CT.

Task-based image quality assessment using model observers is promising to provide an efficient, quantitative, and objective approach to CT dose optimization. Before this approach can be reliably used in practice, its correlation with radiologist performance for the same clinical task needs to be established. Determining human observer performance for a well-defined clinical task, however, has always been a challenge due to the tremendous amount of efforts needed to collect a large number of positive cases. To overcome this challenge, we developed an accurate projection-based insertion technique. In this study, we present a virtual clinical trial using this tool and a low-dose simulation tool to determine radiologist performance on lung-nodule detection as a function of radiation dose, nodule type, nodule size, and reconstruction methods. The lesion insertion and low-dose simulation tools together were demonstrated to provide flexibility to generate realistically-appearing clinical cases under well-defined conditions. The reader performance data obtained in this virtual clinical trial can be used as the basis to develop model observers for lung nodule detection, as well as for dose and protocol optimization in lung cancer screening CT.