Application of computer-aided detection (CAD) software to automatically detect nodules under SDCT and LDCT scans with different parameters.

PURPOSE: To explore the application of computer-aided detection (CAD) software on automatically detecting nodules under standard-dose CT (SDCT) and low-dose CT (LDCT) scans with different parameters including definition modes and blending levels of adaptive statistical iterative reconstruction (ASIR), whose influence was important to optimize radiology workflow serving for clinical work. MATERIALS AND METHODS: 117 patients underwent SDCT and LDCT scans. The comprehensive performance of CAD in detect pulmonary nodules including under different ASIR blending levels (0%, 60%, and 80%) and high-definition (HD) or non-HD modes were assessed. The true positive (TP) rate, false positive (FP) rate and the sensitivity were recorded. RESULTS: The stand-alone sensitivity of CAD system was 78.03% (515/660) in SDCT images and 70.15% (456/650) on LDCT images (p < 0.05). The sensitivity of CAD system to pulmonary nodules under non-HD mode was higher than that under HD mode. The detectability of nodules in images reconstructed with 60% and 80% ASIR was found significantly superior to that with 0% ASIR (p < 0.001). The overall sensitivity of CAD system on LDCT images reconstructed with 60% ASIR under HD mode was greater than that with 0% ASIR (p < 0.05), but lower than that with 80% ASIR. However, under non-HD mode, CAD demonstrated a comparable performance on LDCT images reconstructed with 60% ASIR to those reconstructed with 80% ASIR. CONCLUSION: Using the CAD system to detect pulmonary nodules on LDCT images with appropriate levels of ASIR could maintain high diagnostic sensitivity while reducing the radiation dose, which is useful to optimize the radiology workflow.

Prospective Study of Low- and Standard-dose Chest CT for Pulmonary Nodule Detection: A Comparison of Image Quality, Size Measurements and Radiation Exposure.

OBJECTIVE: To comprehensively and accurately analyze the out-performance of low-dose chest CT (LDCT) vs. standard-dose CT (SDCT). METHODS: The image quality, size measurements and radiation exposure for LDCT and SDCT protocols were evaluated. A total of 117 patients with extra-thoracic malignancies were prospectively enrolled for non-enhanced CT scanning using LDCT and SDCT protocols. Three experienced radiologists evaluated subjective image quality independently using a 5-point score system. Nodule detection efficiency was compared between LDCT and SDCT based on nodule characteristics (size and volume). Radiation metrics and organ doses were analyzed using Radimetrics. RESULTS: The images acquired with the LDCT protocol yielded comparable quality to those acquired with the SDCT protocol. The sensitivity of LDCT for the detection of pulmonary nodules (n=650) was lower than that of SDCT (n=660). There was no significant difference in the diameter and volume of pulmonary nodules between LDCT and SDCT (for BMI <22 kg/m2, 4.37 vs. 4.46 mm, and 43.66 vs. 46.36 mm3; for BMI ≥22 kg/m2, 4.3 vs. 4.41 mm, and 41.66 vs. 44.86 mm3) (P>0.05). The individualized volume CT dose index (CTDIvol), the size specific dose estimate and effective dose were significantly reduced in the LDCT group compared with the SDCT group (all P<0.0001). This was especially true for dose-sensitive organs such as the lung (for BMI <22 kg/m2, 2.62 vs. 12.54 mSV, and for BMI ≥22 kg/m2, 1.62 vs. 9.79 mSV) and the breast (for BMI <22 kg/m2, 2.52 vs. 10.93 mSV, and for BMI ≥22 kg/m2, 1.53 vs. 9.01 mSV) (P<0.0001). CONCLUSION: These results suggest that with the increases in image noise, LDCT and SDCT exhibited a comparable image quality and sensitivity. The LDCT protocol for chest scans may reduce radiation exposure by about 80% compared to the SDCT protocol.