Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT.

BACKGROUND: This study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable. MATERIALS AND METHODS: A standardized CT dataset was established using an anthropomorphic chest phantom (Lungman, Kyoto Kaguku Inc., Kyoto, Japan) containing a set of 3D-printed lung nodules including six diameters (4 to 9 mm) and three morphology classes (lobular, spiculated, smooth), with an established ground truth. Images were acquired at varying radiation doses (6.04, 3.03, 1.54, 0.77, 0.41 and 0.20 mGy) and reconstructed with combinations of reconstruction kernels (soft and hard kernel) and reconstruction algorithms (ASIR-V and DLIR at low, medium and high strength). Semi-automatic volumetry measurements and subjective image quality scores recorded by five radiologists were analyzed with multiple linear regression and mixed-effect ordinal logistic regression models. RESULTS: Volumetric errors of nodules imaged with DLIR are up to 50% lower compared to ASIR-V, especially at radiation doses below 1 mGy and when reconstructed with a hard kernel. Also, across all nodule diameters and morphologies, volumetric errors are commonly lower with DLIR. Furthermore, DLIR renders higher subjective IQ, especially at the sub-mGy doses. Radiologists were up to nine times more likely to score the highest IQ-score to these images compared to those reconstructed with ASIR-V. Lung nodules with irregular margins and small diameters also had an increased likelihood (up to five times more likely) to be ascribed the best IQ scores when reconstructed with DLIR. CONCLUSION: We observed that DLIR performs as good as or even outperforms conventionally used reconstruction algorithms in terms of volumetric accuracy and subjective IQ of nodules in an anthropomorphic chest phantom. As such, DLIR potentially allows to lower the radiation dose to participants of lung cancer screening without compromising accurate measurement and characterization of lung nodules.

Imaging modalities for the staging of patients with colorectal cancer.

Dutch guidelines made the following recommendations for staging colorectal cancer (CRC). For liver metastases, computed tomography (CT) or magnetic resonance imaging (MRI) could be used. For lung metastases, imaging could be limited to chest X-ray. The primary aim of this survey was to summarise the use of imaging modalities and the variation in techniques. Three surveys were created and sent to three groups of medical specialists, namely surgeons, radiologists and nuclear medicine physicians. The management survey included questions on the role of different modalities for evaluation of synchronous liver, lung and extrahepatic metastases. The radiological survey included questions concerning the technical aspects of ultrasound (US), CT and MRI. The nuclear medicine survey included questions concerning the technical aspects of FDG-PET and FDG-PET/CT. The management and radiological surveys were sent to abdominal surgeons and abdominal radiologists within 88 hospitals and the nuclear medicine survey to specialists within 34 hospitals. Response rates were 75.0% (n=66/88), 77.3% (n=68/88) and 64.7% (n=22/34) for the management, radiological and nuclear medicine surveys, respectively. For liver metastases, the first modality of choice was CT in 52 (78.8%) and US in 12 hospitals (18.2%). Lung metastases were evaluated by either chest X-ray or chest CT and extrahepatic metastases mainly by CT (n=55). In the radiological and nuclear medicine surveys, some variations in techniques of US, CT, MRI , FDG-PET and FDG-PET/CT were seen. CT is primarily used for liver and extrahepatic metastases and both chest CT and chest X-ray for lung metastases. There are discrepancies between the survey of daily practice and the present guidelines. Comparative studies on different staging strategies for colon and rectal cancer, including comparing a strategy of CT liver/abdomen versus MRI liver/abdomen for the evaluation of liver and extrahepatic disease and chest X-ray or chest CT for lung metastases would be important for well-founded adjustments of the present guidelines.

Right middle lobe torsion: evaluation with CT angiography.

A case of right middle lobe torsion occurring after a right upper lobectomy is described. HR-CT angiography was successful in identifying the obstructed right middle lobe bronchus and the avascular nature of the infected and displaced right middle lobe. This detailed information, obtainable from present day multislice HR-CT scanners with the right CT protocols, seems to diminish the need for further confirmation by other methods.