Detection of femoropopliteal arterial steno-occlusion at MR angiography: initial experience with artificial intelligence.

BACKGROUND: This study evaluated a deep learning (DL) algorithm for detecting vessel steno-occlusions in patients with peripheral arterial disease (PAD). It utilised a private dataset, which was acquired and annotated by the authors through their institution and subsequently validated by two blinded readers. METHODS: A single-centre retrospective study analysed 105 magnetic resonance angiography (MRA) images using an EfficientNet B0 DL model. Initially, inter-reader variability was assessed using the complete dataset. For a subset of these images (29 from the left side and 35 from the right side) where digital subtraction angiography (DSA) data was available as the ground truth, the model's accuracy and the area under the curve at receiver operating characteristics analysis (ROC-AUC) were evaluated. RESULTS: A total of 105 patient examinations (mean age, 75 years ±12 [mean ± standard deviation], 61 men) were evaluated. Radiologist-DL model agreement had a quadratic weighted Cohen κ ≥ 0.72 (left side) and ≥ 0.66 (right side). Radiologist inter-reader agreement was ≥ 0.90 (left side) and ≥ 0.87 (right side). The DL model achieved a 0.897 accuracy and a 0.913 ROC-AUC (left side) and 0.743 and 0.830 (right side). Radiologists achieved 0.931 and 0.862 accuracies, with 0.930 and 0.861 ROC-AUCs (left side), and 0.800 and 0.799 accuracies, with 0.771 ROC-AUCs (right side). CONCLUSION: The DL model provided valid results in identifying arterial steno-occlusion in the superficial femoral and popliteal arteries on MRA among PAD patients. However, it did not reach the inter-reader agreement of two radiologists. RELEVANCE STATEMENT: The tested DL model is a promising tool for assisting in the detection of arterial steno-occlusion in patients with PAD, but further optimisation is necessary to provide radiologists with useful support in their daily routine diagnostics. KEY POINTS: • This study focused on the application of DL for arterial steno-occlusion detection in lower extremities on MRA. • A previously developed DL model was tested for accuracy and inter-reader agreement. • While the model showed promising results, it does not yet replace human expertise in detecting arterial steno-occlusion on MRA.

Hypodense liver lesions in patients with hepatic steatosis: do we profit from dual-energy computed tomography?

PURPOSE: To evaluate dual-energy CT (DECT) imaging of hypodense liver lesions in patients with hepatic steatosis, having a high incidence in the general population and among cancer patients receiving chemotherapy. METHODS: One hundred and five patients with hepatic steatosis (liver parenchyma <40 HU) underwent contrast-enhanced DECT with reconstruction of pure iodine (PI), optimum contrast (OC), 80 kVp, and 120 kVp-equivalent data sets. Image noise (IN), lesion to liver signal to noise (SNR) and contrast to noise (CNR) ratios were quantitatively analysed; image quality was rated on a 5-point scale (1, excellent; 2, good; 3, fair; 4, poor; 5, non-diagnostic) by two independent reviewers. RESULTS: In 21 patients with hypodense liver lesions, IN was lowest in PI followed by 120 kVp-equivalent and OC, and highest in 80 kVp. SNR was highest in PI (1.30), followed by 120 kVp-equivalent (0.72) and 80 kVp (0.63), and lowest in OC (0.55). CNR was highest in 120 kVp-equivalent (4.95), followed by OC (4.55) and 80 kVp (4.14), and lowest in PI (3.63). The 120 kVp-equivalent series exhibited best overall qualitative image score (1.88), followed by OC (1.98), 80 kVp (3.00) and PI (3.67). CONCLUSION: In our study, the 120 kVp-equivalent series was best suited for visualization of hypodense lesions within steatotic liver parenchyma, while using DECT currently seems to offer no additional diagnostic advantage. KEY POINTS: • Hepatic steatosis has high incidence in the general population and following chemotherapy. • Hypodense liver lesions can be obscured by steatotic liver parenchyma in CT. • Low kV p -CT shows no advantage in detecting hypodense lesions in steatotic livers. • Additional DECT image information does not improve visualization of hypodense lesions in steatosis. • 120 kV p -equivalent imaging yields best quantitative and qualitative image analysis results.