Detection of hypodense hepatic and renal lesions on abdominal CT reconstructed with deep learning image reconstruction technique in patients with large body habitus: A multi-reader study.

Deep learning image reconstruction improves visualization of arterial phase hyperenhancement and washout appearance on dual-energy CT for hepatocellular carcinoma: a non-inferiority study.

Ultra-low dose chest-abdomen-pelvis CT with deep-learning image reconstruction for cancer follow-up: Impact on image quality and lesion detection.

PURPOSE The purpose of this study was to compare the image quality and lesion detection between ultra-low dose (ULD) chest-abdomen-pelvis computed tomography (CAP-CT) reconstructed with a deep-learning image reconstruction (DLR) algorithm, and standard-dose CT (STD-CT) in cancer follow-up. MATERIALS AND METHODS A total of 106 patients undergoing CAP-CT for the follow-up of cancer were prospectively included. Each patient underwent both STD-CT and ULD-CT acquisitions. ULD-CT images were reconstructed using two DLR levels (Smooth/Smoother). Dosimetric indicators, objective image quality, subjective image quality, and lesion detection were compared. Agreement between protocols and readers was assessed using Gwet's AC1 or AC2 coefficients. RESULTS ULD-CT significantly reduced radiation exposure, with a mean CTDIvol reduction of -71.5% and dose-length product reduction of -71.5% (P < 0.05). Minor but statistically significant differences in HU values were observed between STD-CT and ULD-CT across most tissues. For all organs or tissues, image noise was significantly higher with ULD-CT-Smooth than with STD-CT (P < 0.001), and with ULD-CT-Smoother than with STD-CT, except for dorsal vertebra (P = 0.39) and trachea (P = 0.26). For all organs or tissues, image noise was significantly lower with the Smoother DLR level than with Smooth DLR level (P < 0.001). Agreement between STD-CT and ULD-CT regarding lesion detection was almost perfect for thoracic, abdominal, and bone lesions. Detection of infracentimetric hepatic was lower with ULD-CT, whereas detection of larger lesions (≥ 10 mm) remained similar. Subjective image quality was lower with ULD-CT, with moderate inter-reader agreement, and lower diagnostic confidence than with STD-CT. One of the two readers considered that 19%-24% of ULD-CT examinations were uninterpretable. CONCLUSION ULD-CT with DLR offers substantial radiation dose reduction but resulted in poorer image quality and lower detection of small low-contrast abdominal lesions compared with STD-CT. Although lesion detection remained equivalent for thoracic and skeletal lesions, the high proportion of suboptimal or uninterpretable examinations may limit routine use of ULD protocols in cancer follow-up.

Photon-counting CT for hepato-bilio-pancreatic imaging: a qualitative head-to-head comparison with third-generation dual-source CT: preliminary results.

In this preliminary intra-patient comparison, photon-counting CT provided significantly superior image quality and anatomical detail in the hepato-bilio-pancreatic region compared to third-generation dual-source EID-CT.

Distinguishing enhancing from non-enhancing hyperdense adnexal lesions with spectral reconstructions at photon counting CT.

Attenuation change utilizing VUE images and iodine quantification can differentiate enhancing from nonenhancing hyperdense adnexal lesions at PCCT with excellent diagnostic performance.

Feasibility of reducing radiation dose and contrast dose while improving image quality in dual-energy CT pulmonary angiography : Use of low-energy virtual monochromatic images with deep learning image reconstruction algorithm.

Arthroscopy-Validated Diagnostic Performance of a Deep Learning Reconstruction Pipeline for Rapid 7-Minute Five-Sequence 3-T Knee MRI.

Background. Deep learning reconstruction (DLR) methods can enhance image quality and reduce scan time of knee MRI compared with conventional approaches but require validation against independent reference standards to ensure robustness and accuracy. Objective. The purpose of this study was to assess the diagnostic performance of a two- to threefold parallel imaging-accelerated 7-minute five-sequence 3-T knee MRI protocol using a deep learning-based image reconstruction pipeline (AIR Recon DL, GE HealthCare), with arthroscopic surgery as the reference standard. Methods. A total of 117 consecutive adult patients (mean age: 44 ± 16 [SD] years; 65 men, 52 women) with painful knee conditions who underwent DLR 3-T knee MRI and arthroscopic knee surgery with a median MRI-tosurgery interval of 35 days (range: 5-88 days) between June 2021 and May 2024 were retrospectively identified and included. MRI studies were independently reviewed by seven musculoskeletal radiologists for image quality parameters using Likert scales (range: 1 = very bad to 5 = very good) and the presence of meniscus tears, cruciate and collateral ligament tears, and articular cartilage defects. Statistical analyses included interreader agreements and diagnostic performance testing. Results. Overall image quality of DLR knee MRI scans was good (median: 4 [IQR, 4-5]), with minimal image noise (4 [4-4]), good edge sharpness (4 [4-5]), absence of reconstruction artifacts (5 [4-5]), and high interreader agreement for all quality metrics (κ ≥ 0.83). Diagnostic performance for detecting arthroscopy-validated structural abnormalities was very good (AUC ≥ 0.81) with good to very good interreader agreement (κ ≥ 0.62). The sensitivity, specificity, accuracy, and AUC values were 89%, 87%, 88%, and 0.87 for medial meniscus tears (prevalence at arthroscopy: 78/117; 67%), 72%, 91%, 83%, and 0.82 for lateral meniscus tears (50/117; 43%), 97%, 98%, 97%, and 0.97 for anterior cruciate ligament tears (30/117; 26%), and 73%, 89%, 86%, and 0.81 for articular cartilage defects (182/702; 26%). Conclusion. Clinical 7-minute five-sequence 3-T knee MRI with deep learning reconstruction provides good to excellent diagnostic performance for detecting arthroscopy-validated internal derangement of the knee. Clinical Impact. Deep learning reconstruction enables rapid high-quality clinical 3-T knee MRI with high diagnostic performance for arthroscopy-validated abnormalities.