Deep Learning Reconstruction of Accelerated MRI: False-Positive Cartilage Delamination Inserted in MRI Arthrography Under Traction.

OBJECTIVES: The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations. MATERIALS AND METHODS: Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient. RESULTS: The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects. CONCLUSIONS: In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.

Ability of ChatGPT to generate competent radiology reports for distal radius fracture by use of RSNA template items and integrated AO classifier.

The amount of acquired radiology imaging studies grows worldwide at a rapid pace. Novel information technology tools for radiologists promise an increase of reporting quality and as well quantity at the same time. Automated text report drafting is one branch of this development. We defined for the present study in total 9 cases of distal radius fracture. Command files structured according to a template of the Radiological Society of North America (RSNA) and to Arbeitsgemeinschaft Osteosynthese (AO) classifiers were given as input to the natural language processing tool ChatGPT. ChatGPT was tasked with drafting an appropriate radiology report. A parameter study (n = 5 iterations) was performed. An overall high appraisal of ChatGPT radiology report quality was obtained in a score card based assessment. ChatGPT demonstrates the capability to adjust output files in response to minor changes in input command files. Existing shortcomings were found in technical terminology and medical interpretation of findings. Text drafting tools might well support work of radiologists in the future. They would allow a radiologist to focus time on the observation of image details and patient pathology. ChatGPT can be considered a substantial step forward towards that aim.

Avoiding the Intercostal Arteries in Percutaneous Thoracic Interventions.

The purpose of this study was to define relevant intercostal artery (ICA) anatomy potentially impacting the safety of thoracic percutaneous interventional procedures. An ICA abutting the upper rib and running in the subcostal groove was defined as the lowest risk zone for interventions requiring a supracostal needle puncture. A theoretical high-risk zone was defined by the ICA coursing in the lower half of the intercostal space (ICS), and a theoretical moderate-risk zone was defined by the ICA coursing below the subcostal groove but in the upper half of the ICS. Arterial phase computed tomography data from 250 patients were analyzed, revealing demographic variability, with high-risk zones extending more laterally with advancing age and with more cranial ribs. Overall, within the 97.5th percentile, an ICS puncture >7-cm lateral to the spinous process incurs moderate risk and >10-cm lateral incurs the lowest risk.

Assessment of 3-T MRI using susceptibility-weighted imaging to detect and evaluate intra- or periarticular blood metabolites and meniscal tears of the knee.

PURPOSE: The purpose of this study was to assess the suitability of susceptibility-weighted imaging (SWI) sequences using the 3T MRI-unit for assessment of potential intraarticular pathologies in patients with acute and chronic torsion trauma of the knee joint. MATERIAL AND METHODS: Sixty-three patients with subacute and chronic rotary knee joint trauma of either the left or right knee were studied using an Achieva MRI 3T device (Philips, Amsterdam, Netherlands). Ground truth was set by two expert radiologists with seven and 10 years of experience in musculoskeletal imaging. Readings were performed separately for meniscus and joint space including synovia, ligaments, and periarticular soft tissue. Haemorrhage was defined as any lesion that was either T1 or SWI positive, without proton density (PD)-hypointensity (calcification). A lesion was defined as any pathology/variant with any signal positivity of either T1, PD, or SWI. RESULTS: A total of 63 patients were included (F : M = 22 : 41). The median age of the cohort was 29 years (range 13 to 71 years). Thirty-nine patients showed a meniscal tear, and only three of them (7.7%) demonstrated a meniscal haemorrhage. A total of 18 patients suffered from a periarticular injury, and 16 patients (88.9%) demonstrated a concomitant periarticular haemorrhage. CONCLUSIONS: These data suggest that SWI can be used for the diagnosis of intra- or periarticular blood metabolites because their potential have an impact on mechanical conflict with the surface of the knee joints, in particular the cartilage and their effect on malacic lesions, but it performs poorly in the detection of meniscal pathologies.