The edition · Radiology
Commercial AI cut pulmonary nodule reporting time by 15% across 39,000 chest CTs
A real-world before-and-after study puts a number on what AI does to reporting time, saline tract sealing more than halves pneumothorax after CT-guided lung biopsy, and photon-counting CT matches MRI for breast staging while missing nearly half the microcalcifications.
The edition in brief
AI in radiology is usually sold on accuracy and bought on throughput, and throughput has rarely been measured. A retrospective study of 39,323 chest CT examinations at one tertiary centre, split around the introduction of commercial nodule software, found adjusted median reporting time falling from 21.3 to 18.2 minutes — a 14.6% reduction, adjusted hazard ratio 1.17. The effect was uneven: 41.1% faster for ECG-gated thoracic CT and 25.0% for thoracic radiologists, less elsewhere. It is a before-and-after design, so it cannot separate the software from everything else that changed over three years. The most directly usable finding is procedural. A meta-analysis of seven studies and 1,455 patients found saline tract sealing after CT-guided lung biopsy reduced pneumothorax with a risk ratio of 0.46 and chest tube placement with a risk ratio of 0.22. That is a technique requiring no new equipment. Photon-counting CT was compared against MRI, mammography and FDG PET/CT for pretreatment breast assessment in 126 women. It agreed closely with MRI on T category and was 44 percentage points more sensitive than mammography for additional lesions — but missed 44% of microcalcifications that mammography found. The ACR has published its 2026 Appropriateness Criteria update for myelopathy.
Saline tract sealing halves pneumothorax after CT-guided lung biopsy
Adopt saline tract sealing after CT-guided lung biopsy: it more than halves pneumothorax and cuts chest tube placement by around 80%, using nothing you do not already have.
Commercial nodule AI cut reporting time by 15%, but not evenly
Commercial nodule AI cut chest CT reporting time by about 15% in real-world use, with the benefit concentrated in subspecialist readers rather than in the hardest reads.
PET/CT rules lateral nodes out in rectal cancer; MRI does not
When a lateral node in rectal cancer would change the operation, PET/CT is the test that confirms it — specificity 0.97 against 0.82 for MRI — but neither test is sensitive enough to rule it out.
ACR publishes the 2026 Appropriateness Criteria update for myelopathy
Nothing from the drug regulators today; the ACR has updated its Appropriateness Criteria for myelopathy, which is the document your urgent spinal requests will be judged against.
Photon-counting CT matches MRI for breast staging but misses microcalcifications
Photon-counting CT staged breast cancer about as well as MRI in a small prospective study, but missed 44% of microcalcifications — promising for staging, not a replacement for mammography.
Read the rest in the app
You have read your two free briefings this month. The app carries all 27 specialties, every morning, free — and this one is waiting in it.
Scan to keep reading on your phone. No account needed to start.
Tomorrow morning, before your first patient
One edition a day for radiology, written by the desk, every claim tied to its paper. Six minutes.
Get the app — free