Dr. Christopher Austin

IS
3 questions to shape the future of AI and radiology
The introduction of disruptive healthcare technologies rarely threatens the role of the clinician -- but radiology is fast becoming the exception. In this column, Dr. Christopher Austin of GE Healthcare suggests three questions that radiologists should ask themselves if they want to lead and not follow the changes that are coming.
November 15, 2016
2016 11 14 12 36 15 302 Austin Christopher 400
Page 1 of 1
Top Stories
Radiation Symbol
CT
CT 5-star quality rating system supports optimization
The rating framework demonstrated robust reproducibility, with three-reader concordance reaching up to 93% in highly standardized centers.
Radiological Report 400
Ultrasound
READ-DVT model performs well in finding DVT from ultrasound reports
Dexa
Digital X-Ray
Bone scan testing has fallen 35% among Medicare beneficiaries
Child Girl Stuffed Animal 400
MRI
MRI-based models may predict atypical brain development in children
Nominations Are Open — 2026 Minnies
Sponsor Content
Nominations Are Open — 2026 Minnies
More in Home
CT 5-star quality rating system supports optimization
By Will Morton
The rating framework demonstrated robust reproducibility, with three-reader concordance reaching up to 93% in highly standardized centers.
August 7, 2026
Radiation Symbol
READ-DVT model performs well in finding DVT from ultrasound reports
By Amerigo Allegretto
The AI model accurately identified the presence or absence of deep vein thrombosis on unstructured ultrasound reports.
August 7, 2026
Radiological Report 400
Bone scan testing has fallen 35% among Medicare beneficiaries
By Will Morton
Declines in testing were greatest among certain underserved groups.
August 7, 2026
Dexa
MRI-based models may predict atypical brain development in children
By Amerigo Allegretto
The models could provide a framework for identifying which adolescents are at higher risk of developing psychiatric conditions.
August 7, 2026
Child Girl Stuffed Animal 400
Ultrasound MinnieCast, Episode 14: Weathering the sonographer shortage
By Amerigo Allegretto
SDMS President Aubrey Rybyinski discusses how clinics can address sonographer vacancies.
August 7, 2026
Minnie Cast Thumbnail (18)
Avoiding the ED cuts urgent CT turnaround time by half
By Will Morton
This is the first reported pilot of an expedited outpatient direct-to-CT imaging program designed to promote ED avoidance.
August 6, 2026
Emergency2
VLMs miss most lung nodules on chest x-rays
By Will Morton
Findings indicate poor performance of six VLMs for lung nodule detection on chest x-rays.
August 6, 2026
Chatgpt2
Patient-friendly radiology reports improve family comprehension
By Will Morton
Terminology in radiology reports can be difficult for patients and families to comprehend.
August 5, 2026
Pediatric Imaging
Early CTA leads to improved stroke outcomes for patients with BCVI
By Amerigo Allegretto
Early CTA is linked to reduced stroke, decreased complications, and reduced intensive care unit length of stay.
August 5, 2026
Ct Scanner 400
Most histotripsy procedures used for metastatic disease treatment
By Amerigo Allegretto
Trends suggest that histotripsy has low rates of procedure-related complications and is mostly performed in outpatient settings.
August 5, 2026
Liver Cancer 400
Imaging turnaround times continued to climb in 2024
By Erik L. Ridley
The largest increases were found in ultrasound and x-ray.
August 4, 2026
Radiologist Computer Screen X Ray
DBT-based foundational model classifies breast density
By Amerigo Allegretto
DBT-DINO showed strong performance in classifying breast density from DBT images.
August 4, 2026
(A) Free-response receiver operating characteristic (FROC) curve for DBT-DINO and DINOv2 (Meta AI) on the detection task. DINOv2 achieved higher sensitivity than DBT-DINO across most false-positive thresholds. (B) Detection rates of DBT-DINO and DINOv2 for lesions that were ultimately found to be benign (n = 70) and lesions that were found to be cancerous (n = 66). Error bars represent 95% CIs estimated via patient-level bootstrapping with 1000 repetitions. Both models showed similar detection rates for cancerous lesions, whereas DINOv2 detected more benign lesions than DBT-DINO. (C) Example bounding box predictions for DBT-DINO and DINOv2 on the detection test set. Each image is a single two-dimensional section from a three-dimensional digital breast tomosynthesis volume; the first column shows a mediolateral oblique view, and the second and third columns show craniocaudal views. Both models struggled to detect very small lesions, such as the 3-mm-diameter lesion shown in the first column. FP = false positive.
Page 1 of 243
Next Page