Dr. Anton Becker, PhD, and David Gugelmann, PhD

AI
AI-cyberterrorism in radiology: Threat or red herring?
In this Second Opinion article, Dr. Anton Becker, PhD, of Memorial Sloan Cancer Kettering Cancer in New York City and David Gugelmann, PhD, of Exeon Analytics assess the threat posed by artificial intelligence-powered cyberterrorism in radiology.
December 11, 2019
2019 03 26 18 32 2300 Computer Hacker Security 400
Page 1 of 1
Top Stories
Images of a 39-year-old who underwent screening mammography. Right craniocaudal (left) and mediolateral oblique (middle) views from preoperative mammography show suspicious grouped fine pleomorphic calcifications (arrows). After biopsy showed ductal carcinoma of situ (DCIS), patient underwent breast-conserving surgery, yielding final diagnosis of ductal carcinoma in situ (intermediate grade, hormone receptor positive). (Right) Screenshot of an output of a commercial AI tool applied to preoperative mammography. AI detected right breast lesion with score of 95% on both views (concentric colored circles). Present study’s reviewing radiologist deemed AI marking to correspond with site of DCIS.
Womens Imaging
Could AI scoring help with managing DCIS?
An AI model showed associations with recurrence after DCIS surgery and performed comparably to established clinical risk models.
Axial contrast-enhanced CT scan in a 28-year-old premenopausal woman shows an incidentally detected solid-appearing left ovarian lesion (solid arrow) anterior to the uterus (U), associated with trace ascites in the right adnexa and cul de sac (dashed arrows). At pathologic analysis, this was shown to be ovarian dysgerminoma. Two readers misdiagnosed this lesion, one as a leiomyoma and one as an ovarian fibroma.
CT
Clinicians, beware: CT diagnostic accuracy varies by adnexal lesion type
Erin Stephens
Practice Management
Radiology coding update for 2026
Images from two representative cases. (A-C) Images in an 82-year-old man with a calcified plaque in the proximal segment of the left anterior descending artery. (A, B) Curved planar reconstruction images from CCTA with (A) hybrid iterative reconstruction (HIR) and (B) super-resolution deep learning reconstruction (SR-DLR) show that the measured PDS was 66% for the HIR image and 42% for the SR-DLR image. (C) Quantitative analysis of the invasive coronary angiography (ICA) image (reference standard) revealed a PDS of 34% (arrow). (D-F) Images in a 37-year-old woman with a noncalcified plaque in the middle segment of the left circumflex artery. (D, E) Curved planar reconstruction images from CCTA with (D) HIR and (E) SR-DLR show that the measured PDS was 47% for the HIR image and 80% for the SR-DLR image. (F) Quantitative analysis of the ICA image revealed a PDS of 72% (arrow). Blue, red, and yellow lines in A, B, D, and E represent the proximal reference point, stenosed lesion, and distal reference point, respectively, and the insets show the corresponding cross-sectional images.
CT
Super-resolution deep learning reconstruction improves CCTA
Breast Mammo 400
Womens Imaging
Nonsurgical management rising for low-risk DCIS cases
More in Home
Could AI scoring help with managing DCIS?
By Amerigo Allegretto
An AI model showed associations with recurrence after DCIS surgery and performed comparably to established clinical risk models.
February 11, 2026
Images of a 39-year-old who underwent screening mammography. Right craniocaudal (left) and mediolateral oblique (middle) views from preoperative mammography show suspicious grouped fine pleomorphic calcifications (arrows). After biopsy showed ductal carcinoma of situ (DCIS), patient underwent breast-conserving surgery, yielding final diagnosis of ductal carcinoma in situ (intermediate grade, hormone receptor positive). (Right) Screenshot of an output of a commercial AI tool applied to preoperative mammography. AI detected right breast lesion with score of 95% on both views (concentric colored circles). Present study’s reviewing radiologist deemed AI marking to correspond with site of DCIS.
Clinicians, beware: CT diagnostic accuracy varies by adnexal lesion type
By Kate Madden Yee
The modality correctly diagnoses dermoids and simple cysts, but is not as effective at identifying other types of adnexal lesions.
February 11, 2026
Axial contrast-enhanced CT scan in a 28-year-old premenopausal woman shows an incidentally detected solid-appearing left ovarian lesion (solid arrow) anterior to the uterus (U), associated with trace ascites in the right adnexa and cul de sac (dashed arrows). At pathologic analysis, this was shown to be ovarian dysgerminoma. Two readers misdiagnosed this lesion, one as a leiomyoma and one as an ovarian fibroma.
Radiology coding update for 2026
By Erin Stephens
In a new column, Erin Stephens of Healthcare Administrative Partners reviews the 2026 CPT code changes.
February 11, 2026
Erin Stephens
Super-resolution deep learning reconstruction improves CCTA
By Will Morton
The commercially available image reconstruction algorithm outperformed standard hybrid iterative reconstruction for assessing coronary stenosis.
February 10, 2026
Images from two representative cases. (A-C) Images in an 82-year-old man with a calcified plaque in the proximal segment of the left anterior descending artery. (A, B) Curved planar reconstruction images from CCTA with (A) hybrid iterative reconstruction (HIR) and (B) super-resolution deep learning reconstruction (SR-DLR) show that the measured PDS was 66% for the HIR image and 42% for the SR-DLR image. (C) Quantitative analysis of the invasive coronary angiography (ICA) image (reference standard) revealed a PDS of 34% (arrow). (D-F) Images in a 37-year-old woman with a noncalcified plaque in the middle segment of the left circumflex artery. (D, E) Curved planar reconstruction images from CCTA with (D) HIR and (E) SR-DLR show that the measured PDS was 47% for the HIR image and 80% for the SR-DLR image. (F) Quantitative analysis of the ICA image revealed a PDS of 72% (arrow). Blue, red, and yellow lines in A, B, D, and E represent the proximal reference point, stenosed lesion, and distal reference point, respectively, and the insets show the corresponding cross-sectional images.
Nonsurgical management rising for low-risk DCIS cases
By Amerigo Allegretto
Trends show that nonsurgical management of DCIS is rising, paving the way for imaging's role in active surveillance.
February 10, 2026
Breast Mammo 400
Gadoxetate MRI offers high sensitivity for liver cancer screening
By Kate Madden Yee
"Most participants undergoing HCC screening had excellent MRI quality even when ultrasound was limited," researchers noted.
February 10, 2026
2026 02 10 Radiology Lewis Figure2 Thumbnail
Podcast: MRI service engineer faced nightmare with man's entrapment
By Liz Carey
MRI service engineers aren't generally first responders, says MRI safety expert Josh Posh.
February 10, 2026
The Invisible Force Podcast Album Cover Auntminnie Jan 2026 Thumbnail
PET/CT visualizes complications in patients on hemodialysis
By Will Morton
F-18 sodium fluoride PET/CT scans can quantify changes in cardiac and aortic vascular calcifications.
February 9, 2026
2026 02 09 Pet Calcification Thumbnail
DBT-guided biopsies show practical advantages
By Amerigo Allegretto
New research says DBT-guided biopsies lead to less procedure times and radiation exposure compared to mammography-guided biopsies.
February 9, 2026
Breast Dbt Social
Radiology is at an inflection point
By Dhruv Chopra
Radiology is a cornerstone of modern medical diagnostics, but today is at an inflection point, said Civie CEO Dhruv Chopra in a new column.
February 9, 2026
Chopra Dhruv Thumbnail
PSMA-PET/CT best for staging prostate cancer
By Will Morton
The finding is from a head-to-head comparison of PSMA-PET/CT with five other techniques.
February 6, 2026
2026 02 06 Psma Pet Ct Thumbnail
Could CEUS improve BI-RADS assessment?
By Amerigo Allegretto
Adding Contrast-enhanced ultrasound (CEUS) to BI-RADS could help improve classification of breast lesions.
February 6, 2026
Contrast Injector
Page 1 of 201
Next Page