Amerigo Allegretto

[email protected]

SIIM: Quality management needed for successful use of imaging AI

A keynote given at the SIIM-ACR Data Science Summit shared how quality management is important in using imaging AI.

June 9, 2026

AI may provide early breast cancer alerts from mammograms

Commercial AI systems could provide early alerts for breast cancer by picking out early signs of the disease on mammograms.

June 9, 2026

Screening mammograms and AI score changes are depicted over time in two individuals with screen-detected cancer. Full-field digital mammograms show craniocaudal (top) and mediolateral (bottom) views of the left and right breast. The description below each mammogram indicates whether AI scores from three AI-based computer-aided detection systems (AI-1, AI-2, and AI-3) were above or below the 90th percentile. (A) Mammograms from three screening time points (in 2009, 2011, and 2014) in an individual who was diagnosed in February 2014 (at age 73 years) with a left-sided 25-mm grade 2 invasive breast carcinoma, no special type (arrow). Mammographic breast density was classified as BI-RADS B on all three mammograms. (B) Mammograms from four screening time points (in 2009, 2011, 2013, and 2015) in an individual who was diagnosed in October 2015 (at age 65 years) with a left-sided 45-mm grade 2 lobular carcinoma (arrow). Mammographic breast density was classified as BI-RADS C on all four mammograms. Screen-detected cancers were defined as those diagnosed within 90 days for individuals who were recalled at screening (*).

Most women with BACs have no MACE history

Many women with BACs on mammography likely have no history of MACE, researchers found.

June 8, 2026

Mammography Breast Ipad Patient 400 (1)

Women's Imaging MinnieCast, Episode 10: To treat or not to treat DCIS?

Lars Grimm, MD, discusses challenges in DCIS care and his work in the COMET study.

June 5, 2026

Minnie Cast Thumbnail (9)

Image-guided focal laser ablation effective for prostate cancer

MRI-directed, ultrasound-guided TPLA may be a promising technique to treat prostate cancer while avoiding radical therapies.

June 3, 2026

Preablation, postablation, and recurrence multiparametric MRI scans depict a 63-year-old man treated with transperineal focal laser ablation (TPLA) for localized prostate cancer. Clinical parameters included an initial prostate-specific antigen (PSA) level of 7.2 ng/mL, a Prostate Imaging Reporting and Data System (PI-RADS) grade 4 lesion (red circles) in the right apical peripheral zone, and a maximum tumor length of 5 mm. MRI-guided targeted biopsy confirmed a Gleason score 3+4 prostate cancer tumor. (A) Pre-ablation axial T2-weighted MRI scan and apparent diffusion coefficient (ADC) image shows the apical PI-RADS 4 lesion (circles). (B) Six-month post-ablation axial T2-weighted MRI scan and ADC image show cystic necrosis (arrows). There was no evidence of recurrence; the PSA level was 1.5 ng/mL. (C) One-year after ablation, the patient’s PSA level had increased to 4.3 ng/mL. Axial T2-weighted MRI scan and the ADC image shows a recurrent lesion (blue circles) in the right apical peripheral zone adjacent to the ablation scar. Targeted biopsy confirmed Gleason score 3+4 prostate cancer, which was classified as in-field recurrence of clinically significant prostate cancer and subsequently re-treated with TPLA. In summary, serial multiplanar MRI demonstrates treatment response after TPLA with post-ablation necrosis, followed by MRI-detected IFR confirmed with biopsy at 12-month follow-up. Multiparametric MRI was performed with a 3.0-T MRI scanner (Skyra; Siemens Healthineers) using T2-weighted, diffusion-weighted, and ADC sequences, with gadobenate dimeglumine contrast material administration (Bracco Diagnostics).

AI approach could improve DBT efficiency

AI-based slab reconstruction may help improve screening DBT workflows while not compromising on image quality.

June 2, 2026

Slab reconstruction provides visualization of subtle architectural distortion similar to that of standard 1-mm slices in a false-positive screening exam. Images include breast exams from a 45-year-old woman who underwent screening mammography. Craniocaudal tomosynthesis images with (A) 1-mm slices and (B) 6-mm slab reconstructions show an area of architectural distortion in the subareolar region of the left breast (arrow). (C) Targeted ultrasound imaging shows a corresponding irregular hypoechoic mass (arrow), which was subsequently biopsied. Pathologic examination revealed a sclerosing papillary lesion.

SNMMI: Theranostic approach may treat PSMA-negative prostate cancer

A theranostic approach could help improve PET imaging for neuroendocrine prostate cancer care.

June 2, 2026

RET-targeted PET tracer highlights neuroendocrine prostate cancer tumors. Representative PET imaging shows strong tumor uptake of the RET-binding peptide tracer [⁶⁸Ga]Ga-DOTA-RET-L7 in a neuroendocrine prostate cancer (NEPC) model, supporting highly specific, high-contrast detection.

SNMMI: Point-of-care PET system may guide interventional procedures

A portable, point-of-care PET system showed success in imaging organs and may be helpful in interventional guidance.

June 1, 2026

(a) Benchtop portable POC-PET prototype system. (b) Phantom imaging experiment setup. (c) Comparison of conventional full-data MLEM reconstruction with incremental OSEM reconstruction.

AIUM: Capacity building needed for global ultrasound initiatives

Ultrasound is useful in low-resource settings, but imagers in global health have some important considerations to make.

May 30, 2026

AIUM: Which ultrasound gel alternative is best?

KY Jelly, aloe vera, and glucomannan may be practical substitutes for commercial ultrasound gel in low-resource settings.

May 30, 2026

Keith Barron, MD, shares findings at AIUM 2026 on which ultrasound gel alternatives may be best for different environments in low-resource settings.

Page 2 of 66

Nina Kottler, MD

SIIM: Nina Kottler speaks on improving efficiency with AI

Nina Kottler, MD, speaks with AuntMinnie about how radiologists are using AI to improve workflow efficiency.

Bradley Erickson, MD, PhD

SIIM: Brad Erickson talks research challenges, retirement

SIIM: Operational consideration needed for AI in radiation oncology

Minnie Cast Thumbnail (10)

Ultrasound MinnieCast, Episode 10: How to apply POCUS oversight in your hospital

Webinar: AI for CT & PET/CT Imaging

Webinar: AI for CT & PET/CT Imaging

SIIM: LLMs have tradeoffs in energy use for imaging tasks

By Amerigo Allegretto

Research presented at SIIM 2026 shows that reasoning LLMs have energy tradeoffs for their performances.

June 10, 2026

Img 6956 fjv Q1mbuv L

AI gives a boost to cardiac MRI risk prediction

By Kate Madden Yee

Accurate risk prediction for coronary heart disease helps clinicians guide patient therapy and follow-up.

June 10, 2026

C-index for Cox regression and random survival forests models using two feature sets. Adding historical registry data decreases the C-index for Cox regression but increased it for the random survival forests model, consistent with the non-linear structure in the registry data.

Philips Future Health Index quantifies benefits of AI in healthcare

2026 report takes AI beyond potential.

June 10, 2026

MSK AI tool for ultrasound shows promise for assisting novice imagers

The software evaluated for standard plane recognition and automatic key anatomy segmentation.

June 9, 2026

AI-acquired standardized planes. Example ultrasound images acquired in clinical settings with the on-cart, AI-based software, illustrating automated acquisition and anatomic annotation of three standard planes: (A) S5 dorsal longitudinal plane of the wrist joint, (B) S11 transverse section of the proximal carpal tunnel, and (C) S14 transverse section of the second and third flexor tendons. A1 = trochlea A1, Cap = capitate, C-M.JS = recess of the capitate-metacarpal joint, D&Ss = flexor digitorum profundus and superficialis tendons, FCR = flexor carpi radialis tendon, FD = flexor digitorum tendon, FPL = flexor pollicis longus tendon, L-C.JS = recess of the lunate-capitate joint, Lun = lunate, MN = median nerve, Pis = pisiform, Rad = radius, R-C.JS = recess of the radiocarpal joint, Sca = scaphoid, UA = ulnar artery, UN = ulnar nerve, 3rd Met = third metacarpal.

fMRI reveals postmenopausal brain connectivity shifts in midlife women

By Kate Madden Yee

The findings suggest that menopause represents "an important neurological transition," researchers noted.

June 9, 2026

Network-level analysis comparing functional association strength between ROIs of pre- and postmenopausal groups. Lower levels of connectivity were identified among one cluster (F3,106 = 8.84, Puncorrected < 0.001, PFDR = 0.012) in the postmenopausal group, which included the right supramarginal gyrus anterior division, right planum temporale, and right Heschl’s gyrus, among others. FDR, false discovery rate; ROI, region of interest.

Air pollution tied to worse coronary disease on CT, especially in women

By Kate Madden Yee

The strongest effects of pollution exposure is seen in women, even at moderate levels typical of high-income countries.

June 9, 2026

Axial images from unenhanced calcium score cardiac CT (left) and curved planar reformation images from CT angiography (right) show that higher long-term exposure to air pollution is associated with greater coronary artery calcium and more obstructive coronary artery disease (CAD). Top row: Images in a 68-year-old male patient with higher 10-year mean ambient air pollution exposure (7.9 μg/m3 for particulate matter measuring ≤2.5 μm in diameter [PM2.5] and 17.4 parts per billion [ppb] for NO2) with extensive CAD (coronary artery calcium score [CACS] >1,000 and obstructive CAD [≥70% diameter stenosis]). Bottom row: Images in a 57-year-old female patient with lower 10-year mean ambient air pollution exposure (6.3 μg/m3 for PM2.5 and 4.6 ppb for NO2) with no CAD (CACS = 0 and no obstructive stenosis).

SIIM: Quality management needed for successful use of imaging AI

By Amerigo Allegretto

A keynote given at the SIIM-ACR Data Science Summit shared how quality management is important in using imaging AI.

June 9, 2026

AI may provide early breast cancer alerts from mammograms

By Amerigo Allegretto

Commercial AI systems could provide early alerts for breast cancer by picking out early signs of the disease on mammograms.

June 9, 2026

Screening mammograms and AI score changes are depicted over time in two individuals with screen-detected cancer. Full-field digital mammograms show craniocaudal (top) and mediolateral (bottom) views of the left and right breast. The description below each mammogram indicates whether AI scores from three AI-based computer-aided detection systems (AI-1, AI-2, and AI-3) were above or below the 90th percentile. (A) Mammograms from three screening time points (in 2009, 2011, and 2014) in an individual who was diagnosed in February 2014 (at age 73 years) with a left-sided 25-mm grade 2 invasive breast carcinoma, no special type (arrow). Mammographic breast density was classified as BI-RADS B on all three mammograms. (B) Mammograms from four screening time points (in 2009, 2011, 2013, and 2015) in an individual who was diagnosed in October 2015 (at age 65 years) with a left-sided 45-mm grade 2 lobular carcinoma (arrow). Mammographic breast density was classified as BI-RADS C on all four mammograms. Screen-detected cancers were defined as those diagnosed within 90 days for individuals who were recalled at screening (*).

Podcast: Pandharipande talks about leadership as Penn Radiology chair

What is the field of radiology looking for?

June 8, 2026

Keeping Up With The Radiologists Podcast Thumbnail

Radiology job market report casts doubt on U.S. radiologist shortage

Report reveals where and why radiology jobs are hard to fill.

June 8, 2026

Career Jobs Adobe Stock 468964741 Alex

X-ray score linked to hip fracture risk in the elderly

Abdominal aortic calcification (AAC) scores of 5 or higher were significantly associated with hip fractures.

June 8, 2026

Abdominal aortic calcification (AAC) score grading: 0 - no calcific deposits in front of the vertebrae; 1 - small scattered calcific deposits filling less than 1/3 of the longitudinal wall of the aorta; 2 - 1/3-2/3 of the wall calcified; 3 - 2/3 or more of the wall calcified.

Most women with BACs have no MACE history

By Amerigo Allegretto

Many women with BACs on mammography likely have no history of MACE, researchers found.

June 8, 2026

Mammography Breast Ipad Patient 400 (1)

Page 2 of 234