Paul Davis

[email protected]

Responsive - Making the most of the new banner ad formats

August 5, 2014

Page Layout Showing A Portrait Ad And Its Expansion Dimensions

Responsive - The Power of Landing Pages

August 5, 2014

2015 06 24 17 50 06 429 Inline

Responsive - 7 Deadly Sins of Landing Page Design

August 5, 2014

Responsive - 5 Short Videos to help you improve your eBroadcasts

August 5, 2014

Mismatched Goals

June 29, 2009

Lost in Translation...

February 5, 2008

2008 03 14 14 48 17 706

Agents of Change: The new wave of crawlers, spiders and bots

March 13, 2006

Defining your success

June 7, 2005

Defining your success

June 5, 2005

Rich Media: The power of being rich

March 30, 2005

Page 2 of 3

Adobe Stock 285124452

DEXA reveals tea consumption supports bone health

Moderate-frequency tea consumption was associated with better bone mineral status and more favorable longitudinal changes.

Breast Mammo Computer 400 (3)

AI tools may not meet breast radiologists' expectations in practice

Lung Cancer

Stepped reminders boost CT lung cancer screening

Example cases illustrate the double-edged role of large language model (LLM) rationale quality. (A) A 50-year-old female patient with a palpable anterior chest wall mass (correct diagnosis: solitary fibrous tumor of the pleura). The LLM incorrectly suggested synovial sarcoma but provided a persuasive rationale (quality score: 4 of 5), describing a well-defined nodule at axial contrast-enhanced CT spanning the pleura and intercostal space with heterogeneous strong enhancement. Four of five readers (80%) accepted the incorrect suggestion. FDG = fluorodeoxyglucose. (B) A 61-year-old male patient with diabetes presented with cough, sputum, and dyspnea (correct diagnosis: mucormycosis). The LLM correctly suggested mucormycosis with an excellent rationale (quality score: 5 of 5), integrating the reverse halo sign on serial axial CT images and rapidly progressive cavitary lesions. Three of five readers initially selected incorrect diagnoses; after LLM output, all five selected the correct diagnosis (100% acceptance). Blue and orange reader icons denote high- and low-expertise readers, respectively.

Model confidence, reader expertise affect reader-LLM collaboration

Nominations Are Open — 2026 Minnies

Nominations Are Open — 2026 Minnies

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

This is the first reported pilot of an expedited outpatient direct-to-CT imaging program designed to promote ED avoidance.

August 6, 2026

VLMs miss most lung nodules on chest x-rays

Findings indicate poor performance of six VLMs for lung nodule detection on chest x-rays.

August 6, 2026

Patient-friendly radiology reports improve family comprehension

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

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.

Liebel-Flarsheim recalls Optiray CT contrast agent

By AuntMinnie.com staff writers

The CT contrast agent may contain particulate matter comprising polyethylene, other plastic materials, stainless steel, and glass.

August 4, 2026

Can LLMs fill the communication gap with referring clinicians?

LLMs could potentially help address multiple persistent pain points in radiology workflow.

August 4, 2026

CT-selected thrombectomy shows 1-year benefit in large-core stroke

Notably, the TESLA trial used a noncontrast CT (NCCT)-alone patient selection protocol.

August 3, 2026

MRI-based AI model maps local brain aging

By Amerigo Allegretto

The model showed differences in brain structures for normal cognition, mild cognitive impairment, and Alzheimer’s disease.

August 3, 2026

Page 2 of 243