David Stoffel, MD

AI
Radiology AI: Going beyond the algorithm
RapidAI
AI is revolutionizing the way we deliver healthcare, especially in radiology.
May 29, 2024
Ai
Page 1 of 1
Top Stories
Representative longitudinal chest CT images and five-year parametric response mapping (PRM), pulmonary vascular CT reconstructions, and hyperpolarized xenon-129 (Xe-129) ventilation MRI scans from survivors of nonsevere and severe COVID-19 pneumonia. (A–F) Images in a 68-year-old male survivor of nonsevere COVID-19 pneumonia, (G–L) 62-year-old male survivor of severe COVID-19 pneumonia, and (M–R) 55-year-old male survivor of severe COVID-19 pneumonia. For each participant, the first three columns show coronal chest CT images from the acute phase (A, G, M), two-year follow-up (B, H, N), and five-year follow-up (C, I, O) (left to right). The fourth column (D, J, P) shows a coronal PRM image for each participant at five-year follow-up derived from paired inspiratory and expiratory CT scans, showing the spatial distribution of lung functional categories. Green indicates normal lung tissue, yellow indicates functional small airway disease, and red indicates emphysema. The second-to-last column shows volume-rendered small pulmonary vessel visualization (red) at five-year follow-up per participant (E, K, Q). The column on the far right (F, L, R) shows a hyperpolarized Xe-129 MRI ventilation defect percentage (VDP) map at five-year follow-up per participant. Dark blue represents high Xe-129 signal intensity, corresponding to well-ventilated lung regions, whereas red represents no Xe-129 signal intensity, corresponding to ventilation defects. At five-year follow-up, the 68-year-old survivor of nonsevere COVID-19 pneumonia (top row) showed near-complete radiologic resolution, no respiratory symptoms, and preserved pulmonary function. In contrast, the 62-year-old survivor of severe COVID-19 pneumonia (middle row) showed persistent fibrotic linear opacities without respiratory symptoms and mildly reduced pulmonary function. The 55-year-old survivor of severe COVID-19 pneumonia (bottom row) showed persistent scattered fibrotic linear opacities and focal emphysematous changes in both lungs, with dyspnea and impaired gas exchange function. The VDP values obtained from F, L, and R were 7.7%, 7.1%, and 6.3%, respectively.
CT
What are the effects of COVID-19 pneumonia after 5 years?
After five years, residual lesions persisted in 35.6% of survivors (37 of 104).
Nuclear Medicine
Molecular Imaging
USC researchers develop “plug-and-play" platform for PET tracers
Representative MRI scans for which the independently assigned imaging-derived extranodal extension (iENE) grades differed among the readers. (A) Axial and sagittal images in a 56-year-old male patient with nasopharyngeal carcinoma and cervical nodal metastases. Readers 1 and 3 interpreted the finding as a metastatic lymph node invading the left sternocleidomastoid muscle (arrow) and assessed an iENE grade of 3, whereas reader 2 assigned a grade of 2. After joint review, the radiologists reached a consensus on the absence of definite sternocleidomastoid muscle invasion, and the final iENE grade was 2. (B) Axial and sagittal images in a 52-year-old male patient with nasopharyngeal carcinoma and cervical nodal metastases. Reader 1 interpreted the findings as a single enlarged metastatic lymph node and assessed an iENE grade of 1, whereas readers 2 and 3 interpreted them as two coalescent metastatic lymph nodes (arrows) and assessed a grade of 2. After joint review, the radiologists reached a consensus on the coalescence of the two metastatic lymph nodes, and the final iENE grade was 2.
MRI
Image-based grading system estimates nasopharyngeal carcinoma severity
Astro
ASTRO 2026
ASTRO 2026 to center on translating radiotherapy data into dialogue
Free Webinar: CT Contrast Injection Reimagined
Sponsor Content
Free Webinar: CT Contrast Injection Reimagined
More in AI
UltraSight adds $24 million in new financing
By AuntMinnie.com staff writers
The firm will use the funds in part to expand commercially in the U.S.
September 24, 2026
Money Bills Sky Line
Altis Labs raises $25M for CT AI tool
By AuntMinnie.com staff writers
IPRO is designed to generate survival predictions from routinely acquired CT scans.
September 21, 2026
Cash
LLM on par with head-and-neck subspecialists in analyzing MRI reports
By Amerigo Allegretto
GPT-5-Thinking yields similar diagnostic accuracy compared to subspecialists focusing on orbital and head-and-neck MRI.
September 16, 2026
Mri Brain Head 400
Cognita wins $1.29M FDA contract to evaluate radiology AI
By AuntMinnie.com staff writers
The 18-month contract, which took effect June 22, centers on what Cognita calls an "LLMs-as-a-jury" approach.
September 16, 2026
Ai 1
Merge launches MergeIQ AI layer for radiology workflow orchestration
By AuntMinnie.com staff writers
Initial applications for the layer aim to inform diagnostic reading workflows without the need to switch between systems.
September 15, 2026
Image (1)
Epsilon Health raises $27.6M for AI-native radiology practice
By AuntMinnie.com staff writers
The funding will support market expansion, clinical partnerships, and infrastructure investment for the company.
September 10, 2026
Artificial Intelligence Ai Suit 400
Rubric safeguards patient-friendly AI-generated imaging reports
By Amerigo Allegretto
The rubric includes clarity, content, certainty, tone, and verbosity as core attributes.
September 9, 2026
Radiological Report 400
AI model on par with experts in finding femoral-neck fractures
By Amerigo Allegretto
The model improved expert performance in detecting these fractures on pelvic or hip radiographs.
September 9, 2026
Example anteroposterior (AP) pelvic radiographs showing simulated acquisition artifacts used for stage 1 artifact-robust pretraining. Images are derived from the same AP pelvic radiograph from a 75-year-old woman with a CT- or MRI-confirmed left femoral-neck fracture. (A) Original AP pelvic radiograph. (B) Simulated grid or cable-shadow artifact. (C) Simulated motion-blur artifact. (D) Simulated sensor saturation or overexposure artifact.
MRI-based model shows changes over time in multiple myeloma patients
By Amerigo Allegretto
Whole-body MRI could serve as a scalable biomarker for risk stratification in multiple myeloma patients.
September 4, 2026
Multiple Myeloma 400
Heartvue.ai gets FDA nod for cardiac MRI analysis software
By AuntMinnie.com staff writers
The platform allows for viewing, post-processing, and quantitative evaluation of cardiovascular MR images.
September 3, 2026
Heartvue
AI cuts chest CT reporting time
By Will Morton
Exploratory modeling suggested an approximate reduction of 0.5 full-time equivalent radiologist workload.
September 1, 2026
Example of AI-assisted pulmonary nodule detection and longitudinal volumetric assessment in a 65-year-old woman with peripheral arterial disease, a 24-pack-year smoking history, emphysema, and a family history of lung cancer. An incidental 8.5-mm right lower lobe pulmonary nodule is identified at CT angiography of the abdomen in July 2022 but does not receive follow-up. Subsequent imaging demonstrates interval growth, and CT-guided biopsy confirms stage IA lung adenocarcinoma. Contrast-enhanced axial chest CT images obtained on February 2, 2024, before robotic-assisted thoracoscopic segmentectomy, show a 12.1-mm spiculated right lower lobe pulmonary nodule. (A) Conventional contrast-enhanced axial chest CT image without AI assistance shows a 12.1-mm spiculated right lower lobe pulmonary nodule. (B) Corresponding CT image with AI-assisted pulmonary nodule detection, automated segmentation, and quantitative nodule assessment identifies a solid pulmonary nodule (nodule #1) measuring 13 × 8 (11) mm, with a volume of 739 mm3, a 45% volumetric increase compared with the previous contrast-enhanced chest CT performed on October 9, 2023 (510 mm3), and an estimated volume doubling time (VDT) of 216 days. (C) AI-generated longitudinal nodule analysis displays automated segmentation of the current (February 2, 2024) and previous (October 9, 2023) CT examinations, 3D nodule reconstruction, and quantitative volumetric assessment for longitudinal follow-up. The AI interface is displayed in the original software language (Dutch).
Nanox AI signs distribution deal for HealthOST software
By AuntMinnie.com staff writers
The distribution deal with Vertec Scientific covers an initial three-year term.
August 27, 2026
Business Handshake 400
Page 1 of 417
Next Page