AuntMinnie

Case example of a false-negative AI result. An 85-year-old female presented to the emergency department with dyspnea. Axial 0.625-mm from CT pulmonary angiography examination with contrast (CTPA) images demonstrate a thin, linear right-sided filling defect extending from the right interlobar pulmonary artery (A and B, red arrows) into the right middle lobar artery (B, yellow arrow), consistent with acute pulmonary embolism (PE). The finding was described in the radiology report; however, the AI result was negative for PE. Adjudication was consistent with acute PE.

Human-AI collaboration beats AI alone for identifying PE

Study findings highlight the continued central role of radiologists for this indication.

Featured

Breast Cancer3

AI model predicts 10-year breast cancer risk

Cropped secondary capture examples. These are illustrative and not intended to imply superiority or inferiority of any device. (A) Posteroanterior radiograph in a 46-year-old female patient. The device correctly identified a right lower lobe nodule projected below the right hemidiaphragm and hilar lymphadenopathy. (B) Posteroanterior radiograph in an 86-year-old female patient with a classic Golden S sign highly suggestive of cancer. Three devices did not identify any findings. (C) The output from one device for the same radiograph as in B. The device placed a contour around the area of abnormality but mislabeled it as segmental collapse, and there are no other elements in the output to raise suspicion of cancer. (D) Posteroanterior radiograph in a 60-year-old male patient -- a case of confirmed lung cancer that was not deemed visible in retrospect. The device identified multiple false-positive abnormalities. (E) Posteroanterior radiograph in a 77-year-old female patient with two right lower lobe nodules. The device mislabeled the abnormality as infection -- a diagnostic term that could incorrectly influence clinical management. (F) Posteroanterior radiograph in a 77-year-old female patient with a right hilar tumor. Most of the lungs have been labeled by the device, with excessive overlap of the abnormality that pragmatically represents an incorrect result. All annotations shown were produced by the devices. LL = lung lesion, LO = lung opacity, PO = pleural other, TBC = tuberculosis.

AI devices vary widely in lung cancer detection

Overview of the study design, including data collection, radiomics model construction, and biologic interpretation. (A) The primary cohort for model development and evaluation in the training and internal test sets includes 168 patients with colorectal cancer (CRC) from center 1 (Fudan University Shanghai Cancer Center), whereas external testing was performed using data from 85 patients from centers 2 (Huashan Hospital, Fudan University) and 3 (Zhongshan Hospital, Fudan University). For model interpretation, RNA sequencing (RNA-seq) data from 18 patients with CRC in center 1 and single-cell data from 35 patients from the Gene Expression Omnibus (GEO) database are incorporated. Mismatch repair (MMR) protein expression, obtained from pathologic reports in electronic medical records (EMRs), was used to identify patients with consensus molecular subtype 1 (CMS1) CRC. Tissue microarrays (TMAs) from surgically obtained CRC tissues were analyzed for immunohistochemical staining of caudal-type homeobox 2 (CDX2), 5-hydroxytryptamine receptor 2B (HTR2B), FERM domain containing 6 (FRMD6), and zinc finger E-box binding homeobox 1 (ZEB1), and the results were subsequently entered into an online classification tool that assigned patients to CMS2, 3, or 4 subtypes. (B) Radiomics workflow for CMS4 prediction. Lesions were manually delineated on T2-weighted imaging (T2WI) and contrast-enhanced (CE) T1-weighted imaging (T1WI), followed by radiomics feature extraction. Feature selection and model development were performed in the training set using machine-learning algorithms with fivefold cross-validation for model selection, and the final model was evaluated in the internal and external test sets using receiver operating characteristic (ROC) curve analysis. (C) Transcriptomic interpretation workflow. Using the radiomics-predicted CMS4 classification, bulk RNA sequencing (RNA-seq) data were used to perform differential expression analysis between predicted CMS4 and non-CMS4 groups, followed by pathway enrichment analyses to assess biologic relevance. Public single-cell RNA sequencing data from the Gene Expression Omnibus database were then used for cell-type–level interrogation to support interpretation of the associated pathways.

MRI-based ML model shows promise in colorectal cancer subtyping

May 19, 2026

The Invisible Force Podcast Album Cover Auntminnie Jan 2026 Thumbnail sra O0 D Ij Z6

Podcast: Expert witness hats come out to begin closing investigation

May 19, 2026

The Wedding Was Easy. The Marriage Is the Work.

The Wedding Was Easy. The Marriage Is the Work.

May 1, 2026

A graphical abstract of the study.

Combined fluoride and lead exposure reduces bone health in youth

May 18, 2026

Podcast: Expert witness hats come out to begin closing investigation

More episodes »

Radiology is Under Pressure

Radiology is Under Pressure

Check out our Cases of the Week!

67-year-old woman with chronic cough

A 67-year-old woman presented with chronic cough.

61-year-old woman with confusion, weakness, incontinence

40-year-old man with right hip finding

Case example of a false-negative AI result. An 85-year-old female presented to the emergency department with dyspnea. Axial 0.625-mm from CT pulmonary angiography examination with contrast (CTPA) images demonstrate a thin, linear right-sided filling defect extending from the right interlobar pulmonary artery (A and B, red arrows) into the right middle lobar artery (B, yellow arrow), consistent with acute pulmonary embolism (PE). The finding was described in the radiology report; however, the AI result was negative for PE. Adjudication was consistent with acute PE.

Human-AI collaboration beats AI alone for identifying PE

AI model predicts 10-year breast cancer risk

AI devices vary widely in lung cancer detection

MRI-based ML model shows promise in colorectal cancer subtyping

Podcast: Expert witness hats come out to begin closing investigation

OmniMRI in the context of reporting.

ISMRM: Researchers highlight advancements in MRI foundation models

Women's Imaging MinnieCast, Episode 8: New NCCN guidance on AI and breast cancer risk

Imaging fellow tries vibe coding to solve radiology challenges

MRI reveals how hidden muscle fat increases risk to heart, metabolism

DL model outperforms breast density in measuring women's cancer risk

Brain Stroke

Maine couple sues radiologist for overlooking warning sign of stroke

Radiology Associates of North Texas flags $51M No Surprises Act costs

ACR issues guidance on stereotactic breast biopsy needle shortage

DeepHealth secures FDA clearance, CE marking for neuro, prostate AI

Azra AI, RevealDx announce partnership

Brain Stroke

Maine couple sues radiologist for overlooking warning sign of stroke

The suit claims that nine hours before the stroke, an imaging exam showed a potential clot in a major artery.

Radiology Associates of North Texas flags $51M No Surprises Act costs

ACR issues guidance on stereotactic breast biopsy needle shortage

More Practice Management

Maine couple sues radiologist for overlooking warning sign of stroke

By AuntMinnie.com staff writers

The suit claims that nine hours before the stroke, an imaging exam showed a potential clot in a major artery.

May 20, 2026

Radiology Associates of North Texas flags $51M No Surprises Act costs

By AuntMinnie.com staff writers

The costs are tied to current No Surprises Act arbitration batching rules and unpaid Independent Dispute Resolution (IDR) awards.

May 20, 2026

ACR issues guidance on stereotactic breast biopsy needle shortage

By AuntMinnie.com staff writers

The shortage began earlier this year after a major manufacturer halted shipments to address a product issue, the ACR said.

May 20, 2026

DeepHealth secures FDA clearance, CE marking for neuro, prostate AI

By AuntMinnie.com staff writers

The company has won multiple regulatory clearances for neuro, prostate, and lumbar MRI AI.

May 20, 2026

Azra AI, RevealDx announce partnership

By AuntMinnie.com staff writers

The partnership builds on Azra AI's recent acquisition of Thynk Health.

May 20, 2026

NRC to ease burden on radiopharmaceutical licensees

By AuntMinnie.com staff writers

The rule would eliminates decommissioning financial assurance (DFA) for all radionuclides with half-lives of 120 days or less.

May 19, 2026

Siemens unveils CT-guided PCI workflow system

By AuntMinnieEurope.com staff writers

The new system combines two components.

May 19, 2026

The combination of Syngo.CT Coronary Cockpit and Syngo PCI Connect gives interventional cardiologists valuable insights on morphology, plaque and lesion details and allows for strategic planning of the intervention.

GE HealthCare opens free AI training program

By AuntMinnie.com staff writers

The company is making more than 20 hours of AI education available at no cost through its HelloAI program.

May 19, 2026

Plus Therapeutics inks AI deal with Ephemeral Technologies

By AuntMinnie.com staff writers

Plus Therapeutics is a clinical-stage pharmaceutical company developing radiopharmaceutical therapies for CNS cancers.

May 19, 2026

HOPPR launches mammography vision-language model

By AuntMinnie.com staff writers

The model was trained on more than 200,000 mammography studies from multiple U.S. sites.

May 19, 2026

ISMRM ShowCast Roundup: 'Ubuntu', the meeting's theme | The state of MRI in Africa | Using AI, fMRI

By Kate Madden Yee

Ubuntu is a South African term that translates to "I am, because we are."

May 19, 2026

Medical societies applaud proposed CEUS training recommendations

By Amerigo Allegretto

Ultrasound societies are voicing support for new proposed training standards by CAAHEP for CEUS education.

May 18, 2026

Contrast Injector 400