article thumbnail

What can we do to increase global access to imaging?

AuntMinnie

In 2018, we decided that instead of reading an x-ray sent to us by charities, we could read an x-ray for charities. The response was overwhelming. Many of the radiologists wanted to contribute and support our colleagues doing charitable work. Emergency Medical Services (EMS) in Tijuana, Baja California, Mexico.

X-ray 299
article thumbnail

FES-PET shows promise staging patients with low-grade breast cancer

AuntMinnie

Thus, the researchers aimed to determine prospectively whether 18F-FES PET improves staging for patients with clinical stage II/III or local-regional recurrent, grade 1 or 2, ER-positive breast cancer compared with standard F-18 FDG-PET. The full study is available here.

PET Scan 283
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

AuntMinnie 2018: NIH releases massive database of chest x-rays

AuntMinnie

Our top article in 2018 covered an important early development that supported efforts to train AI algorithms. The database was created from studies of 30,000 patients who were seen at the NIH Clinical Center in Bethesda, MD; the information has been anonymized to protect patient identities. Image courtesy of the NIH.

X-ray 147
article thumbnail

Generative AI, radiologist shortages feature in 2024 Minnies

AuntMinnie

Middlebrooks, MD, Mayo Clinic, Jacksonville, FL Erik H. Middlebrooks, MD, of the Mayo Clinic in Jacksonville, FL. Given the extensive array of sequences and techniques employed in clinical imaging, we must address the inherent challenges associated with each," he noted. Middlebrooks, MD.

article thumbnail

Adding AI to brain MRI finds previously occult epilepsy lesions in kids

AuntMinnie

MELD Graph's] clinical implementation holds promise for early diagnosis and improved management of focal epilepsy, potentially leading to better patient outcomes," Ripart and colleagues wrote. The study was published February 24 in JAMA Neurology. in patients who were seizure-free a year after surgery and 63.7%

MRI 158
article thumbnail

BERT-based AI poised for use in radiology

AuntMinnie

BERT (Bidirectional Encoder Representations from Transformers) is a natural language processing (NLP) foundation model introduced in 2018. The authors conducted a search on PubMed for literature on BERT-based models and NLP tasks in radiology from January 2018 to February 2023. Google’s Bard chatbot is based on BERT.

Radiology 306
article thumbnail

Deep learning combines breast imaging data to predict cancer prognosis

AuntMinnie

Deep-learning models could have potential as predictive tools for breast cancer prognosis, a study published January 17 in Clinical Breast Cancer has found. The researchers included data from 1,242 patients recruited between 2013 and 2018 and divided them into training (n = 1,014) and testing groups (n = 228).

Imaging 298