Researchers also noted that mammography-based AI software was associated with over a threefold higher likelihood of false-positive risk scores in patients 61 to 70 years of age in comparison to women 51 to 60 years of age.

Review the case and test your knowledge to make the correct diagnosis.

Do you have a true voice in the direction of the radiology practice or are you more likely to be voting with your feet?

Incorporating dynamic contrast-enhanced MRI, a deep learning model demonstrated a 20 percent higher AUC in external validation testing than clinical factors alone and over a 17 percent higher AUC than radiological factors alone in predicting proliferative hepatocellular carcinoma (HCC).

Catch up on the top radiology content of the past week.

In recognition of National Women’s Health Month, Dana Bonaminio, MD, Amy Patel, MD, and Stacy Smith-Foley, MD, shared their thoughts and perspectives on the recently updated breast cancer screening recommendations from the United States Preventive Services Task Force (USPSTF).

Reportedly trained on thousands of computed tomography scans, the e-Lung software utilizes machine learning to detect and assess the progression of features associated with interstitial lung diseases.

The package of point-of-care ultrasound (POCUS) applications can reportedly facilitate rapid implementation of POCUS into imaging workflows.

The second version of the device reportedly detects T2/T3 fetal ultrasound views with 93.7 percent sensitivity and enables 63 percent of AIUM exam protocols without manual annotation.

Combining clinical and CT features, adjunctive use of a classification and regression tree (CART) diagnostic model demonstrated AUCs for detecting clear cell renal cell carcinoma (ccRCC) that were 15 to 22 percent higher than unassisted radiologist assessments.

An emerging deep learning algorithm had a lower AUC and sensitivity than urological radiologists for differentiating between small renal masses on computed tomography (CT) scans but had a 21 percent higher sensitivity rate than non-urological radiologists, according to new research.

The artificial intelligence (AI)-powered module provides a prostate segmentation tool for MRI-guided transurethral ultrasound ablation (TULSA) procedures in patients with prostate cancer.

While radiologists and other providers may be discouraged by insurer denials saying the use of a technological advance is “unproven and investigational,” 82 percent of appeals for prior authorization denials were approved in 2021.

While acknowledging variable accuracy overall with CT-derived fractional flow reserve (FFR-CT) values, researchers found that the accuracy rate increased to 90 percent for FFR-CT values greater > 0.90 and < 0.49.

Could the principles of operant conditioning reinforce more of a simpatico relationship between radiologists and technologists?

Catch up on the top radiology content of the past week.

In a recent lecture at the 2024 ARRS Annual Meeting, Jordana Phillips, MD, discussed the role of contrast-enhanced mammography in staging breast cancer, evaluating response to neoadjuvant chemotherapy and recalls from screening.

Using a learning network model to discuss challenges and share insights among radiology departments from five different organizations, researchers noted that 87 percent of audited prostate MRI exams had PI-QUAL scores > 4 at the conclusion of the collaborative program.

In a recent interview, Stacy Smith-Foley, M.D., shared her perspective on the shortcomings of the recently issued breast cancer screening recommendations from the United States Preventive Services Task Force (USPSTF).

In a study involving over 1,000 visible prostate lesions on biparametric MRI, a deep learning algorithm detected 96 percent of clinically significant prostate cancer (csPCa) in comparison to a 98 percent detection rate for an expert genitourinary radiologist.