Penile Ultrasound Integral to Diagnosing Erectile Dysfunction Cause

Ultrasound of the penis can play a vital role in determining the underlying cause of erectile dysfunction in men who don’t respond to medication.

Although prescription drugs have significantly – and successfully – changed how providers treat erectile dysfunction (ED), for those men who don’t see improvement, relying on ultrasound can be the key to identifying next steps and possible treatments, according to an article published in the American Journal of Roentgenology.

“Radiologists must be familiar with the imaging protocol, the limitations of the technique, and the interpretations of its findings, to warrant an accurate diagnosis and appropriate patient management,” said lead study author Cristian Gómez Varela, from the radiology department in Complejo Hospitalario Universitario de Pontevedra in Spain. “It is essential to differentiating between the vascular and nonvascular causes of the ED and, therefore, determining appropriate management of the patient.”

The Conditions

When used correctly – with a high-frequency linear array (7.5-12 MHz) and full-length images of the penis in both flaccid and erect states – ultrasound can contribute to successfully diagnosing three vascular-related causes of ED, Varela said.

Peyronie’s Disease (PD): This penile deformity caused by scar tissue that develops after repeated injury results in painful erections. In most cases, MRI is the preferred modality to assess PD. But, gray-scale ultrasound can be very helpful in diagnosis and follow-up, assessing size and location of plaques, detecting small non-palpable lesions or the involvement of the penile septum, or evaluating disease progression. In addition, sonoelastography can estimate tissue stiffness, as well as identify plaques that go undetected on gray-scale ultrasound.

Penile Fracture: Caused by trauma to the penis, usually during sexual intercourse, fracture can cause a rupture in the membrane responsible for trapping blood in the penis to sustain an erection. Ultrasound can make pinpointing any ruptures easier, as fractures are seen as dark breaches in the membrane.

Priapism: This condition can occur in two forms – both high-flow and low-flow. Low-flow priapism is considered a medical emergency as it can cause tissue death and, if left untreated, permanent ED. Ultrasound can identify tissue thickening and scarring in the arteries of the penis, and Doppler ultrasound can also pinpoint inadequate blood retention.
Given its effectiveness is identifying these vascular-related conditions behind ED, according to Varela and colleagues, ultrasound is the preferred method for initially evaluating the penile anatomy and blood flow. Not only is it readily available, but it is minimally invasive and can be well tolerated by patients.

AI helps characterize breast masses on ultrasound

By Erik L. Ridley, AuntMinnie staff writer

February 4, 2020 -- A breast ultrasound artificial intelligence (AI) algorithm was able to differentiate breast masses at a high level of accuracy by combining analysis of B-mode and color Doppler images, according to research published online January 31 in European Radiology. It even yielded comparable performance to experienced radiologists.

A research team led by Xuejun Qian, PhD, of the University of Southern California and Bo Zhang, PhD, of Central South University in Hunan, China, found that their deep-learning algorithm had substantial agreement with radiologists for providing BI-RADS categorization. It also yielded high sensitivity and specificity.

"The decisions determined by the model and quantitative measurements of each descriptive category can potentially help radiologists to optimize clinical decision-making," the authors wrote.

Breast ultrasound interpretation has been characterized by variable inter- and intrareader reproducibility, with higher false positives than other imaging tests, according to the researchers. Seeking to develop an automated breast classification system that could improve consistency and performance, they gathered a training set of 103,212 breast masses and a validation set of 2,748 independent breast masses at two Chinese hospitals between August 2014 and March 2017. They also assembled a test set of biopsy-proven 605 breast masses classified as BI-RADS 2 to 5 from March 2017 to September 2017.

Next, the researchers trained two convolutional neural networks: one based just on B-mode images and the other based on both B-mode and color Doppler images. On the validation cases, the model based on both B-mode and color Doppler image analysis had a higher level of agreement (kappa = 0.73) with the original interpreting radiologists for BI-RADS categorization than the network based only on B-mode images (kappa = 0.58). The difference was statistically significant (p < 0.001).

They then evaluated the performance of both models on the test set of 605 masses.

Performance of neural networks for classifying breast masses on test set
	Model based on B-mode images	Model based on both B-mode and color Doppler images
Sensitivity	96.8%	97.1%
Specificity	75.5%	88.7%
Accuracy	85.3%	92.6%
Area under the curve (AUC)	0.956	0.982

The researchers noted that the addition of color Doppler information improved the algorithm's specificity and accuracy on a statistically significant basis (p < 0.001). The small increase in sensitivity was not statistically significant, however.

"Overall, Doppler information should be incorporated into breast [ultrasound] examination protocols for breast masses, and the use of such a dual-modal system may improve cancer diagnostics," the authors wrote.

The researchers also had 10 radiologists with three to 20 years of breast imaging experience assess the 605 masses in the test set. Nine of the 10 radiologists had a sensitivity that ranged from 87.8% to 94.6%, while the last radiologist had 64.7% sensitivity. That same radiologist had the highest specificity (98.5%), with the remaining participants producing sensitivity ranging from 84.1% to 91.7%. Overall, the 10 readers produced an AUC of 0.948.

"These results indicate that the performance of model 2 reached the levels of the human experts," the authors concluded.