Tag: breast imaging

ABUS Boosts Breast Screening

Posted on by Brian Casey

Automated breast ultrasound led to sharp increases in cancer detection rates and sensitivity when it was performed as a supplement to screening digital mammography in a study of Asian women. 

In Radiology, researchers from South Korea explain the shortcomings of X-ray-based mammography, which has limited sensitivity in women with dense breast tissue. Handheld ultrasound can be used as a screening supplement, but it has drawbacks of its own, such as longer exam time and operator variability. 

ABUS has been proposed as an alternative, acquiring 3D volumes of the entire breast in an automated mode that’s more structured and standardized. ABUS also provides coronal-plane images that can help differentiate malignant from benign lesions.

But most of the studies validating ABUS have been conducted on Western women, and Asian women tend to have mammographically denser breasts.

So researchers decided to test ABUS as a supplement to digital mammography with 2,301 South Korean women who were screened from 2018 to 2019. Women were first screened with digital mammography (either Hologic’s Selenia Dimensions or Siemens Healthineers’ Mammomat Revelation), then received ABUS scans with GE HealthCare’s Invenia ABUS system. 

For women with dense breasts, screening with ABUS and DM turned in better performance than DM alone in multiple categories, including:

  • Higher cancer detection rate per 1,000 screening exams (9.3 vs. 6.5)
  • Better sensitivity (90.9% vs. 63.6%)
  • Higher AUC (0.89 vs. 0.79)
  • Detection of smaller cancers, with a mean size of 1.2 cm vs. 2.3 cm

On the down side, ABUS + DM in women with dense breasts had lower specificity (86.8% vs. 94.6%), driving higher biopsy rates (3.3% vs. 1.9%) and false-positive biopsy rates (2.4% vs. 1.3%).

The Takeaway

In a time when breast cancer inequities are under the microscope, the new study provides encouraging news that imaging technology can help compensate for the shortcomings of the traditional “one size fits all” paradigm of breast screening. 

The results are also a shot in the arm for ABUS as it seeks to cement a role as a complement to X-ray-based screening mammography, although work remains to be done in improving specificity and recall rates.

Breast Screening’s New Gold Standard?

Posted on by Brian Casey

A new study in Radiology on the use of digital breast tomosynthesis for breast screening makes the case that DBT has so many advantages over conventional 2D digital mammography that it should be considered the gold standard for breast screening. 

Unlike 2D mammography, DBT systems scan around the breast in an arc, acquiring multiple breast images that are combined into 3D volumes. The technique is believed to be more effective in revealing pathology that might be obscured on 2D projections.

Previous research already demonstrated the effectiveness of DBT for certain uses, but the new study is notable for its large patient population, as well as its focus on general screening rather than subgroups like women with cancer risk factors such as dense breast tissue.

Researchers led by Dr. Emily Conant of the University of Pennsylvania reviewed DBT’s performance in five large U.S. healthcare systems, with a total study population of over 1 million women. 

The advantages of DBT were notable:

  • Higher cancer detection rate: 5.5 vs. 4.5 per 1k women screened
  • Lower recall rate:  8.9% vs. 10.3%
  • Higher recall PPV: 5.9% vs. 4.3%.

On the negative side, DBT had higher biopsy rates, of 17.6 biopsies per 1,000 women versus 14.5 biopsies for 2D digital mammography. But PPV of biopsy for both techniques was largely the same. 

Researchers note that breast cancer mortality rates have fallen 41% since 1989, a development attributed to earlier diagnosis and better treatment. DBT could help accelerate this trend as it finds more cancers relative to 2D digital mammography.

The Takeaway

This study reinforces the idea that DBT is now the gold standard for breast screening. While mammography vendors have already seen high market penetration for DBT systems, the new study is likely to convince any remaining holdouts that 3D mammography is a necessary technology for any breast imaging facility. 

FDA Finally Moves on Breast Density

Posted on by Brian Casey

After a long wait, the FDA issued a final rule that adds details on breast density reporting to the Mammography Quality Standards Act. The rule takes effect in September 2024 and should go a long way toward clarifying the issue of breast density for patients. 

Breast tissue density is a risk factor for cancer, and dense breast tissue can make it more difficult for radiologists to identify tumors on conventional x-ray mammography. This shortcoming is often not communicated to women who receive “normal” mammograms, but later find out that a cancer was missed.

Prodded by a strong patient advocacy movement, individual states have been passing laws requiring women to be notified of their density status, creating a patchwork of regulation across the U.S. 

The FDA in 2018 agreed to set a national standard by rolling breast density reporting into an update of the MQSA. But the long wait has frustrated many in the breast density advocacy movement.

There are several major components to the new rule, which: 

  • Requires breast imaging facilities to provide patients with a summary of the mammography report written in lay terms that identifies whether patients have dense or non-dense breast tissue.
  • Instructs facilities to include a section in the mammography report explaining the significance of breast density. 
  • Establishes four categories for reporting breast tissue density in the mammography report. 
  • Sets the specific language to be used for reporting density. 

The new rules provide much-needed national consistency in breast density reporting, and will replace the patchwork of state regulation that has developed over the years. Developers of breast density software may also benefit from the new federal rules, as they simplify the number of regulations that need to be tracked. 

The Takeaway

Better late than never. While the FDA should have signed off on this years ago, now that the rules are issued the breast imaging community can move ahead with integrating them into clinical practice. The new rules should also help density reporting software developers by setting a national standard rather than a patchwork of state regulation. 

Multimodal AI Virtual Breast Biopsies

Posted on by Jake Fishman

Radiology Journal detailed a multimodal AI solution that can classify breast lesion subtypes using mammograms, potentially reducing unnecessary biopsies and improving biopsy interpretations. 

Researchers from Israel and IBM/Merative first pretrained a deep learning model with 26k digital mammograms to classify images (malignant, benign, or normal), and used these pretraining weights to develop a lesion subtype classification model trained with mammograms and clinical data. Finally, they trained a pair of lesion classification models using digital mammograms linked to biopsy results from 2,120 women in Israel and 1,642 women in the US. 

When the Israel AI model was tested against mammograms from 441 Israeli women it…

  • Predicted malignancy with an 0.88 AUC
  • Classified ductal carcinoma in situ, invasive carcinomas, or benign lesions with 0.76, 0.85, and 0.82 AUCs
  • Correctly interpreted 98.7% of malignant mammographic examinations and 74.6% of invasive carcinomas (matching three radiologists)
  • Would have prevented 13% of unnecessary biopsies and missed 1.3% of malignancies (at 99% sensitivity)

When the US AI model was tested against mammograms from 344 US women it…

  • Predicted malignancy with a lower 0.80 AUC
  • Classified ductal carcinoma in situ, invasive carcinomas, or benign lesions with lower 0.74, 0.83, and 0.72 AUCs 
  • Correctly interpreted 96.8% of malignant mammographic examinations and 63% of invasive carcinomas (matching three radiologists)

The authors attributed the US model’s lower accuracy to its smaller training dataset, and noted that the two models’ also had worse performance when tested against data from the other country (US model w/Israel data, Israel model w/ US data) or when classifying rare lesion types. 

However, they were still bullish about this approach with enough training data, and noted the future potential to add other imaging modalities and genetic information to further enhance multimodal breast cancer assessments.

The Takeaway 

We’ve historically relied on biopsy results to classify breast lesion subtypes, and that will remain true for quite a while. However, this study shows that multimodal-trained AI can extract far more information from mammograms, while potentially reducing unnecessary biopsies and improving the accuracy of the biopsies that are performed.

Get every issue of The Imaging Wire, delivered right to your inbox.

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You might also like..

Select All

You're all set!