Multimodal AI Virtual Breast Biopsies

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.

iSono Health’s Wearable Breast Ultrasound

iSono Health announced the FDA clearance of its ATUSA automated wearable 3D breast ultrasound system, a first-of-its-kind device that taps into some of the biggest trends in imaging.

The wearable ATUSA system automatically captures the entire breast volume, producing standardized/repeatable breast ultrasound exams in two minutes without requiring a trained operator. The scanner combines with iSono’s ATUSA Software Suite to support real-time 2D visualization, advanced 3D visualization and localization, and AI integration (including iSono’s forthcoming AI tools). That positions the ATUSA for a range of interesting use cases:

  • Enhancing routine exams in primary care and women’s health clinics
  • Expanding breast imaging access in developing countries
  • Supporting longitudinal monitoring for higher-risk women
  • Allowing remote breast cancer monitoring

iSono might have to overcome some pretty big biases regarding how and where providers believe breast exams are supposed to take place. However, the ATUSA’s intended use cases and value propositions have already been gaining momentum across imaging.

  • The rapid expansion of handheld POCUS systems and AI guidance solutions has made ultrasound an everyday tool for far more clinicians than just a few years ago.
  • Wearable imaging continues to be an innovation hotspot, including a range of interesting projects that are developing imaging helmets, patches, and even a few other wearable breast ultrasound systems.
  • There’s a growing focus on addressing the developing world’s imaging gap with portable imaging systems.
  • We’re seeing greater momentum towards technology-enabled enhancements to routine breast exams, including Siemens Healthineers’ recent move to distribute UE LifeSciences’ iBreastExam device (uses vibrations, not imaging).
  • At-home imaging is becoming a far more realistic idea, with commercial initiatives from companies like Butterfly and Pulsenmore in place, and earlier-stage efforts from other breast ultrasound startups. 

The Takeaway

iSono Health has a long way to go before it earns an established role in breast cancer pathways. However, the ATUSA’s use cases and value proposition are well aligned with some of imaging’s biggest trends, and there’s still plenty of demand to improve breast imaging access and efficiency across the world.

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.

Another important feature of the best 10 dollar minimum deposit online casino is casino licensing. The best online casinos are regulated by regulators and must meet set standards in order to keep their clients happy. Regulatory bodies such as the UK Gambling Commission, the Malta Gaming Authority, and the Kahnawake Gaming Commission oversee casinos and ensure that they adhere to their rules. Licensed casinos will not accept players under the legal age limit, and they will have to audit their games to ensure fairness and safety.

-- The Imaging Wire team