MedImaging

Download Mobile App
Recent News Radiography MRI Ultrasound Nuclear Medicine General/Advanced Imaging Imaging IT Industry News

AI Solution Provides Radiologists with 'Second Pair' Of Eyes to Detect Breast Cancers

By MedImaging International staff writers
Posted on 22 Feb 2024
Print article
Image: AI markers highlight suspicious calcifications and soft tissue lesions together with an objective Region Score (Photo courtesy of ScreenPoint Medical)
Image: AI markers highlight suspicious calcifications and soft tissue lesions together with an objective Region Score (Photo courtesy of ScreenPoint Medical)

Mammography, a key tool in breast cancer screening, has proven effective in improving patient outcomes and reducing mortality by identifying breast cancers at an earlier, more manageable stage. Despite its effectiveness, it's estimated that 20-30% of interval cancers, which should have been detected during the previous mammogram, are missed. Additionally, many suspicious findings are ultimately found to be benign. To enhance sensitivity in detecting disease, European guidelines recommend that two radiologists independently review each screening mammogram. However, there's a notable shortage of breast radiologists globally, and training a radiologist to proficiently interpret mammograms can take more than a decade. In response to these challenges, Artificial Intelligence (AI) has been suggested as a potential automated second reviewer for mammograms. This could not only reduce the radiologists' workload but also enhance screening accuracy. AI has shown promising results in retrospective studies, where it was used to decide whether mammogram examinations should be read by one or two radiologists, and in providing radiologists with computer-aided detection (CAD) markings to highlight suspicious areas, thereby reducing the incidence of false negatives. Now, an advanced AI solution provides radiologists with a 'second pair' of eyes to help detect cancers earlier and reduce recall rates.

ScreenPoint Medical’s (Nijmegen, Netherlands) Transpara breast AI is designed to assist radiologists in the early detection of breast cancers and enhance the efficiency of breast screening programs. Utilized by numerous leading institutions across over 30 countries, Transpara is integrated into the radiologists' workflow. Studies have shown that Transpara can identify up to 45% of interval cancers earlier, while also reducing the workload and optimizing workflow processes. Transpara demonstrates consistent performance across various countries, patient ages, breast densities, and ethnic backgrounds. To date, Transpara breast AI has analyzed over five million mammograms, including more than one million Tomosynthesis (3D) exams, supporting radiologists in mammography examinations. The system has received FDA clearance and European regulatory approval (CE Mark) for use with both 2D and 3D mammography from multiple manufacturers.

Transpara continues to deliver proven clinical and workflow benefits in mammography screening in global practice and clinical research. A first-of-its-kind randomized controlled trial, the MASAI-trial, investigated cancer detection rates and the types of cancers detected using AI-supported screening. This trial found notable improvements in cancer detection when AI support was used, compared to traditional double reading methods without AI. Another prospective clinical trial explored the use of AI in safely reducing the radiologists' workload. It focused on using AI to exclude low-risk cases from human review and applying double reading to the remaining cases.

"We are glad that users and researchers continue to see value from Transpara in improving the mammography screening process,” said Mark Koeniguer, ScreenPoint Medical CEO. “It's important to note that these studies reflect global consistency in Transpara's performance. In fact, we now have retrospective, prospective and randomized controlled trials all showing that Transpara provides radiologists with the ability to effectively detect cancer early while keeping recall rates consistent. Women should not have to compromise."

Gold Member
Electrode Solution and Skin Prep
Signaspray
Gold Member
Ultrasound System
FUTUS LE
Silver Member
Solid State Kv/Dose Multi-Sensor
AGMS-DM+
Ferromagnetic Hand-Held Detector
FerrAlert Target Scanner

Print article
Radcal

Channels

MRI

view channel
Image: PET/MRI can accurately classify prostate cancer patients (Photo courtesy of 123RF)

PET/MRI Improves Diagnostic Accuracy for Prostate Cancer Patients

The Prostate Imaging Reporting and Data System (PI-RADS) is a five-point scale to assess potential prostate cancer in MR images. PI-RADS category 3 which offers an unclear suggestion of clinically significant... Read more

Nuclear Medicine

view channel
Image: The new SPECT/CT technique demonstrated impressive biomarker identification (Journal of Nuclear Medicine: doi.org/10.2967/jnumed.123.267189)

New SPECT/CT Technique Could Change Imaging Practices and Increase Patient Access

The development of lead-212 (212Pb)-PSMA–based targeted alpha therapy (TAT) is garnering significant interest in treating patients with metastatic castration-resistant prostate cancer. The imaging of 212Pb,... Read more

General/Advanced Imaging

view channel
Image: The Tyche machine-learning model could help capture crucial information. (Photo courtesy of 123RF)

New AI Method Captures Uncertainty in Medical Images

In the field of biomedicine, segmentation is the process of annotating pixels from an important structure in medical images, such as organs or cells. Artificial Intelligence (AI) models are utilized to... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more