We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

MedImaging

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

CADx System Combines AI with Low-Cost MRI Scans to Speed up Prostate Cancer Detection

By MedImaging International staff writers
Posted on 29 Mar 2023
Print article
Image: New AI tool can safely delay, as well as inexpensively and accurately monitor prostate cancer treatment (Photo courtesy of Bot Image)
Image: New AI tool can safely delay, as well as inexpensively and accurately monitor prostate cancer treatment (Photo courtesy of Bot Image)

The current protocol for treating prostate cancer involves a number of uncomfortable and unreliable procedures. One example is the PSA test, which measures the level of prostate-specific antigen (PSA) in the blood and can sometimes indicate the presence of prostate cancer. However, this test is not conclusive and often leads to additional testing such as MRI to identify any abnormalities in the prostate. The development of new blood, urine or tissue tests for prostate cancer could be very promising but such tests do not reveal the location or extent of the cancer, which is something that imaging with artificial intelligence (AI) can do.

Similarly, digital rectal exams (DREs) have been found to be just slightly over 50% accurate due to the significant number of prostate cancers located in the anterior aspect of the gland, which is far from the rectum and cannot be felt. In addition, while biopsies can confirm the presence of cancer, their random or targeted sampling often miss cancerous lesions. Biopsies are also costly, carry a risk of infection, and can lead to false positives. Therefore, biopsies are not an effective screening method for prostate cancer but can confirm a diagnosis if used in conjunction with imaging guidance. Now, a powerful computer-aided diagnosis (CADx) software device is poised to change the standard of care for prostate cancer screening, detection and diagnosis by avoiding the expensive pitfalls of current prostate cancer pathways.

The ProstatID AI software from Bot Image, Inc. (Omaha, NE, USA) is not only intended for cancer detection and diagnosis but also for prostate cancer screening using MRI and a non-invasive/non-contrast "short-form" of MRI sequences known as bi-parametric MRI (bpMRI). bpMRI eliminates the need for expensive, time-consuming contrast agents that can damage the kidneys, thereby facilitating a low cost and easily accessible MRI. Bot Image's Prostate AI has enormous implications for men's health and healthcare cost savings, as it is a highly accurate tool for active surveillance. This means that periodic low-cost MRI scans supplemented with the AI interpretation of ProstatID can be conducted, resulting in significant savings.

In clinical trials conducted by Bot Image, the algorithm performed with 93.6% accuracy when used on its own (with area under the sensitivity-specificity curve). Additionally, physician performance was considerably enhanced. In comparison, no other screening method comes close to matching ProstatID's level of sensitivity, specificity, and ability to locate and determine the extent of cancer. ProstatID has been developed using thousands of proprietary MR image sets, radiologist interpretations, segmented prostate gland image sets, pathology laboratory results, correlation data, and initial AI interpretations to aid in the early diagnosis of prostate cancer. Bot Image has received FDA-clearance for its ProstatID AI software for cancer detection and diagnosis, as well as for prostate cancer screening using MRI and bpMRI.

Related Links:
Bot Image, Inc.

Gold Member
Solid State Kv/Dose Multi-Sensor
AGMS-DM+
Brachytherapy Planning System
Oncentra Brachy
Silver Member
Mobile X-Ray Barrier
Lead Acrylic Mobile X-Ray Barriers
New
Pre-Op Planning Solution
Sectra 3D Trauma

Print article

Channels

Ultrasound

view channel
Image: The powerful machine learning algorithm can “interpret” echocardiogram images and assess key findings (Photo courtesy of 123RF)

Largest Model Trained On Echocardiography Images Assesses Heart Structure and Function

Foundation models represent an exciting frontier in generative artificial intelligence (AI), yet many lack the specialized medical data needed to make them applicable in healthcare settings.... Read more

Nuclear Medicine

view channel
Image: The multi-spectral optoacoustic tomography (MSOT) machine generates images of biological tissues (Photo courtesy of University of Missouri)

New Imaging Technique Monitors Inflammation Disorders without Radiation Exposure

Imaging inflammation using traditional radiological techniques presents significant challenges, including radiation exposure, poor image quality, high costs, and invasive procedures. Now, new contrast... 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