Although most heart murmurs aren’t serious, abnormal heart murmurs can cause shortness of breath, chronic coughing, chest pains, an enlarged liver, and sudden weight gain. They can be signs of a congenital defect like a hole in the heart, a cardiac shunt, or a heart valve problem that has been present since birth. They can be caused by fever, exercise, pregnancy, low red blood cell count, an overactive thyroid gland, or even during times of rapid growth in children, and they shouldn’t be taken lightly.

Eko, a cardiopulmonary digital health company, has recognized the seriousness of the disease and recently announced its heart murmur-detecting AI algorithm is performing comparably to that of expert cardiologists in detecting heart murmurs. The FDA-cleared AI algorithm recorded a sensitivity of 90.0% and specificity of 91.4% for detecting murmurs, when difficult to hear grade 1 murmurs were excluded.

“We designed the study to see whether the algorithm could not only identify murmurs in an experimental setting, but whether it could help clinicians actually make difficult diagnostic decisions at the bedside. And that’s what the results show,” said Dr. John Chorba, the study’s lead author.

The competition for AI algorithm solutions is heating up, with products like eMurmur ID, a smartphone app that utilizes a third-party digital stethoscope and a machine learning algorithm to automate the detection of heart murmurs also recently receiving FDA approval. The platform is designed to fit into a healthcare provider’s current workflow and the heart murmur recordings can be securely shared with other experts for consultation.

By detecting heart disease quickly with AI, patients can get immediate treatment, which lowers costs, improves outcomes, and reduces unnecessary testing. AI has the potential to disrupt the status-quo of heart murmur screening, as well as substantially improve patient care, while significantly reducing costs to healthcare systems around the world.

Radiology, in particular, is seeing impressive results with AI, which isn’t surprising as machine learning’s ability to discover hard-to-find patterns in massive amounts of data, even image data, is a natural fit for the discipline that uses medical imaging to diagnose and treat diseases within the body.

Today, half of all published research studies in the top radiology journals are AI-related. AI, including machine learning and deep learning, is being prominently endorsed at radiology conferences worldwide, including at this year’s prestigious European Congress of Radiology. 

No longer just seen as a futuristic technology, AI is becoming an integral part of daily life in radiology departments worldwide. Understandably so as AI can optimize radiologists’ workflows, facilitate quantitative radiology, and assist in discovering genomic markers.

How is AI helping Radiologists?

The technology helps radiologists increase efficiency as well as lower a patient’s overall healthcare costs because diagnoses can be delivered faster and more accurately than before.

One company that is developing groundbreaking AI technology in the radiological field is RADLogics, the healthcare software company that develops AI-Powered solutions to support image analysis that improves radiologists’ accuracy and productivity, while also improving patient outcomes.

Approved AI Applications for Radiology

On July 8, 2021, the company announced FDA 510(k) clearance for its novel AI-Powered chest X-ray pneumothorax application. The solution gives healthcare providers, hospital networks, and clinicians access to AI software that is trained via pattern recognition to flag chest X-rays suspected of pneumothorax or collapsed lungs. 

Operating in parallel with existing radiological workflows, the chest X-ray solution analyzes images for features suggestive of pneumothorax, then makes case-level output available to a PACS workstation for worklist prioritization or triage. 

The AI-Powered solution integrates into a comprehensive, seamless, and secure workflow to augment acute care teams with deep clinical insight and actionable intelligence in minutes.

In accordance with FDA guidance for imaging systems and software to tackle the COVID-19 public health crisis, RADLogics has made its FDA cleared X-ray and CT solutions available to hospitals and healthcare systems throughout the U.S.  The application is available at the Nuance AI Marketplace for Diagnostic Imaging

Navigation is an important ability of an autonomous system. The need to move around without the use of external inputs and a map has led to research in 3D localization. 3D localization is necessary for the success of any autonomous system. For example, if a robot’s purpose is to clean the trash in a room, it will not be able to take any action just with captured video of the room. The robot will need to know factors like the location of the trashcan and the layout of the room to locate objects.

For this, point clouds are used for tracking objects in 3D space. A point cloud is a dataset that represents an item or a place. These points indicate the geometric coordinates of a single point on an underlying surface on the X, Y, and Z axes. In more simple terms, point clouds create points that represent a 3D shape, object, or area. Point clouds can be generated manually by taking pictures from different perspectives or automatically by taking images with a camera attached to a moving object.

Many algorithms work on these point clouds and help self-navigation systems such as robots find their way accurately in unfamiliar environments. This article will discuss what point clouds are and answer some questions about how they are helpful in autonomous systems.

What’s the Point of Point Clouds?

Autonomous systems collect data from different sensors to perform their desired action. In most cases, robots cannot perform actions with just the raw data captured from various sensors. As with the trash cleaning robot example, the robot wouldn’t be able to extract information about the room from only a raw video file. Point clouds provide more information about the area around the robotic or autonomous object, enabling them to perform the task at hand.

A potential use of this is with self-driving cars. Self-driving cars must be aware of their surroundings to accelerate, decelerate, stop, turn 5 degrees left, etc. An automobile must identify other cars, trucks, pedestrians, barriers, traffic signs, signals, lanes, and more to be aware of its surroundings.

Point Clouds and Self-Driving Vehicles

RediMinds tested out the use of point clouds to detect the surroundings of an autonomous vehicle. LIDAR data captured from the self-driving car was used to determine the location, approximate size, and orientation of the surrounding vehicles in 3D space. Lidar is a technique for determining ranges that involves aiming a laser at an object and timing the time it takes for the reflected light to return to the receiver.

Using the LIDAR data in conjunction with the cylindrically stitched visual frames from six other cameras, the model could detect other cars in 360 degrees surrounding the vehicle. Although LIDAR data was used for this experiment, this technique could be expanded to just use cameras for 3-D object recognition, tracking, and monitoring with other robotic systems.

Why Not Use 2D Localization?

Humans view the world in three dimensions. To compete with or outperform us, autonomous objects need to obtain information in the way that we do or better. Like 3D localization, 2D detection identifies a list of surrounding objects and their location in the images. However, 2D localization lacks crucial information, like how far the objects are relative to the self-driving car.

3D object detection provides answers to these questions, as it has much richer information about its surroundings. When this detected information is supplied to the decision-maker and other processed data such as traffic signs and lane detection, the trajectory of nearby objects, and more, the decision-maker acts according to that information.

Why Does This Matter?

Self-driving cars require access to a large amount of high-quality data in many categories to build a trustworthy model for predicting the surroundings and reducing accidents. If the overall goal of a self-driving vehicle is to create safer roads, then self-driving cars need to detect their surroundings similarly or better than humans do. Autonomous vehicles need to accurately identify thousands of street objects such as road signs, borders, lanes, traffic lights, automobiles, trucks, pedestrians, and corresponding travel routes.

Outside of self-driving cars, other robotic objects, like automated robots in manufacturing warehouses, need to be conscious of the world around them to improve safety conditions. This is made possible with 3D localization and point cloud. This method may also be extended to 3D tracking and monitoring. For example, monitoring consumers at a business with automated billing or tracking items in an automated process.

To learn more, check out this case study.