At Body Vision, we invest a superior effort in human resources and team-building activities. Our culture inspires challenges and achievements; however, the ways to achieve our goals and our communication habits are equally important.
The ability to detect and diagnose lung cancer at an early stage leads to a cure in the majority of patients. Companies, including Body Vision Medical, are taking great strides towards making early stage, minimally invasive lung cancer diagnostics accessible to more hospitals, physicians, and ultimately, patients throughout the world.
Local minimally invasive therapies in the lung are the only option for non-surgical patients. Moreover, these therapies provide a legitimate alternative for the larger patient population due to reduced associated risks, lower costs and timely availability in procedure room. Ongoing studies suggest that if applied at the accurate location of the lesion, some local therapies may increase the patient survival rate. However, until today, it has been challenging to apply local therapies to small pulmonary nodules in a standard bronchoscopy suite since the nodules are invisible through conventional imaging modalities and are very tricky to reach. The LungVision™ platform is opening a new era in local therapies since it makes any nodule visible and accessible in real time, while tracking tissue movement during breathing and instrument placement.
According to the American Cancer Society, three out of four American families will have a family member diagnosed with some form of cancer. That’s a lot of people who need love and support from the people closest to them, lots of opportunities to make a positive impact for people who find themselves fighting the biggest challenge of their lives.
Shape matching, stereo reconstruction, motion estimation, image restoration, and object segmentation are all problems in the field of Computer Vision that are often solved using global optimization methods. In this post, we will present typical nonlinear optimization challenges and suggest a graceful solution.
Lung cancer is the leading cause of cancer-related deaths in the world.
Identification of lung cancer at an early stage of the disease when the lesion is small and localized, allows a proper treatment and dramatically increases the chance of survival. The proper treatment relies on a definitive diagnosis for the type of lung cancer. There are two major challenges that the pulmonologist is facing with this regard. First of all, there is a need for an accurate localization and navigation to the suspicious lesion. Furthermore there is a need to obtain an adequate tissue sample for pathology analysis. The later is discussed in this blog.
Diagnostic yield is one of the main factors in evaluating the clinical effectiveness of an interventional medical technique, such as diagnostic bronchoscopy, intended for biopsy of suspicious lesions.
The purpose of the diagnostic yield value is to determine the probability that the selected medical technique will provide the information needed to establish a definitive diagnosis.
As most lung cancers are diagnosed at an advanced stage with very low survival rates, it is very important to achieve a definitive diagnosis at an early stage in order to increase the chances of a successful treatment. (1)
Two related questions are asked here: What would be considered a definitive diagnosis? And how is diagnostic yield calculated?
As everyone knows, the release process for medical device software is stressful and time-consuming. Medical software verification and validation (V&V) requires verification that software meets predefined specifications and validation that it fulfills the intended purpose in the view of the customer. Practically speaking, this is achieved by performing functional and nonfunctional testing. Regulatory compliance and documentation requirements demand a huge manual effort from development teams, including multiple iterations of development and testing. All of this leads to long release cycles, overspending of resources for software developers, software testing, project management, and technical writing, as well as frequent delays in release timelines.
It seems that in the area of deep learning, sometimes the algorithms and math side of things are easier to understand and practice