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 of Lung Cancer

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?

Automatic testing for medical device software

Automatic testing for medical device software

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.

Deep Learning Environment

Deep Learning Environment

It seems that in the area of deep learning, sometimes the algorithms and math side of things are easier to understand and practice then the engineering and IT counterparts. Here at Body Vision Medical we are applying deep learning to solve computer vision problems like segmentation and localization on large data sets of medical images. While doing so we have gained experience with several setups which we will share.

LungVision Meets Unmet Needs in Lung Cancer Diagnosis

When radiologic imaging reveals a spot on the lung that physicians suspect may be lung cancer, a tissue biopsy is required to obtain a definitive diagnosis. Unlike lesions located in areas such as the stomach or colon, a lesion in the periphery of the lungs does not always have a clear, known or even visible pathway. A physician must advance a bronchoscope through the trachea into the lungs, where a complex network of airways branching into smaller airways presents very difficult challenges. Body Vision Medical has developed the Lung Vision solution which provides solutions to these specific challenges.