The radiographic assessment of knee alignment and leg length discrepancy is producing an ever increasing workload on radiologists and orthopedic surgeons, that, in time, can negatively affect the quality of diagnosis. LAMA aims to support physicians in assessment of knee alignment and leg length discrepancy, particularly for preparing surgical planning and post-operative assessment on the non-surgically treated leg. LAMA Software is intended to be used on adult humans presenting with suspected deformities of the lower extremities among them functional limitations, bio-mechanical and cosmetic indications. LAMA can automatically identify relevant anatomical landmarks at the hip, knee and ankle and output angles and measurements which would normally require manual annotation by physicians. LAMA was trained on data from 3 large studies and two research centers : OAI, MOST, CHECK, and two Austrian research centers and with over 100.000 manual training annotations.

Value Proposition

Frontal plane deformities in the lower extremity are common and may lead to late degenerative changes in the hip, knee and ankle due to the inability of these joints to compensate for deformation. The mechanical effects of load distribution make it biologically and mechanically plausible that malalignment may influence the incidence and progression of different diseases. Several methods of measuring the lower extremities have been described (analog, semi-automated on-screen and digital), each of which is prone to both intra-observer and inter-observer variability and can be a tedious and time consuming task to complete. Automated AI-based measurements of the lower extremities can provide accurate results through a reproducible measuring technique.

Narrative

LAMA receives radiographs from a PACS, analyzes the images and stores the analysis results in the PACS. As soon as LAMA receives the image, the analysis and the generation of reports are fully automated and entail no user interaction besides the user viewing the reports. The user can send images to LAMA via standardized DICOM commands or the file interface and receive reports over the same interface. In this sense, the user does not “operate” the device but simply reviews the reports and can accept or reject them. The LAMA software does not provide a graphical user interface that uses the DICOM-viewers of existing workflows by attaching reports to the original study. All relevant images can be pre-analyzed by LAMA automatically by appropriate filter rules in the PACS. With this the original workflow is seamlessly augmented by LAMA.

Intended Use

IB Lab LAMA is a radiological fully-automated image processing software device of either computed (CR) or directly digital (DX) images intended to aid medical professionals in the measurement of leg geometry. IB Lab LAMA aids in the detection of knee alignment deformities by providing the following measurements: mechanical lateral proximal femur angle (mLPFA), mechanical lateral distal femur angle (mLDFA), mechanical medial proximal tibia angle (mMPTA), mechanical lateral distal tibia angle (mLDTA), mechanical axis deviation (MAD), hip-knee angle (HKA) on standing AP radiographs of the leg. IB Lab LAMA aids in the detection of leg length discrepancy by providing the following measurements: femur, tibia and full leg length as well as the difference between right and left legs on bilateral images. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained medical professionals including, but not limited to, orthopedics and radiologists.

Limitations

It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained professionals including, but not limited to, radiologists, orthopedics, physicians and medical technicians.
The latest CE version is not intended for use on legs where knee, hip or ankle implant is present. The software includes an implant detector which will exclude legs from analysis when an implant is found. For producing accurate length measurements, the latest CE version includes a number of ways to set the magnification factor. For sites where a calibration ball is used, the software can be pre-configured with the calibration ball size. A calibration ball detector will find the calibration ball in the image and set the magnification factor based on the results. Otherwise, the software can be pre-configured with a fixed magnification factor. If no magnification factor is provided through either of these methods, the distance measurements will be reported based on the pixel size of the image, and a warning will be presented on the report.

Model performance metrics

LAMA was compared with expert annotations in a reader study on 110 images designed to assess the measurement agreement of the hip-knee-ankle angle (HKA), joint line convergence angle (JLCA), mechanical axis deviation (MAD), as well as leg and bone length measurements and mechanical axis angle measurements. LAMA measures HKA, JLCA and MAD to within 0.3°, 0.8° and 1.1 mm, respectively, as measured by mean absolute deviation to the mean of the expert readers. Leg length discrepancy of IB Lab LAMA is accurate to 0.2 cm compared with expert readers

ImageBiopsy Lab

ImageBiopsy Lab

Musculoskeletal (MSK) diagnoses are often subjective and inconsistent. This and the general need to bring MSK-measurements to the digital age finally drove us to change the status quo. Our software offers simplification and standardization and full integration to your existing system. Furthermore, we provide quantitative disease parameters to support treatment decisions of medical experts. ImageBiopsy Lab offers AI-driven solutions for anatomical regions such as the knee, the hand, and hip while constantly working on additional MSK solutions. 

PHILIP

Philip Meier

Email