JAQ software download

Hand Joint Space Analysis and Quantification


Joint Analysis and Quantification (JAQ) is a software application which is used to automatically measure the joint space width (JSW) in the finger joints in hand radiographs. The JSW measurement closely reflects semi-quantitative scoring of joint space narrowing, which is often used to assess osteoarthritis. The method and its validation is described in detail in [1] (Van ‘t Klooster et al. 2008). And more extensive validation was performed using a phantom and cadaver joints in [2] (Huétink et al. 2012). The software application is currently being used in different clinical studies, see [3] (Kwok et al. 2011) and [4] (Biermasz et al. 2012).

The JAQ software application is now publicly available and can be downloaded from this page. For further information and details about the method, validation and application, please refer to the following articles:

  1. Van 't Klooster R, Hendriks EA, Watt I, Kloppenburg M, Reiber JH, Stoel BC. Automatic quantification of osteoarthritis in hand radiographs: validation of a new method to measure joint space width. Osteoarthritis Cartilage. 2008;16(1):18-25. Epub 2007 Jul 16. (Van ‘t Klooster et al. 2008)
  2. Huétink K, van 't Klooster R, Kaptein BL, Watt I, Kloppenburg M, Nelissen RG, Reiber JH, Stoel BC. Automatic radiographic quantification of hand osteoarthritis; accuracy and sensitivity to change in joint space width in a phantom and cadaver study. Skeletal Radiol. 2012;41(1):41-9. (Huetink et al. 2012)
  3. Kwok WY, Bijsterbosch J, Malm SH, Biermasz NR, Huetink K, Nelissen RG, Meulenbelt I, Huizinga TW, van 't Klooster R, Stoel BC, Kloppenburg M. Validity of joint space width measurements in hand osteoarthritis. Osteoarthritis Cartilage. 2011;19(11):1349-55. (Kwok et al. 2011)
  4. Biermasz NR, van 't Klooster R, Wassenaar MJ, Malm SH, Claessen KM, Nelissen RG, Roelfsema F, Pereira AM, Kroon HM, Stoel BC, Romijn JA, Kloppenburg M. Automated image analysis of hand radiographs reveals widened joint spaces in patients with long-term control of acromegaly: relation to disease activity and symptoms. Eur J Endocrinol. 2012;166(3):407-13. (Biermasz et al. 2012)

Terms and conditions

The JAQ software application is free for download under the following conditions:

  • The software may be used for research purposes only
  • The software is for personal use only, and may not be redistributed
  • In no event shall the LUMC be liable for any direct or indirect damage, arising in any way out of the use of this software.
  • Any publication arising from the use of JAQ software should cite reference [1] (Van ‘t Klooster et al. 2008) from the list above.

To obtain the papers that are referenced, please send a request to the contacts available below.


The online form has to be filled and subsequently the download page will be loaded. The e-mail address will be used only for verification purposes.

The downloaded JAQ software is written in Matlab (version 2011A or higher, although older version might work, see www.mathworks.com) and requires the DIPimage toolbox (version 2.5 or later, see www.diplib.org).


Extract the zip archive and start JAQ by running jaq.m in Matlab. A graphical user interface (GUI) will appear on the screen. A wizard will guide the user through the analysis process which consists of the following steps.

  1. Load and review the hand radiograph (DICOM, JPEG or TIFF format).
  2. Pre-processing of the image data, separation of the two hands.
  3. Calculation of the measurement intervals.
  4. Detection of the joint locations.
  5. Joint space width measurement.

The "Instructions" tab (top left in the GUI) will show instructions for the current step of the wizard. On the bottom left you can use the "Previous" and "Next" buttons to go back and forward in the wizard. In each step the user can make corrections if needed.

Finally, the results are saved and exported into an Excel worksheet. The results are saved in the same directory as the image.

The software application assumes there are two hands present on the radiograph, in case only one hand is present, just ignore the measurements of the second hand.

Contact information

B. C. Stoel – b.c.stoel@lumc.nl