Early identification of diabetic foot complications and their precursors is essential in preventing their devastating consequences, such as foot infection and amputation. Frequent, automatic risk assessment by an intelligent telemedicine system might be feasible and cost effective. Infrared thermography is a promising modality for such a system. The temperature differences between corresponding areas on contralateral feet are the clinically significant parameters. This asymmetric analysis is hindered by (1) foot segmentation errors, especially when the foot temperature and the ambient temperature are comparable, and by (2) different shapes and sizes between contralateral feet due to deformities or minor amputations. To circumvent the first problem, we used a color image and a thermal image acquired synchronously. Foot regions, detected in the color image, were rigidly registered to the thermal image. This resulted in 97.8%±1.1% sensitivity and 98.4%±0.5% specificity over 76 high-risk diabetic patients with manual annotation as a reference. Nonrigid landmark-based registration with B-splines solved the second problem. Corresponding points in the two feet could be found regardless of the shapes and sizes of the feet. With that, the temperature difference of the left and right feet could be obtained.
KEYWORDS: Optical filters, Skin, Statistical analysis, Intelligence systems, Error analysis, Linear filtering, Principal component analysis, Feature extraction, Spectroscopy, Signal to noise ratio
Early detection of (pre-)signs of ulceration on a diabetic foot is valuable for clinical practice. Hyperspectral imaging is a promising technique for detection and classification of such (pre-)signs. However, the number of the spectral bands should be limited to avoid overfitting, which is critical for pixel classification with hyperspectral image data. The goal was to design a detector/classifier based on spectral imaging (SI) with a small number of optical bandpass filters. The performance and stability of the design were also investigated. The selection of the bandpass filters boils down to a feature selection problem. A dataset was built, containing reflectance spectra of 227 skin spots from 64 patients, measured with a spectrometer. Each skin spot was annotated manually by clinicians as “healthy” or a specific (pre-)sign of ulceration. Statistical analysis on the data set showed the number of required filters is between 3 and 7, depending on additional constraints on the filter set. The stability analysis revealed that shot noise was the most critical factor affecting the classification performance. It indicated that this impact could be avoided in future SI systems with a camera sensor whose saturation level is higher than 10 6 , or by postimage processing.
Diabetic foot ulceration is a major complication for patients with diabetes mellitus. If not adequately treated, these ulcers may lead to foot infection, and ultimately to lower extremity amputation, which imposes a major burden to society and great loss in health-related quality of life for patients. Early identification and subsequent preventive treatment have proven useful to limit the incidence of foot ulcers and lower extremity amputation. Thus, the development of new diagnosis tools has become an attractive option. The ultimate objective of our project is to develop an intelligent telemedicine monitoring system for frequent examination on patients’ feet, to timely detect pre-signs of ulceration. Inflammation in diabetic feet can be an early and predictive warning sign for ulceration, and temperature has been proven to be a vicarious marker for inflammation. Studies have indicated that infrared dermal thermography of foot soles can be one of the important parameters for assessing the risk of diabetic foot ulceration. This paper covers the feasibility study of using an infrared camera, FLIR SC305, in our setup, to acquire the spatial thermal distribution on the feet soles. With the obtained thermal images, automated detection through image analysis was performed to identify the abnormal increased/decreased temperature and assess the risk for ulceration. The thermography for feet soles of patients with diagnosed diabetic foot complications were acquired before the ordinary foot examinations. Assessment from clinicians and thermography were compared and follow-up measurements were performed to investigate the prediction. A preliminary case study will be presented, indicating that dermal thermography in our proposed setup can be a screening modality to timely detect pre-signs of ulceration.
Diabetic foot ulceration is a major complication for patients with diabetes mellitus. Approximately 15% to
25% of patients with Type I and Type II diabetes eventually develop feet ulcers. If not adequately treated,
these ulcers may lead to foot infection, and ultimately to total (or partial) lower extremity amputation, which
means a great loss in health-related quality of life. The incidence of foot ulcers may be prevented by early
identification and subsequent treatment of pre-signs of ulceration, such as callus formation, redness, fissures,
and blisters. Therefore, frequent examination of the feet is necessary, preferably on a daily basis. However,
self-examination is difficult or impossible due to consequences of the diabetes. Moreover, frequent examination
by health care professionals is costly and not feasible. The objective of our project is to develop an intelligent
telemedicine monitoring system that can be deployed at the patients' home environment for frequent examination
of patients feet, to timely detect pre-signs of ulceration. The current paper reports the preliminary results of
an implementation of a photometric stereo imaging system to detect 3D geometric abnormalities of the skin
surfaces of foot soles. Using a flexible experimental setup, the system parameters such as number and positions
of the illuminators have been selected so as to optimize the performance with respect to reconstructed surface.
The system has been applied to a dummy foot sole. Finally, the curvature on the resulting 3D topography of
the foot sole is implemented to show the feasibility of detecting the pre-signs of ulceration using photometric
stereo imaging. The obtained results indicate clinical potential of this technology for detecting the pre-signs of
ulceration on diabetic feet soles.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.