Dynamic infrared imaging for skin cancer screening

Abstract

Dynamic thermal imaging (DTI) with infrared cameras is a non-invasive technique with the ability to detect the most common types of skin cancer. We discuss and propose a standardized analysis method for DTI of actual patient data, which achieves high levels of sensitivity and specificity by judiciously selecting pixels with the same initial temperature. This process compensates the intrinsic limitations of the cooling unit and is the key enabling tool in the DTI data analysis. We have extensively tested the methodology on human subjects using thermal infrared image sequences from a pilot study conducted jointly with the University of New Mexico Dermatology Clinic in Albuquerque, New Mexico (ClinicalTrials ID number NCT02154451). All individuals were adult subjects who were scheduled for biopsy or adult volunteers with clinically diagnosed benign condition. The sample size was 102 subjects for the present study. Statistically significant results were obtained that allowed us to distinguish between benign and malignant skin conditions. The sensitivity and specificity was 95% (with a 95% confidence interval of [87.8% 100.0%]) and 83% (with a 95% confidence interval of [73.4% 92.5%]), respectively, and with an area under the curve of 95%. Our results lead us to conclude that the DTI approach in conjunction with the judicious selection of pixels has the potential to provide a fast, accurate, non-contact, and non-invasive way to screen for common types of skin cancer. As such, it has the potential to significantly reduce the number of biopsies performed on suspicious lesions.

Detection theory for accurate and non-invasive skin cancer diagnosis using dynamic thermal imaging

“…The term evolution is emphasized to highlight the importance of the temporal order of the warming-up data obtained from the image sequence. This is why the performance is far better than that obtained when the Euclidean norm of the thermal-image sequence is used because the latter, unlike the proposed method, does not depend on the ordering of the images in the sequence [30].…”

“…As it was aforementioned, the suspicious lesion must be probed several times before such an accuracy is achieved, which makes the acquisition time prohibitively high for clinical applications. The only approach found in the literature that utilized DTI with reported sensitivity and specificity is our previous work [30]. In that work, we performed classification by a distance-based classifier.…”

“…In that work, we performed classification by a distance-based classifier. To do so, [4,5] 0.56 -0.65 0.11 -0.53 Melafind [19,20] >0.95 >0.90 Vivosight [21] 0.79 -0.94 0.04 -0.15 DTI (Euclidean-norm-based) [30] >0.95 <0.17 DTI (optimal decision theory) >0.99 <0.01…”

“…DTI has already demonstrated to have high potential for the skin cancer diagnosis [22,23] and it is a technique in which a thermal stimulus is applied to the suspected lesion and the thermal recovery is captured as function of time using an infrared (IR) camera [24]. Even though several groups have reported that the thermal recovery curves (TRCs) of a skin-cancer lesion and the surrounding healthy skin is different [25][26][27][28][29][30], these methods only partially extracted the information present in the temporal evolution of the recovery process. More specifically, the existing DTI techniques have neglected the temporal statistical features inherent in the thermal recovery process.…”

Infrared imaging: a potential powerful tool for neuroimaging and neurodiagnostics

“…IR imaging in medicine provides a noninvasive and nonradiating analysis tool for analyzing physiological functions related to the control of skin temperature. 1 This rapidly developing technology is used to detect and locate thermal abnormalities characterized by an increase or decrease in temperature found at the skin surface. The technique involves the detection of IR radiation that can be directly correlated with the temperature distribution of a defined body region.…”