Acute and chronic wounds have varying etiologies and are an economic burden to healthcare systems around the world. The advanced wound care market is expected to exceed $22 billion by 2024. Wound care professionals rely heavily on images and image documentation for proper diagnosis and treatment. Unfortunately lack of expertise can lead to improper diagnosis of wound etiology and inaccurate wound management and documentation. Fully automatic segmentation of wound areas in natural images is an important part of the diagnosis and care protocol since it is crucial to measure the area of the wound and provide quantitative parameters in the treatment. Various deep learning models have gained success in image analysis including semantic segmentation. This manuscript proposes a novel convolutional framework based on MobileNetV2 and connected component labelling to segment wound regions from natural images. The advantage of this model is its lightweight and less compute-intensive architecture. The performance is not compromised and is comparable to deeper neural networks. We build an annotated wound image dataset consisting of 1109 foot ulcer images from 889 patients to train and test the deep learning models. We demonstrate the effectiveness and mobility of our method by conducting comprehensive experiments and analyses on various segmentation neural networks. The full implementation is available at https://github.com/uwm-bigdata/wound-segmentation.

Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound and provide quantitative measurement for the treatment. Unfortunately, this process is very time-consuming and requires a high level of expertise, hence the need for automatic wound measurement methods. Recently, automatic wound segmentation methods based on deep learning have shown promising performance; yet, they heavily rely on large training datasets. A few wound image datasets were published including the Diabetic Foot Ulcer Challenge dataset, the Medetec wound dataset, and WoundDB. Existing public wound image datasets suffer from small size and a lack of annotation. There is a need to build a fully annotated dataset to benchmark wound segmentation methods. To address these issues, we propose the Foot Ulcer Segmentation Challenge (FUSeg), organized in conjunction with the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). It contains 1210 pixel-wise annotated foot ulcer images collected over 2 years from 889 patients. The submitted algorithms are reviewed in this paper and the dataset can be accessed through the Foot Ulcer Segmentation Challenge website.

Background: Photobiomodulation (PBM) by far-red (FR) to near-infrared (NIR) light has been demonstrated to accelerate diabetic wound healing in preclinical and clinical studies. Mitochondrial dysfunction and oxidative stress play key roles in impaired diabetic wound healing, and the effect of PBM on the metabolic state of diabetic wounds remains to be elucidated. Methods: In this study, a custom-designed in vivo fluorescence imaging technique was used to quantitatively assess the effect of FR-PBM on the mitochondrial bioenergetics of diabetic wounds. The intrinsic fluorescence of two mitochondrial co-enzymes, nicotinamide adenine dinucleotide (NADH) and oxidized flavin adenine dinucleotide (FAD), was monitored to quantify the redox ratio (RR) (NADH/FAD) of wounds over time. Results: Using an excisional model of wound healing, we demonstrated that 670 nm (FR) PBM improved mitochondrial bioenergetics and stimulated the rate of wound healing in diabetic db/db mice. Wound closure and the RR of diabetic wounds in response to 670 nm PBM (4.5 J/cm², 60 mW/cm² for 90 s per day, 5 days/week) were compared to the sham-treated group. At day 9 of post-wounding, we observed a 43% decrease in the wound area and a 75% increase in RR in FR-treated diabetic mice compared to sham-treated diabetic mice. Conclusions: We conclude that the increase in mitochondrial RR and the related decrease in oxidative stress may be an important factor in FR-PBM mediated acceleration of wound healing in diabetic mice.

Background: Current assessment standards in chronic limb-threatening ischemia (CLTI) focus on macrovascular function while neglecting the microcirculation. Multispectral near-infrared spectroscopy (NIRS) provides hemodynamic characteristics of the microcirculation (i.e., capillaries) and may be a powerful tool for monitoring CLTI and preventing extremity loss. The aims of this study were to (1) investigate the effects of lower limb revascularization on the microcirculation and (2) determine if macrovascular and microvascular assessments correlate. Methods: An observational, retrospective cohort study of 38 endovascular interventions in 30 CLTI subjects was analyzed pre- and post-intervention for arterial Doppler acceleration times (AcT; macrovascular) and NIRS metrics (microvascular). Pre-intervention ankle-brachial index (ABI) was also analyzed. Results: AcT significantly decreased (p = 0.009) while oxyhemoglobin (HbO) significantly increased (p < 0.04) after endovascular intervention, indicating treatment efficacy. However, macrovascular measurements (ABI, AcT) and NIRS metrics of oxygenation and perfusion did not correlate (p > 0.06, r² < 0.15, n = 23) indicating that macro- and microvascular assessment are not congruent. Conclusion: These findings suggest that macrovascular and microvascular assessments can determine interventional efficacy in their corresponding vasculature. Their lack of correlation, however, suggests the need for simultaneous assessment as independent use may cause diagnostic information to be missed.