Use of hyperspectral imaging to predict healing of diabetic foot ulceration

Hyperspectral Imaging in the Healing Prognosis of Diabetes Related Foot Ulcers. A Systematic Review and Meta-Analysis

OBJECTIVE

The diagnostic capability of hyperspectral (HSI) imaging has been focused on the prognosis of wound healing in patients with peripheral artery disease and diabetic foot ulcers (DFUs). The aim of this study was to evaluate the performance characteristics of HSI to determine the pretest probability for the prognosis of DFU healing.

METHODS

A systematic search was performed on the PubMed, Medline, and Cochrane databases to identify studies evaluating HSI in predicting the prognosis of DFUs. This study was registered with PROSPERO (CRD42023495391). All selected studies were evaluated using the STROBE guidelines to assess the reporting quality for observational studies. Meta-DiSc software was used to analyze the collected data.

RESULTS

Nine publications (142 participants) were evaluated for systematic review. The meta-analysis included four publications examining the prospective diagnostic capability of HSI. Concerning the prognostic accuracy of HSI, it had a pooled sensitivity of 0.84 (0.75-0.9) and a specificity of 0.79 (0.66-0.88) for predicting DFU healing, as well as an odds ratio of 20.4, resulting in a positive likelihood ratio of 4.1 and a negative likelihood ratio of 0.2 (heterogeneity I2 = 0).

CONCLUSIONS

The meta-analysis revealed promising prognostic capability of HSI for the healing of DFU. More randomized clinical trials need to be published as our results are based on only prospective and comparative studies.

Advancing hyperspectral imaging and machine learning tools toward clinical adoption in tissue diagnostics: A comprehensive review

Hyperspectral imaging (HSI) has become an evident transformative apparatus in medical diagnostics. The review aims to appraise the present advancement and challenges in HSI for medical applications. It features a variety of medical applications namely diagnosing diabetic retinopathy, neurodegenerative diseases like Parkinson's and Alzheimer's, which illustrates its effectiveness in early diagnosis, early caries detection in periodontal disease, and dermatology by detecting skin cancer. Regardless of these advances, the challenges exist within every aspect that limits its broader clinical adoption. It has various constraints including difficulties with technology related to the complexity of the HSI system and needing specialist training, which may act as a drawback to its clinical settings. This article pertains to potential challenges expressed in medical applications and probable solutions to overcome these constraints. Successful companies that perform advanced solutions with HSI in terms of medical applications are being emphasized in this study to signal the high level of interest in medical diagnosis for systems to incorporate machine learning ML and artificial intelligence AI to foster precision diagnosis and standardized clinical workflow. This advancement signifies progressive possibilities of HSI in real-time clinical assessments. In conclusion despite HSI has been presented as a significant advanced medical imaging tool, addressing its limitations and probable solutions is for broader clinical adoption.

Advancing hyperspectral imaging and machine learning tools toward clinical adoption in tissue diagnostics: A comprehensive review

Hyperspectral imaging (HSI) has become an evident transformative apparatus in medical diagnostics. The review aims to appraise the present advancement and challenges in HSI for medical applications. It features a variety of medical applications namely diagnosing diabetic retinopathy, neurodegenerative diseases like Parkinson's and Alzheimer's, which illustrates its effectiveness in early diagnosis, early caries detection in periodontal disease, and dermatology by detecting skin cancer. Regardless of these advances, the challenges exist within every aspect that limits its broader clinical adoption. It has various constraints including difficulties with technology related to the complexity of the HSI system and needing specialist training, which may act as a drawback to its clinical settings. This article pertains to potential challenges expressed in medical applications and probable solutions to overcome these constraints. Successful companies that perform advanced solutions with HSI in terms of medical applications are being emphasized in this study to signal the high level of interest in medical diagnosis for systems to incorporate machine learning ML and artificial intelligence AI to foster precision diagnosis and standardized clinical workflow. This advancement signifies progressive possibilities of HSI in real-time clinical assessments. In conclusion despite HSI has been presented as a significant advanced medical imaging tool, addressing its limitations and probable solutions is for broader clinical adoption.

Near-infrared spectroscopy data for foot skin oxygen saturation in healthy subjects

Our objective was to evaluate normative data for near-infrared spectroscopy (NIRS) in 110 healthy volunteers by Fitzpatrick skin type (FST) and region of the foot. We obtained measurements of the dorsum and plantar foot using a commercially available device (SnapshotNIR, Kent Imaging, Calgary Canada). On the dorsum of the foot, people with FST6 had significantly lower oxygen saturation compared to FST1-5 (p < 0.001), lower oxyhaemoglobin compared to FST2-5 (p = 0.001), but there was no difference in deoxyhaemoglobin. No differences were found on the plantar foot. When comparing dorsal and plantar foot, there was higher oxyhaemoglobin (0.40 ± 0.09 vs. 0.51 ± 0.12, p < 0.001) and deoxyhaemoglobin (0.16 ± 0.05 vs. 0.21 ± 0.05, p < 0.001) on the plantar foot, but no differences in oxygen saturation (dorsal 70.7 ± 10.8, plantar 70.0 ± 9.5, p = 0.414). In 6.4% of feet, there were black areas, for which no NIRS measurements could be generated. All areas with no data were on the dorsal foot and only found in FST 5-6. People with FST6 had significantly larger areas with no data compared to FST 5 (22.2 cm2  ± 20.4 vs. 1.9 cm2  ± 0.90, p = 0.007). These findings should be considered when using NIRS technology. Skin pigmentation should be evaluated in future NIRS studies.