Superpixel Raman spectroscopy for rapid skin cancer margin assessment

Feng, Xu; Fox, Matthew C.; Reichenberg, Jason S.; Lopes, Fabiana C P S; Sebastian, Katherine R.; Dunn, Andrew K.; Markey, Mia K.; Tunnell, James W.

doi:10.1002/jbio.201960109

Cited by 16 publications

(17 citation statements)

References 19 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that, the Raman effect was particularly useful for medical applications because the scattered radiation measured is unique for each biomolecule [108]. Since that time, Raman spectroscopy has been applied in skin cancer margin assessment, diagnosis of endometriosis, differentiation between tumor and normal brain tissues, or between parathyroid adenomas and hyperplasia [46,[109][110][111]. In this method, the frequency of a molecule, either vibrational or rotational can be changed with the use of laser light.…”

Section: Raman Spectroscopymentioning

confidence: 99%

Preoperative and Intraoperative Methods of Parathyroid Gland Localization and the Diagnosis of Parathyroid Adenomas

et al. 2020

View full text Add to dashboard Cite

Accurate pre-operative determination of parathyroid glands localization is critical in the selection of minimally invasive parathyroidectomy as a surgical treatment approach in patients with primary hyperparathyroidism (PHPT). Its importance cannot be overemphasized as it helps to minimize the harmful side effects associated with damage to the parathyroid glands such as in hypocalcemia, severe hemorrhage or recurrent laryngeal nerve dysfunction. Preoperative and intraoperative methods decrease the incidence of mistakenly injuring the parathyroid glands and allow for the timely diagnosis of various abnormalities, including parathyroid adenomas. This article reviews 139 studies conducted between 1970 and 2020 (49 years). Studies that were reviewed focused on several techniques including application of carbon nanoparticles, carbon nanoparticles with technetium sestamibi (99m Tc-MIBI), Raman spectroscopy, near-infrared autofluorescence, dynamic optical contrast imaging, laser speckle contrast imaging, shear wave elastography, and indocyanine green to test their potential in providing proper parathyroid glands’ localization. Apart from reviewing the aforementioned techniques, this study focused on the applications that helped in the detection of parathyroid adenomas. Results suggest that applying all the reviewed techniques significantly improves the possibility of providing proper localization of parathyroid glands, and the application of indocyanine green has proven to be the ‘ideal’ approach for the diagnosis of parathyroid adenomas.

show abstract

Section: Raman Spectroscopymentioning

confidence: 99%

Preoperative and Intraoperative Methods of Parathyroid Gland Localization and the Diagnosis of Parathyroid Adenomas

et al. 2020

View full text Add to dashboard Cite

show abstract

“…RCM imaging and frozen section hematoxylin and eosin (H&E) staining were also acquired for reference, but were not used for diagnosis. 21 Those images were obtained using the same system and in the same scale as the Feng 2019 study. Overall, there were 230 RCM images (30 BCC and 200 non-BCC) in the train group and 62 RCM images (36 BCC and 26 non-BCC) in the task group.…”

Section: Clinical Data Setmentioning

confidence: 99%

“…The copyright holder for this preprint this version posted March 4, 2022. ; https://doi.org/10.1101/2022.03.03.482837 doi: bioRxiv preprint pixel paper. 21 Images in the red boxes were Train group and Task group used for our models. Images in the rectangular black box were the abnormal hair structure images that were removed.…”

Section: Clinical Data Setmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning on reflectance confocal microscopy improves Raman spectral diagnosis of basal cell carcinoma

Chen

Feng

Fox

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

SignificanceRaman spectroscopy may be useful to assist Mohs micrographic surgery for skin cancer diagnosis; however, the specificity of Raman spectroscopy is limited by the high spectral similarity between tumors and normal tissues structures such as epidermis and hair follicles. Reflectance confocal microscopy (RCM) can provide imaging guidance with morphological and cytological details similar to histology. Combining Raman spectroscopy with deep-learning-aided RCM has the potential to improve the diagnostic accuracy of Raman without requiring additional input from the clinician.AimWe seek to improve the specificity of Raman for basal cell carcinoma (BCC) by integrating information from RCM images using an Artificial Neural Network.ApproachA Raman biophysical model was used in prior work to classify BCC tumors from surrounding normal tissue structures. 191 RCM images were collected from the same site as the Raman data and served as inputs to train two ResNet50 networks. The networks selected the hair structure images and epidermis images respectively within all the images corresponding to the positive predictions of the Raman Biophysical Model.ResultsDeep learning on RCM images removes 54% of false positive predictions from the Raman Biophysical Model result and keeps the sensitivity as 100%. The specificity was improved from 84.8% by using Raman spectra alone to 93.0% by integrating Raman spectra with RCM imagesConclusionsCombining Raman spectroscopy with deep-learning-aided RCM imaging is a promising tool to guide tumor resection surgery.

show abstract

“…The efficacy of Mohs surgery may increase if the surgical margins could be analysed faster, more reliably and without requiring tissue processing (freezing, cutting and staining) While multiple techniques were employed for the investigation of BCC in-situ , few have been utilised ex-vivo , to investigate the resection surface of skin specimens excised in Mohs surgery [ 6 – 8 ]. Fluorescence confocal microscopy (FCM) scans the tissue surface with a laser beam that is selected to excite fluorophores that bind to cell nuclei [ 7 , 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

Clinical integration of fast Raman spectroscopy for Mohs micrographic surgery of basal cell carcinoma

Boitor

Wolf

Weesie

et al. 2021

Biomed. Opt. Express

View full text Add to dashboard Cite

We present the first clinical integration of a prototype device based on integrated auto-fluorescence imaging and Raman spectroscopy (Fast Raman device) for intra-operative assessment of surgical margins during Mohs micrographic surgery of basal cell carcinoma (BCC). Fresh skin specimens from 112 patients were used to optimise the tissue pre-processing and the Fast Raman algorithms to enable an analysis of complete Mohs layers within 30 minutes. The optimisation allowed >95% of the resection surface area to be investigated (including the deep and epidermal margins). The Fast Raman device was then used to analyse skin layers excised from the most relevant anatomical sites (nose, temple, eyelid, cheek, forehead, eyebrow and lip) and to detect the three main types of BCC (nodular, superficial and infiltrative). These results suggest that the Fast Raman technique is a promising tool to provide an objective diagnosis “tumour clear yes/no” during Mohs surgery of BCC. This clinical integration study is a key step towards a larger scale diagnosis test accuracy study to reliably determine the sensitivity and specificity in a clinical setting.

show abstract

Superpixel Raman spectroscopy for rapid skin cancer margin assessment

Cited by 16 publications

References 19 publications

Preoperative and Intraoperative Methods of Parathyroid Gland Localization and the Diagnosis of Parathyroid Adenomas

Preoperative and Intraoperative Methods of Parathyroid Gland Localization and the Diagnosis of Parathyroid Adenomas

Deep learning on reflectance confocal microscopy improves Raman spectral diagnosis of basal cell carcinoma

Clinical integration of fast Raman spectroscopy for Mohs micrographic surgery of basal cell carcinoma

Contact Info

Product

Resources

About