Hyperspectral imaging in detecting dermal invasion in lentigo maligna melanoma

Neittaanmäki, Noora; Salmivuori, Mari; Pölönen, Ilkka; Jeskanen, Leila; Ranki, Annamari; Saksela, Olli; Snellman, Erna; Grönroos, Mari

doi:10.1111/bjd.15267

Cited by 18 publications

(22 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Panasyuk et al were one of the first to demonstrate that HSI may be used to guide surgery in vivo by using HSI to distinguish tumour tissue from normal breast and other tissues in an experimental rat breast tumour model . Others have also evaluated the effectiveness of HSI to examine tumour resection margins in ex vivo surgical specimens in the operating room including patients undergoing head and neck cancer , colon , and skin cancer surgery and in vivo fluorescence‐based HSI systems have been reported for guiding urological and brain tumour surgery .…”

Section: Discussionmentioning

confidence: 99%

Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies

Shapey

Xie

Nabavi

et al. 2019

Journal of Biophotonics

View full text Add to dashboard Cite

Multispectral and hyperspectral imaging (HSI) are emerging optical imaging techniques with the potential to transform the way surgery is performed but it is not clear whether current systems are capable of delivering real-time tissue characterization and surgical guidance. We conducted a systematic review of surgical in vivo label-free multispectral and HSI systems that have been assessed intraoperatively in adult patients, published over a 10-year period to May 2018. We analysed 13 studies including 7 different HSI systems. Current in-vivo HSI systems generate an intraoperative tissue oxygenation map or enable tumour detection. Intraoperative tissue oxygenation measurements may help to predict those patients at risk of postoperative complications and in-vivo intraoperative tissue characterization may be performed with high specificity and sensitivity. All systems utilized a line-scanning or wavelength-scanning method but the spectral range and number of spectral bands employed varied significantly between studies and according to the system's clinical aim. The time to acquire a hyperspectral cube dataset ranged between 5 and 30 seconds. No safety concerns were reported in any studies. A small number of studies have demonstrated the capabilities of intraoperative in-vivo label-free HSI but further work is needed to fully integrate it into the current surgical workflow.

show abstract

Section: Discussionmentioning

confidence: 99%

Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies

Shapey

Xie

Nabavi

et al. 2019

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…These borders were then traced on a transparent plastic sheet and photographed. The lesions were also imaged with a HSC, prototype HSCP2 (Revenio Group, Vantaa, Finland), in order to reveal possible invasion and to provide a guide to the biopsy site …”

Section: Methodsmentioning

confidence: 99%

“…Clinically, it can be difficult to distinguish between LM and LMM . A novel imaging method employing a hyperspectral camera (HSC) can be used to delineate LM margins and detect dermal invasion …”

Section: Introductionmentioning

confidence: 99%

Ablative fractional laser‐assisted photodynamic therapy for lentigo maligna: a prospective pilot study

Räsänen

Neittaanmäki

Jeskanen

et al. 2019

Acad Dermatol Venereol

Self Cite

View full text Add to dashboard Cite

Background Lentigo maligna (LM) is an in situ form of melanoma carrying a risk of progression to invasive lentigo maligna melanoma (LMM). LM poses a clinical challenge, with subclinical extension and high recurrence rates after incomplete surgery. Alternative treatment methods have been investigated with varying results. Photodynamic therapy (PDT) with methylaminolaevulinate (MAL) has already proved promising in this respect. Objectives To investigate the efficacy of ablative fractional laser (AFL)‐assisted PDT with 5‐aminolaevulinic acid nanoemulsion (BF‐200 ALA) for treating LM. Methods In this non‐sponsored prospective pilot study, ten histologically verified LMs were treated with AFL‐assisted PDT three times at 2‐week intervals using a light dose of 90 J/cm2 per treatment session. Local anaesthesia with ropivacaine was used. Four weeks after the last PDT treatment the lesions were treated surgically with a wide excision and sent for histopathological examination. The primary outcome was complete histopathological clearance of the LM from the surgical specimen. Patient‐reported pain during illumination and the severity of the skin reaction after the PDT treatments were monitored as secondary outcomes. Results The complete histopathological clearance rate was 7 out of 10 LMs (70%). The pain during illumination was tolerable, with the mean pain scores for the PDT sessions on a visual assessment scale ranging from 2.9 to 3.8. Some severe skin reactions occurred during the treatment period, however. Conclusions Ablative fractional laser‐assisted PDT showed moderate efficacy in terms of histological clearance. It could constitute an alternative treatment for LM but due to the side effects it should only be considered in inoperable cases.

show abstract

“…Previously we have used it in delineation of tumor border and distinguish in-situ melanoma from malignant melanoma. 4,5 If you look at closely two spectra in the figure 1 , it is quite easy to see that in clear cases melanoma and healthy skin have characteristic spectra. Unfortunately this is not so in all the cases.…”

Section: Introductionmentioning

confidence: 99%

“…With hyperspectral data containing wavebands from visible to infra-red region, we are able to gather more information from each pixel than using regular imaging systems. 4,5 Using sliding window method over captured spectral image, we will have spectral and spatial domain for further analysis. In this study we describe some incremental steps, which are taking us closer to automatic skin cancer detection, identification and delineation.…”

Section: Introductionmentioning

confidence: 99%

Convolutional neural networks in skin cancer detection using spatial and spectral domain

Pölönen¹,

Rahkonen²,

Annala

et al. 2019

Photonics in Dermatology and Plastic Surgery 2019

View full text Add to dashboard Cite

Skin cancers are world wide deathly health problem, where significant life and cost savings could be achieved if detection of cancer can be done in early phase. Hypespectral imaging is prominent tool for non-invasive screening. In this study we compare how use of both spectral and spatial domain increase classification performance of convolutional neural networks. We compare five different neural network architectures for real patient data. Our models gain same or slightly better positive predictive value as clinicians. Towards more general and reliable model more data is needed and collection of training data should be systematic.

show abstract

Hyperspectral imaging in detecting dermal invasion in lentigo maligna melanoma

Cited by 18 publications

References 7 publications

Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies

Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies

Ablative fractional laser‐assisted photodynamic therapy for lentigo maligna: a prospective pilot study

Convolutional neural networks in skin cancer detection using spatial and spectral domain

Contact Info

Product

Resources

About