Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer
The diagnosis and treatment of non-melanoma skin cancer remain urgent problems. Histological examination of biopsy material—the gold standard of diagnosis—is an invasive procedure that requires a certain amount of time to perform. The ability to detect abnormal cells using fluorescence spectroscopy...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/1/72 |
| _version_ | 1797494772700545024 |
|---|---|
| author | Victoriya Andreeva Evgeniia Aksamentova Andrey Muhachev Alexey Solovey Igor Litvinov Alexey Gusarov Natalia N. Shevtsova Dmitry Kushkin Karina Litvinova |
| author_facet | Victoriya Andreeva Evgeniia Aksamentova Andrey Muhachev Alexey Solovey Igor Litvinov Alexey Gusarov Natalia N. Shevtsova Dmitry Kushkin Karina Litvinova |
| author_sort | Victoriya Andreeva |
| collection | DOAJ |
| description | The diagnosis and treatment of non-melanoma skin cancer remain urgent problems. Histological examination of biopsy material—the gold standard of diagnosis—is an invasive procedure that requires a certain amount of time to perform. The ability to detect abnormal cells using fluorescence spectroscopy (FS) has been shown in many studies. This technique is rapidly expanding due to its safety, relative cost-effectiveness, and efficiency. However, skin lesion FS-based diagnosis is challenging due to a number of single overlapping spectra emitted by fluorescent molecules, making it difficult to distinguish changes in the overall spectrum and the molecular basis for it. We applied deep learning (DL) algorithms to quantitatively assess the ability of FS to differentiate between pathologies and normal skin. A total of 137 patients with various forms of primary and recurrent basal cell carcinoma (BCC) were observed by a multispectral laser-based device with a built-in neural network (NN) “DSL-1”. We measured the fluorescence spectra of suspected non-melanoma skin cancers and compared them with “normal” skin spectra. These spectra were input into DL algorithms to determine whether the skin is normal, pigmented normal, benign, or BCC. The preoperative differential AI-driven fluorescence diagnosis method correctly predicted the BCC lesions. We obtained an average sensitivity of 62% and average specificity of 83% in our experiments. Thus, the presented “DSL-1” diagnostic device can be a viable tool for the real-time diagnosis and guidance of non-melanoma skin cancer resection. |
| first_indexed | 2024-03-10T01:39:06Z |
| format | Article |
| id | doaj.art-20dccf5dcaef4affae0ba9bb28347935 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T01:39:06Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-20dccf5dcaef4affae0ba9bb283479352023-11-23T13:27:44ZengMDPI AGDiagnostics2075-44182021-12-011217210.3390/diagnostics12010072Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin CancerVictoriya Andreeva0Evgeniia Aksamentova1Andrey Muhachev2Alexey Solovey3Igor Litvinov4Alexey Gusarov5Natalia N. Shevtsova6Dmitry Kushkin7Karina Litvinova8Moscow Regional Research and Clinical Institute (MONIKI), 129110 Moscow, RussiaMoscow Regional Research and Clinical Institute (MONIKI), 129110 Moscow, RussiaDeep Smart Light Ltd., 7 Bell Yard, London WC2A 2JR, UKDeep Smart Light Ltd., 7 Bell Yard, London WC2A 2JR, UKDeep Smart Light Ltd., 7 Bell Yard, London WC2A 2JR, UKDeep Smart Light Ltd., 7 Bell Yard, London WC2A 2JR, UKMoscow Regional Research and Clinical Institute (MONIKI), 129110 Moscow, RussiaDermclinic LLC, Bannyy Pereulok 2c2, 129110 Moscow, RussiaDepartment of Bioengineering, Imperial College London, South Kensington, London SW7 2BT, UKThe diagnosis and treatment of non-melanoma skin cancer remain urgent problems. Histological examination of biopsy material—the gold standard of diagnosis—is an invasive procedure that requires a certain amount of time to perform. The ability to detect abnormal cells using fluorescence spectroscopy (FS) has been shown in many studies. This technique is rapidly expanding due to its safety, relative cost-effectiveness, and efficiency. However, skin lesion FS-based diagnosis is challenging due to a number of single overlapping spectra emitted by fluorescent molecules, making it difficult to distinguish changes in the overall spectrum and the molecular basis for it. We applied deep learning (DL) algorithms to quantitatively assess the ability of FS to differentiate between pathologies and normal skin. A total of 137 patients with various forms of primary and recurrent basal cell carcinoma (BCC) were observed by a multispectral laser-based device with a built-in neural network (NN) “DSL-1”. We measured the fluorescence spectra of suspected non-melanoma skin cancers and compared them with “normal” skin spectra. These spectra were input into DL algorithms to determine whether the skin is normal, pigmented normal, benign, or BCC. The preoperative differential AI-driven fluorescence diagnosis method correctly predicted the BCC lesions. We obtained an average sensitivity of 62% and average specificity of 83% in our experiments. Thus, the presented “DSL-1” diagnostic device can be a viable tool for the real-time diagnosis and guidance of non-melanoma skin cancer resection.https://www.mdpi.com/2075-4418/12/1/72non-melanoma skin cancerbasal cell carcinomafluorescence diagnosticsartificial intelligenceneural networkdeep learning |
| spellingShingle | Victoriya Andreeva Evgeniia Aksamentova Andrey Muhachev Alexey Solovey Igor Litvinov Alexey Gusarov Natalia N. Shevtsova Dmitry Kushkin Karina Litvinova Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer Diagnostics non-melanoma skin cancer basal cell carcinoma fluorescence diagnostics artificial intelligence neural network deep learning |
| title | Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer |
| title_full | Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer |
| title_fullStr | Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer |
| title_full_unstemmed | Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer |
| title_short | Preoperative AI-Driven Fluorescence Diagnosis of Non-Melanoma Skin Cancer |
| title_sort | preoperative ai driven fluorescence diagnosis of non melanoma skin cancer |
| topic | non-melanoma skin cancer basal cell carcinoma fluorescence diagnostics artificial intelligence neural network deep learning |
| url | https://www.mdpi.com/2075-4418/12/1/72 |
| work_keys_str_mv | AT victoriyaandreeva preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT evgeniiaaksamentova preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT andreymuhachev preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT alexeysolovey preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT igorlitvinov preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT alexeygusarov preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT natalianshevtsova preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT dmitrykushkin preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer AT karinalitvinova preoperativeaidrivenfluorescencediagnosisofnonmelanomaskincancer |