1
|
Parasca SV, Calin MA, Manea D, Radvan R. Hyperspectral imaging with machine learning for in vivo skin carcinoma margin assessment: a preliminary study. Phys Eng Sci Med 2024:10.1007/s13246-024-01435-8. [PMID: 38771442 DOI: 10.1007/s13246-024-01435-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Accepted: 04/30/2024] [Indexed: 05/22/2024]
Abstract
Surgical excision is the most effective treatment of skin carcinomas (basal cell carcinoma or squamous cell carcinoma). Preoperative assessment of tumoral margins plays a decisive role for a successful result. The aim of this work was to evaluate the possibility that hyperspectral imaging could become a valuable tool in solving this problem. Hyperspectral images of 11 histologically diagnosed carcinomas (six basal cell carcinomas and five squamous cell carcinomas) were acquired prior clinical evaluation and surgical excision. The hyperspectral data were then analyzed using a newly developed method for delineating skin cancer tumor margins. This proposed method is based on a segmentation process of the hyperspectral images into regions with similar spectral and spatial features, followed by a machine learning-based data classification process resulting in the generation of classification maps illustrating tumor margins. The Spectral Angle Mapper classifier was used in the data classification process using approximately 37% of the segments as the training sample, the rest being used for testing. The receiver operating characteristic was used as the method for evaluating the performance of the proposed method and the area under the curve as a metric. The results revealed that the performance of the method was very good, with median AUC values of 0.8014 for SCCs, 0.8924 for BCCs, and 0.8930 for normal skin. With AUC values above 0.89 for all types of tissue, the method was considered to have performed very well. In conclusion, hyperspectral imaging can become an objective aid in the preoperative evaluation of carcinoma margins.
Collapse
Affiliation(s)
- Sorin Viorel Parasca
- Carol Davila University of Medicine and Pharmacy, 37 Dionisie Lupu Street, Bucharest, Romania
- Emergency Clinical Hospital for Plastic, Reconstructive Surgery and Burns, 218 Grivitei Street, Bucharest, Romania
| | - Mihaela Antonina Calin
- National Institute of Research and Development for Optoelectronics- INOE 2000, 409 Atomistilor Street, 077125, Magurele, Ilfov, P.O. BOX MG5, Romania.
| | - Dragos Manea
- National Institute of Research and Development for Optoelectronics- INOE 2000, 409 Atomistilor Street, 077125, Magurele, Ilfov, P.O. BOX MG5, Romania
| | - Roxana Radvan
- National Institute of Research and Development for Optoelectronics- INOE 2000, 409 Atomistilor Street, 077125, Magurele, Ilfov, P.O. BOX MG5, Romania
| |
Collapse
|
2
|
A Novel Approach for the Shape Characterisation of Non-Melanoma Skin Lesions Using Elliptic Fourier Analyses and Clinical Images. J Clin Med 2022; 11:jcm11154392. [PMID: 35956008 PMCID: PMC9369039 DOI: 10.3390/jcm11154392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2022] [Revised: 07/23/2022] [Accepted: 07/27/2022] [Indexed: 12/07/2022] Open
Abstract
The early detection of Non-Melanoma Skin Cancer (NMSC) is crucial to achieve the best treatment outcomes. Shape is considered one of the main parameters taken for the detection of some types of skin cancer such as melanoma. For NMSC, the importance of shape as a visual detection parameter is not well-studied. A dataset of 993 standard camera images containing different types of NMSC and benign skin lesions was analysed. For each image, the lesion boundaries were extracted. After an alignment and scaling, Elliptic Fourier Analysis (EFA) coefficients were calculated for the boundary of each lesion. The asymmetry of lesions was also calculated. Then, multivariate statistics were employed for dimensionality reduction and finally computational learning classification was employed to evaluate the separability of the classes. The separation between malignant and benign samples was successful in most cases. The best-performing approach was the combination of EFA coefficients and asymmetry. The combination of EFA and asymmetry resulted in a balanced accuracy of 0.786 and an Area Under Curve of 0.735. The combination of EFA and asymmetry for lesion classification resulted in notable success rates when distinguishing between benign and malignant lesions. In light of these results, skin lesions’ shape should be integrated as a fundamental part of future detection techniques in clinical screening.
Collapse
|
3
|
Zaytsev SM, Amouroux M, Khairallah G, Bashkatov AN, Tuchin VV, Blondel W, Genina EA. Impact of optical clearing on ex vivo human skin optical properties characterized by spatially resolved multimodal spectroscopy. JOURNAL OF BIOPHOTONICS 2022; 15:e202100202. [PMID: 34476912 DOI: 10.1002/jbio.202100202] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2021] [Revised: 08/26/2021] [Accepted: 08/30/2021] [Indexed: 06/13/2023]
Abstract
A spatially resolved multimodal spectroscopic device was used on a two-layered "hybrid" model made of ex vivo skin and fluorescent gel to investigate the effect of skin optical clearing on the depth sensitivity of optical spectroscopy. Time kinetics of fluorescence and diffuse reflectance spectra were acquired in four experimental conditions: with optical clearing agent (OCA) 1 made of polyethylene glycol 400 (PEG-400), propylene glycol and sucrose; with OCA 2 made of PEG-400 and dimethyl sulfoxide (DMSO); with saline solution as control and a "dry" condition. An increase in the gel fluorescence back reflected intensity was measured after optical clearing. Effect of OCA 2 turned out to be stronger than that of OCA 1, possibly due to DMSO impact on the stratum corneum keratin conformation. Complementary experimental results showed increased light transmittance through the skin and confirmed that the improvement in the depth sensitivity of the multimodal spectroscopic approach is related not only to the dehydration and refractive indices matching due to optical clearing, but also to the mechanical compression of tissues caused by the application of the spectroscopic probe.
Collapse
Affiliation(s)
- Sergey M Zaytsev
- Université de Lorraine, CNRS, CRAN UMR 7039, Vandoeuvre-lès-Nancy, France
- Saratov State University, Institute of Physics, Department of Optics and Biophotonics, Saratov, Russian Federation
| | - Marine Amouroux
- Université de Lorraine, CNRS, CRAN UMR 7039, Vandoeuvre-lès-Nancy, France
| | - Grégoire Khairallah
- Université de Lorraine, CNRS, CRAN UMR 7039, Vandoeuvre-lès-Nancy, France
- Department of Plastic, Aesthetic and Reconstructive Surgery, Metz-Thionville Regional Hospital, Ars-Laquenexy, France
| | - Alexey N Bashkatov
- Saratov State University, Institute of Physics, Department of Optics and Biophotonics, Saratov, Russian Federation
- National Research Tomsk State University, Interdisciplinary Laboratory of Biophotonics, Tomsk, Russian Federation
| | - Valery V Tuchin
- Saratov State University, Institute of Physics, Department of Optics and Biophotonics, Saratov, Russian Federation
- National Research Tomsk State University, Interdisciplinary Laboratory of Biophotonics, Tomsk, Russian Federation
- Institute of Precision Mechanics and Control RAS, Laboratory of Laser Diagnostics of Technical and Living Systems, Saratov, Russian Federation
| | - Walter Blondel
- Université de Lorraine, CNRS, CRAN UMR 7039, Vandoeuvre-lès-Nancy, France
| | - Elina A Genina
- Saratov State University, Institute of Physics, Department of Optics and Biophotonics, Saratov, Russian Federation
- National Research Tomsk State University, Interdisciplinary Laboratory of Biophotonics, Tomsk, Russian Federation
| |
Collapse
|
4
|
Stier AC, Goth W, Hurley A, Brown T, Feng X, Zhang Y, Lopes FCPS, Sebastian KR, Ren P, Fox MC, Reichenberg JS, Markey MK, Tunnell JW. Imaging sub-diffuse optical properties of cancerous and normal skin tissue using machine learning-aided spatial frequency domain imaging. JOURNAL OF BIOMEDICAL OPTICS 2021; 26:JBO-210048RR. [PMID: 34558235 PMCID: PMC8459901 DOI: 10.1117/1.jbo.26.9.096007] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Accepted: 08/27/2021] [Indexed: 05/28/2023]
Abstract
SIGNIFICANCE Sub-diffuse optical properties may serve as useful cancer biomarkers, and wide-field heatmaps of these properties could aid physicians in identifying cancerous tissue. Sub-diffuse spatial frequency domain imaging (sd-SFDI) can reveal such wide-field maps, but the current time cost of experimentally validated methods for rendering these heatmaps precludes this technology from potential real-time applications. AIM Our study renders heatmaps of sub-diffuse optical properties from experimental sd-SFDI images in real time and reports these properties for cancerous and normal skin tissue subtypes. APPROACH A phase function sampling method was used to simulate sd-SFDI spectra over a wide range of optical properties. A machine learning model trained on these simulations and tested on tissue phantoms was used to render sub-diffuse optical property heatmaps from sd-SFDI images of cancerous and normal skin tissue. RESULTS The model accurately rendered heatmaps from experimental sd-SFDI images in real time. In addition, heatmaps of a small number of tissue samples are presented to inform hypotheses on sub-diffuse optical property differences across skin tissue subtypes. CONCLUSION These results bring the overall process of sd-SFDI a fundamental step closer to real-time speeds and set a foundation for future real-time medical applications of sd-SFDI such as image guided surgery.
Collapse
Affiliation(s)
- Andrew C. Stier
- The University of Texas at Austin, Department of Electrical and Computer Engineering, Austin, Texas, United States
| | - Will Goth
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Aislinn Hurley
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Treshayla Brown
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Xu Feng
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Yao Zhang
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Fabiana C. P. S. Lopes
- The University of Texas at Austin, Dell Medical School, Department of Internal Medicine, Austin, Texas, United States
| | - Katherine R. Sebastian
- The University of Texas at Austin, Dell Medical School, Department of Internal Medicine, Austin, Texas, United States
| | - Pengyu Ren
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| | - Matthew C. Fox
- The University of Texas at Austin, Dell Medical School, Department of Internal Medicine, Austin, Texas, United States
| | - Jason S. Reichenberg
- The University of Texas at Austin, Dell Medical School, Department of Internal Medicine, Austin, Texas, United States
| | - Mia K. Markey
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
- The University of Texas MD Anderson Cancer Center, Imaging Physics Residency Program, Houston, Texas, United States
| | - James W. Tunnell
- The University of Texas at Austin, Department of Biomedical Engineering, Austin, Texas, United States
| |
Collapse
|
5
|
Bratchenko IA, Bratchenko LA, Moryatov AA, Khristoforova YA, Artemyev DN, Myakinin OO, Orlov AE, Kozlov SV, Zakharov VP. In vivo diagnosis of skin cancer with a portable Raman spectroscopic device. Exp Dermatol 2021; 30:652-663. [PMID: 33566431 DOI: 10.1111/exd.14301] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2020] [Revised: 01/29/2021] [Accepted: 02/05/2021] [Indexed: 12/18/2022]
Abstract
In this study, we performed in vivo diagnosis of skin cancer based on implementation of a portable low-cost spectroscopy setup combining analysis of Raman and autofluorescence spectra in the near-infrared region (800-915 nm). We studied 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable setup. The studies considered the patients examined by GPs in local clinics and directed to a specialized Oncology Dispensary with suspected skin cancer. Each sample was histologically examined after excisional biopsy. The spectra were classified with a projection on latent structures and discriminant analysis. To check the classification models stability, a 10-fold cross-validation was performed. We obtained ROC AUCs of 0.75 (0.71-0.79; 95% CI), 0.69 (0.63-0.76; 95% CI) and 0.81 (0.74-0.87; 95% CI) for classification of a) malignant and benign tumors, b) melanomas and pigmented tumors and c) melanomas and seborrhoeic keratosis, respectively. The positive and negative predictive values ranged from 20% to 52% and from 73% to 99%, respectively. The biopsy ratio varied from 0.92:1 to 4.08:1 (at sensitivity levels from 90% to 99%). The accuracy of automatic analysis with the proposed system is higher than the accuracy of GPs and trainees, and is comparable or less to the accuracy of trained dermatologists. The proposed approach may be combined with other optical techniques of skin lesion analysis, such as dermoscopy- and spectroscopy-based computer-assisted diagnosis systems to increase accuracy of neoplasms classification.
Collapse
Affiliation(s)
- Ivan A Bratchenko
- Department of Laser and Biotechnical Systems, Samara University, Samara, Russia
| | | | - Alexander A Moryatov
- Department of Oncology, Samara State Medical University, Samara, Russia.,Department of Visual Localization Tumors, Samara Regional Clinical Oncology Dispensary, Samara, Russia
| | | | - Dmitry N Artemyev
- Department of Laser and Biotechnical Systems, Samara University, Samara, Russia
| | - Oleg O Myakinin
- Department of Laser and Biotechnical Systems, Samara University, Samara, Russia
| | - Andrey E Orlov
- Department of Visual Localization Tumors, Samara Regional Clinical Oncology Dispensary, Samara, Russia
| | - Sergey V Kozlov
- Department of Oncology, Samara State Medical University, Samara, Russia.,Department of Visual Localization Tumors, Samara Regional Clinical Oncology Dispensary, Samara, Russia
| | - Valery P Zakharov
- Department of Laser and Biotechnical Systems, Samara University, Samara, Russia
| |
Collapse
|