Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Araújo, Daniella Castro; Veloso, Adriano; Filho, Renato Santos de Oliveira; Giraud, Marie-Noëlle; Raniero, Leandro; Ferreira, Lydia Masako; Bitar, Renata Andrade

doi:10.1016/j.artmed.2021.102161

Cited by 26 publications

(13 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raman spectroscopy in breast cancer is dominantly performed from breast samples, including handheld Raman probes for tissue classification and assessment of surgical margins ( 17 ). Since skin cancer lesions usually lie on the surface of the body and facilitate Raman spectroscopy, several studies examined skin cancer biopsy specimens for Raman detection to improve the time and convenience needed to confirm the properties of the excised tissue intraoperatively, as well as the strict requirement to expand the extent of excised tumor for reasons similar to the aesthetic needs arising from the excision of facial tumors, where Raman spectroscopy is used to confirm the properties of the edge of the surgical resection area as much as possible intraoperatively ( 19 , 20 ). The successful application of Raman spectroscopy in tumors mentioned above and others for instance nasopharyngeal carcinoma ( 18 ) and prostate cancer ( 22 ) reveals that Raman spectroscopy accepted a wide range of biological samples thanks to its highly sensitive features than the other detection means.…”

Section: Application Of Raman Spectroscopy In Tumormentioning

confidence: 99%

“…Moreover, the Rapidity and non-invasive properties of Raman spectroscopy also enable its potential as an intraoperative inspection method to improve the EOR of glioma surgery, so as to improve surgical outcomes and promote patient prognosis ( 13 – 15 ). Numerous studies have reported the applicability of Raman spectroscopy in the diagnosis of several tumors, which include colorectal cancer ( 16 ), breast cancer ( 17 ), nasopharyngeal carcinoma ( 18 ), skin cancer ( 19 , 20 ), gastric cancer ( 21 ), and prostate cancer ( 22 ), etc. These studies show the prospect of Raman spectroscopy as a novel surgical adjunct to assist in the diagnosis of tumors, and the prominence of Raman spectroscopy in the diagnosis of these tumors and its specific properties - non-invasive, rapid, and accurate - makes it potentially capable of supporting neurosurgeons in the rapid identification of glioma boundaries during surgery ( 8 , 23 , 24 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Raman spectroscopy: A prospective intraoperative visualization technique for gliomas

Zhang

Yu²,

Li³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

The infiltrative growth and malignant biological behavior of glioma make it one of the most challenging malignant tumors in the brain, and how to maximize the extent of resection (EOR) while minimizing the impact on normal brain tissue is the pursuit of neurosurgeons. The current intraoperative visualization assistance techniques applied in clinical practice suffer from low specificity, slow detection speed and low accuracy, while Raman spectroscopy (RS) is a novel spectroscopy technique gradually developed and applied to clinical practice in recent years, which has the advantages of being non-destructive, rapid and accurate at the same time, allowing excellent intraoperative identification of gliomas. In the present work, the latest research on Raman spectroscopy in glioma is summarized to explore the prospect of Raman spectroscopy in glioma surgery.

show abstract

Section: Application Of Raman Spectroscopy In Tumormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Raman spectroscopy: A prospective intraoperative visualization technique for gliomas

Zhang

Yu²,

Li³

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Additionally, it has social and economic effects on people's lives [6,7]. In this regard, the paper written by Araújo et al [21], suggests that histological examination for a skin lesion diagnosis and prognosis.…”

Section: Literature Reviewmentioning

confidence: 99%

Segmentation based early Melanoma Detection Using Random Forest Algorithm

Abate,

Hussein,

Varadarajan

et al. 2023

Preprint

View full text Add to dashboard Cite

This article proposes a method to detect melanoma at the early stage before it becomes something severe. The lesion of melanoma has five stages, stage zero to stage four, of which stage one and stage two are early stages. Melanoma is mainly caused by UV radiation, unhealthy lifestyle, hereditary etc.; In addition, age and gender (sex) are also part of the risk factors causing melanoma. So people ought to be aware of what skin disease they have and what precautions and measures they must be taken at its early stage so as to treat it. Because fatal and dangerous cancers must be managed either through prevention or immediate reaction as it occurs. The purpose of this work is to detect melanoma by applying segmentation method at its early stage using random forest classification algorithms. Therefore, segmentation process is implemented as a means of its detection by taking 600 image datasets which are randomly selected from SIIM- ISIC-2020 training dataset. And attained an accuracy of 95%, a precision of 97.3%, a specificity of 95.4%, a selectivity of 95.3% and an f1 score of 96.3. Hopefully, this result will help physicians treat diseases at an early stage and thus prevent further damage.

show abstract

“…Furthermore, telemedicine applications could adopt such technologies to enable medical doctors to early diagnose patients who do not have access to hospitals with guided information from artificial intelligence. Such early-stage detection of malignant skin diseases could vastly increase the chances of successful treatment [20]. Various computer vision and machine learning techniques have been proposed to address skin lesion classification problems.…”

Section: Background and Related Workmentioning

confidence: 99%

DeepMetaForge: A Deep Vision-Transformer Metadata-Fusion Network for Automatic Skin Lesion Classification

Vachmanus,

Noraset,

Piyanonpong

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Skin cancer is a dangerous form of cancer that develops slowly in skin cells. Delays in diagnosing and treating these malignant skin conditions may have serious repercussions. Likewise, early skin cancer detection has been shown to improve treatment outcomes. This paper proposes DeepMetaForge, a deeplearning framework for skin cancer detection from metadata-accompanied images. The proposed framework utilizes BEiT, a vision transformer pre-trained as a masked image modeling task, as the image-encoding backbone. We further propose merging the encoded metadata with the derived visual characteristics while compressing the aggregate information simultaneously, simulating how photos with metadata are interpreted. The experiment results on four public datasets of dermoscopic and smartphone skin lesion images reveal that the best configuration of our proposed framework yields 87.1% macro-average F1 on average. The empirical scalability analysis further shows that the proposed framework can be implemented in a variety of machine-learning paradigms, including applications on low-resource devices and as services. The findings shed light on not only the possibility of implementing telemedicine solutions for skin cancer on a nationwide scale that could benefit those in need of quality healthcare but also open doors to many intelligent applications in medicine where images and metadata are collected together, such as disease detection from CT-scan images and patients' expression recognition from facial images.

show abstract

Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Cited by 26 publications

References 59 publications

Raman spectroscopy: A prospective intraoperative visualization technique for gliomas

Raman spectroscopy: A prospective intraoperative visualization technique for gliomas

Segmentation based early Melanoma Detection Using Random Forest Algorithm

DeepMetaForge: A Deep Vision-Transformer Metadata-Fusion Network for Automatic Skin Lesion Classification

Contact Info

Product

Resources

About