China
Africa
Explore chapters and articles related to this topic
Artificial Intelligence and Machine Learning
Published in Archana Mire, Vinayak Elangovan, Shailaja Patil, Advances in Deep Learning for Medical Image Analysis, 2022
Kaushik Dehingia, Mdi B. Jeelani, Anusmita Das
The two most common types of skin cancer are melanoma and non-melanoma. Because of melanoma’s high variability and propensity to spread, identification can be more difficult. Dermatologists can diagnose and classify skin cancer using visual examination and dermoscopy. They were able to identify the cancer stage and the treatment or diagnostic protocol for cancer using their pattern recognition experience. AI and ML algorithms are gaining much traction in skin cancer diagnosis [Goyal et al. 2020]. According to Esteva et al. [2017], the performance of DL algorithms in skin cancer classification is extremely strong compared to dermatologists’ performance in skin cancer classification. ML technologies that extract sophisticated features, such as the ABCD rule, the three-point checklist, and deep CNN (DCNN), have also obtained substantial achievements in the area of medical imaging, in which features are directly derived from the images. Ramya et al. [2015] used an adaptive histogram equalization method, a Wiener filter, a segmentation mechanism, and an SVM classifier to identify a small dataset of skin lesions. The skin cancer categorization was highly reliable and widely accepted. Aima and Sharma [2019] achieved an accuracy of 74.76% and a validation loss of 57.56% in their work when handling early-stage melanogenic skin identification by CNN on 514 dermoscopic pictures from International Skin Imaging Collaboration (ISIC) datasets.
Automatic analysis of dermoscopy images–a review
Published in João Manuel, R. S. Tavares, R. M. Natal Jorge, Computational Modelling of Objects Represented in Images, 2018
T. Mendonça, A.R.S. Marçal, A. Vieira, L. Lacerda, C. Caridade, J. Rozeira
Dermoscopy (dermatoscopy or skin surface microscopy) is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions used for dermatology. This diagnostic tool allows for a better visualization of surface and subsurface structures and permits the recognition of morphologic structures not visible by the naked eye, thus opening a new dimension of the clinical morphologic features of pigmented skin lesions (Argenziano et al. 2000). In the last few years there have been significant developments in both dermoscopy and telemedicine, allowing for improved clinical diagnosis of cutaneous lesions. At present there is great interest in the prospects of automatic image analysis systems for dermoscopy. The benefits of such systems are two fold: (1) to provide quantitative information about a lesion that can be relevant for the clinician; (2) to be used as a stand alone early warning tool.
A Probabilistic Neural Network Framework for the Detection of Malignant Melanoma
Published in Raouf N.G. Naguib, Gajanan V. Sherbet, Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management, 2001
M. Hintz-Madsen, L.K. Hansen, J. Larsen, K.T. Drzewiecki
Dermatoscopy is a noninvasive imaging technique that renders the stratum corneum (top layer of the skin) translucent and makes subsurface structures of the skin visible. The technique is fairly simple and involves removing reflections from the skin surface. This is done by applying immersion oil onto the skin lesion and pressing a glass plate with the same reflection index as the stratum corneum onto the lesion. The oil ensures that small cavities between the skin and the glass plate are filled in order to reduce reflections. With a strong light source, usually a halogen lamp, it is now possible to see skin structures below the skin surface. Usually the glass plate and light source are integrated into devices like a dermatoscope or a dermatoscopic camera. Both of these have lenses allowing a 10× magnification of pigmented skin lesions. In Figure 13.1* an example of a skin lesion, recorded by the dermatoscopic imaging technique, is shown.
Recent advances in nanotechnology based combination drug therapy for skin cancer
Published in Journal of Biomaterials Science, Polymer Edition, 2022
Shweta Kumari, Prabhat Kumar Choudhary, Rahul Shukla, Amirhossein Sahebkar, Prashant Kesharwani
Diagnoses of skin cancer starts with a medical history, local examination of skin, dermatoscopy, high frequency ultrasonography and histopathological examination with surgical biopsy (Figure 3). Dermatoscopy is a noninvasive method, it refers to the examination of skin using skin surface microscopy (lens system) and a strong light source which is useful in distinguishing typical skin cancerous changes and is also called as ‘epiluminoscopy’ and ‘epiluminescent microscopy’. Dermatoscopy is mainly used for the evaluation of pigmented skin lesions. In, experienced hands, it is easier to diagnose melanoma. Dermatoscopy is helpful in diagnosing basal cell cancer in addition to skin inspection [31]. With both melanoma and non melanoma skin cancer, the diagnostic confirmation of a suspected lesion is done with the help of skin biopsy and histopathological examinations. The biopsy of the lesion is done by doing excision of 2–5 mm of healthy skin and is accomplished either using punch or shave biopsy. The treatment is decided on the basis of size and the anatomical site of the tumour.
Skin disease migration segmentation network based on multi-scale channel attention
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Bin Yu, Long Yu, Shengwei Tian, Weidong Wu, Zhang Dezhi, Xiaojing Kang
In recent years, dermoscopy has been used as the main diagnosis method for skin diseases in clinical medicine, providing clear and visualised images of skin diseases for clinical medicine, dermatologists can more effectively determine the type of skin lesions through dermatoscopy. However, subjective factors have a greater impact on the diagnosis results (Jutzi et al. 2022). In order to support and help doctors to make more accurate skin disease diagnoses, automatic segmentation computer-aided diagnosis systems to achieve skin disease image segmentation has become an urgent need for clinical diagnosis.