• Corpus ID: 86503922

Malignant Melanoma Classification with Deep Learning

@inproceedings{Kisselgof2019MalignantMC,
  title={Malignant Melanoma Classification with Deep Learning},
  author={Jakob Kisselgof},
  year={2019}
}
Malignant melanoma is the deadliest form of skin cancer. If correctly diagnosed in time, the expected five-year survival rate can increase up to 97 %. Therefore, exploring various methods for early ... 

References

SHOWING 1-10 OF 37 REFERENCES
Malignant Melanoma: A Pictorial Review
TLDR
This review will discuss pathophysiology and risk factors with a focus on history, examination and differential diagnosis, assessment tools to aid early detection, referral pathways based on how and when to refer to secondary care will be discussed briefly.
Malignant melanoma in the 21st century, part 1: epidemiology, risk factors, screening, prevention, and diagnosis.
TLDR
Management of systemic melanoma is a challenge because of a paucity of active treatment modalities and several clinically relevant pathologic subtypes have been identified and need to be recognized.
Survival rates of patients with metastatic malignant melanoma
TLDR
The influence of metastases distribution on the overall survival was examined and it was noticed that there were statistically significant differences between the risks of death of various groups of patients, depending on metastasis topography.
Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
TLDR
In this ISIC 2017 skin lesion analysis challenge, it is proposed to exploit the deep ResNets for robust visual features learning and representations to identify diseases such as melanoma.
Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)
TLDR
The design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge are described, to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer.
Deep Learning and Convolutional Neural Networks in the Aid of the Classification of Melanoma
TLDR
This work uses some techniques of deep learning to try to get better results in the task of classifying whether a melanotic lesion is the malignant type (melanoma) or not (nevus), and presents a training approach using a custom dataset of skin diseases, transfer learning, convolutional neural networks and data augmentation of theDeep Residual Network.
Dermatologist-level classification of skin cancer with deep neural networks
TLDR
This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.
Basic Science and Principles of Dermatologic Diagnosis
TLDR
The fundamental aspects of skin structure and function are reviewed, with many cross-references to the chapters where topics are expanded upon.
Dermoscopy of pigmented skin lesions--a valuable tool for early diagnosis of melanoma.
Using the 7-point checklist as a diagnostic aid for pigmented skin lesions in general practice: a diagnostic validation study.
  • F. Walter, A. Prevost, J. Emery
  • Medicine
    The British journal of general practice : the journal of the Royal College of General Practitioners
  • 2013
TLDR
The Weighted 7PCL, with a revised cut-off score of 4 from 3, performs slightly better and could be applied in general practice to support the recognition of clinically significant lesions and therefore the early identification of melanoma.
...
...