Digital imaging biomarkers feed machine learning for melanoma screening

Gareau, Daniel S.; Rosa, Joel Correa da; Yagerman, Sarah; Carucci, John A.; Gulati, Nicholas; Hueto, Ferran; DeFazio, Jennifer L.; Suárez‐Fariñas, Mayte; Marghoob, Ashfaq A.; Krueger, James G.

doi:10.1111/exd.13250

Cited by 25 publications

(32 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most were outperformed by the computer diagnostic tool (Haenssle et al 2018). A machine-learning approach was also used prior to surgery to predict the risk of melanoma with promising results that approach the sensitivity and specificity of diagnostic evaluations by expert physicians (Gareau et al 2017).…”

Section: Digital Pathology and Machine Learning/artificial Intelligencementioning

confidence: 99%

Clinical protein science in translational medicine targeting malignant melanoma

et al. 2019

View full text Add to dashboard Cite

Melanoma of the skin is the sixth most common type of cancer in Europe and accounts for 3.4% of all diagnosed cancers. More alarming is the degree of recurrence that occurs with approximately 20% of patients lethally relapsing following treatment. Malignant melanoma is a highly aggressive skin cancer and metastases rapidly extend to the regional lymph nodes (stage 3) and to distal organs (stage 4). Targeted oncotherapy is one of the standard treatment for progressive stage 4 melanoma, and BRAF inhibitors (e.g. vemurafenib, dabrafenib) combined with MEK inhibitor (e.g. trametinib) can effectively counter BRAFV600E-mutated melanomas. Compared to conventional chemotherapy, targeted BRAFV600E inhibition achieves a significantly higher response rate. After a period of cancer control, however, most responsive patients develop resistance to the therapy and lethal progression. The many underlying factors potentially causing resistance to BRAF inhibitors have been extensively studied. Nevertheless, the remaining unsolved clinical questions necessitate alternative research approaches to address the molecular mechanisms underlying metastatic and treatment-resistant melanoma. In broader terms, proteomics can address clinical questions far beyond the reach of genomics, by measuring, i.e. the relative abundance of protein products, post-translational modifications (PTMs), protein localisation, turnover, protein interactions and protein function. More specifically, proteomic analysis of body fluids and tissues in a given medical and clinical setting can aid in the identification of cancer biomarkers and novel therapeutic targets. Achieving this goal requires the development of a robust and reproducible clinical proteomic platform that encompasses automated biobanking of patient samples, tissue sectioning and histological examination, efficient protein extraction, enzymatic digestion, mass spectrometry-based quantitative protein analysis by label-free or labelling technologies and/or enrichment of peptides with specific PTMs. By combining data from, e.g. phosphoproteomics and acetylomics, the protein expression profiles of different melanoma stages can provide a solid framework for understanding the biology and progression of the disease. When complemented by proteogenomics, customised protein sequence databases generated from patient-specific genomic and transcriptomic data aid in interpreting clinical proteomic biomarker data to provide a deeper and more comprehensive molecular characterisation of cellular

show abstract

Section: Digital Pathology and Machine Learning/artificial Intelligencementioning

confidence: 99%

Clinical protein science in translational medicine targeting malignant melanoma

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Clinical melanoma screening is a signal‐detection problem, which guides the binary decision for or against biopsy. Physicians screening for melanoma prior to the (gold standard) biopsy may be aided or, in some cases, outperformed by artificial‐intelligence analysis . However, deep‐learning dermatology algorithms cannot show a physician how a decision was arrived at, diminishing enthusiasm in the medical community .…”

Section: Introductionmentioning

confidence: 99%

“…Examples of melanoma imaging biomarkers include symmetry, border, brightness, number of colors, organization of pigmented network pattern, etc. In our previous report, we described two types of imaging biomarkers: single color channel imaging biomarkers derived from gray scale images extracted from individual color channels, that is, Red, Green, Blue (RGB), and multi‐color imaging biomarkers that were derived from all color channels simultaneously . An example of a multi‐color imaging biomarker would be the number of dermoscopic colors contained in the lesion, since the definition of a color includes relative levels of intensity for the red, green, and blue channels.…”

Section: Introductionmentioning

confidence: 99%

“…An example of a multi‐color imaging biomarker would be the number of dermoscopic colors contained in the lesion, since the definition of a color includes relative levels of intensity for the red, green, and blue channels. These melanoma imaging biomarkers are spectrally dependent in RGB color channels, with the majority of imaging biomarkers showing statistical significance for melanoma detection in the red or blue color channels .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral imaging in automated digital dermoscopy screening for melanoma

et al. 2019

Self Cite

View full text Add to dashboard Cite

Objectives Early melanoma detection decreases morbidity and mortality. Early detection classically involves dermoscopy to identify suspicious lesions for which biopsy is indicated. Biopsy and histological examination then diagnose benign nevi, atypical nevi, or cancerous growths. With current methods, a considerable number of unnecessary biopsies are performed as only 11% of all biopsied, suspicious lesions are actually melanomas. Thus, there is a need for more advanced noninvasive diagnostics to guide the decision of whether or not to biopsy. Artificial intelligence can generate screening algorithms that transform a set of imaging biomarkers into a risk score that can be used to classify a lesion as a melanoma or a nevus by comparing the score to a classification threshold. Melanoma imaging biomarkers have been shown to be spectrally dependent in Red, Green, Blue (RGB) color channels, and hyperspectral imaging may further enhance diagnostic power. The purpose of this study was to use the same melanoma imaging biomarkers previously described, but over a wider range of wavelengths to determine if, in combination with machine learning algorithms, this could result in enhanced melanoma detection. Methods We used the melanoma advanced imaging dermatoscope (mAID) to image pigmented lesions assessed by dermatologists as requiring a biopsy. The mAID is a 21‐wavelength imaging device in the 350–950 nm range. We then generated imaging biomarkers from these hyperspectral dermoscopy images, and, with the help of artificial intelligence algorithms, generated a melanoma Q‐score for each lesion (0 = nevus, 1 = melanoma). The Q‐score was then compared to the histopathologic diagnosis. Results The overall sensitivity and specificity of hyperspectral dermoscopy in detecting melanoma when evaluated in a set of lesions selected by dermatologists as requiring biopsy was 100% and 36%, respectively. Conclusion With widespread application, and if validated in larger clinical trials, this non‐invasive methodology could decrease unnecessary biopsies and potentially increase life‐saving early detection events. Lasers Surg. Med. 51:214–222, 2019. © 2019 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.

show abstract

“…Current development in image processing and machine learning techniques have produced systems based on artificial neural convolutional networks which are better than humans in object classification tasks − including the diagnostics of skin neoplasms (Gavrilov, 2018). There are algorithms for automated computer analysis of dermatological images, allowing to determine the border, brightness, diameter and symmetry of pigmentation (Gareau D.S. et al 2017) and, thus, provide assistance to doctors to improve the accuracy of diagnosis (Fink C. et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Skin Lesions Diagnosis

Gavrilov

Shchelkunov

Melerzanov

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> Melanoma is one of the most virulent lesions of human’s skin. The visual diagnosis accuracy of melanoma directly depends on the doctor’s qualification and specialization. State-of-the-art solutions in the field of image processing and machine learning allows to create intelligent systems based on artificial convolutional neural network exceeding human’s rates in the field of object classification, including the case of malignant skin lesions. This paper presents an algorithm for the early melanoma diagnosis based on artificial deep convolutional neural networks. The algorithm proposed allows to reach the classification accuracy of melanoma at least 91%.</p>

show abstract

Digital imaging biomarkers feed machine learning for melanoma screening

Cited by 25 publications

References 9 publications

Clinical protein science in translational medicine targeting malignant melanoma

Clinical protein science in translational medicine targeting malignant melanoma

Hyperspectral imaging in automated digital dermoscopy screening for melanoma

Deep Learning Based Skin Lesions Diagnosis

Contact Info

Product

Resources

About