Susan M. Swetter

Bio: Susan M. Swetter is an academic researcher from Stanford University. The author has contributed to research in topics: Melanoma & Cutaneous melanoma. The author has an hindex of 52, co-authored 186 publications receiving 14655 citations. Previous affiliations of Susan M. Swetter include University of Utah & VA Palo Alto Healthcare System.

Dermatologist-level classification of skin cancer with deep neural networks

Abstract: Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.

Characterization of circulating T cells specific for tumor-associated antigens in melanoma patients.

Abstract: We identified circulating CD8+ T-cell populations specific for the tumor-associated antigens (TAAs) MART-1 (27-35) or tyrosinase (368-376) in six of eleven patients with metastatic melanoma using peptide/HLA-A*0201 tetramers. These TAA-specific populations were of two phenotypically distinct types: one, typical for memory/effector T cells; the other, a previously undescribed phenotype expressing both naive and effector cell markers. This latter type represented more than 2% of the total CD8+ T cells in one patient, permitting detailed phenotypic and functional analysis. Although these cells have many of the hallmarks of effector T cells, they were functionally unresponsive, unable to directly lyse melanoma target cells or produce cytokines in response to mitogens. In contrast, CD8+ T cells from the same patient were able to lyse EBV-pulsed target cells and showed robust allogeneic responses. Thus, the clonally expanded TAA-specific population seems to have been selectively rendered anergic in vivo. Peptide stimulation of the TAA-specific T-cell populations in other patients failed to induce substantial upregulation of CD69 expression, indicating that these cells may also have functional defects, leading to blunted activation responses. These data demonstrate that systemic TAA-specific T-cell responses can develop de novo in cancer patients, but that antigen-specific unresponsiveness may explain why such cells are unable to control tumor growth.

Human melanoma-initiating cells express neural crest nerve growth factor receptor CD271

Abstract: The question of whether tumorigenic cancer stem cells exist in human melanomas has arisen in the last few years. Here we show that in melanomas, tumour stem cells (MTSCs, for melanoma tumour stem cells) can be isolated prospectively as a highly enriched CD271(+) MTSC population using a process that maximizes viable cell transplantation. The tumours sampled in this study were taken from a broad spectrum of sites and stages. High-viability cells isolated by fluorescence-activated cell sorting and re-suspended in a matrigel vehicle were implanted into T-, B- and natural-killer-deficient Rag2(-/-)gammac(-/-) mice. The CD271(+) subset of cells was the tumour-initiating population in 90% (nine out of ten) of melanomas tested. Transplantation of isolated CD271(+) melanoma cells into engrafted human skin or bone in Rag2(-/-)gammac(-/-) mice resulted in melanoma; however, melanoma did not develop after transplantation of isolated CD271(-) cells. We also show that in mice, tumours derived from transplanted human CD271(+) melanoma cells were capable of metastatsis in vivo. CD271(+) melanoma cells lacked expression of TYR, MART1 and MAGE in 86%, 69% and 68% of melanoma patients, respectively, which helps to explain why T-cell therapies directed at these antigens usually result in only temporary tumour shrinkage.

Guidelines of care for the management of primary cutaneous melanoma

Abstract: The incidence of primary cutaneous melanoma has been increasing dramatically for several decades. Melanoma accounts for the majority of skin cancer–related deaths, but treatment is nearly always curative with early detection of disease. In this update of the guidelines of care, we will discuss the treatment of patients with primary cutaneous melanoma. We will discuss biopsy techniques of a lesion clinically suspicious for melanoma and offer recommendations for the histopathologic interpretation of cutaneous melanoma. We will offer recommendations for the use of laboratory and imaging tests in the initial workup of patients with newly diagnosed melanoma and for follow-up of asymptomatic patients. With regard to treatment of primary cutaneous melanoma, we will provide recommendations for surgical margins and briefly discuss nonsurgical treatments. Finally, we will discuss the value and limitations of sentinel lymph node biopsy and offer recommendations for its use in patients with primary cutaneous melanoma.

A survey on Image Data Augmentation for Deep Learning

Abstract: Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them. The image augmentation algorithms discussed in this survey include geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks, neural style transfer, and meta-learning. The application of augmentation methods based on GANs are heavily covered in this survey. In addition to augmentation techniques, this paper will briefly discuss other characteristics of Data Augmentation such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing Data Augmentation. Readers will understand how Data Augmentation can improve the performance of their models and expand limited datasets to take advantage of the capabilities of big data.

Specific recruitment of regulatory T cells in ovarian carcinoma fosters immune privilege and predicts reduced survival.

Abstract: Regulatory T (T(reg)) cells mediate homeostatic peripheral tolerance by suppressing autoreactive T cells. Failure of host antitumor immunity may be caused by exaggerated suppression of tumor-associated antigen-reactive lymphocytes mediated by T(reg) cells; however, definitive evidence that T(reg) cells have an immunopathological role in human cancer is lacking. Here we show, in detailed studies of CD4(+)CD25(+)FOXP3(+) T(reg) cells in 104 individuals affected with ovarian carcinoma, that human tumor T(reg) cells suppress tumor-specific T cell immunity and contribute to growth of human tumors in vivo. We also show that tumor T(reg) cells are associated with a high death hazard and reduced survival. Human T(reg) cells preferentially move to and accumulate in tumors and ascites, but rarely enter draining lymph nodes in later cancer stages. Tumor cells and microenvironmental macrophages produce the chemokine CCL22, which mediates trafficking of T(reg) cells to the tumor. This specific recruitment of T(reg) cells represents a mechanism by which tumors may foster immune privilege. Thus, blocking T(reg) cell migration or function may help to defeat human cancer.