Deep Learning Model to Predict Sentinel Lymph Node Status in Melanoma Patients

April 2023 in “ Journal of Investigative Dermatology ”

T. Okamoto, M. Kawai, M. Le, S. Shimada, T. Kawamura

melanoma sentinel lymph nodes histopathological images skin cutaneous melanoma The Cancer Genome Atlas convnet attention-pooling layer area under ROC curve lymph node metastasis SLNs AUROC

TLDR The AI model somewhat predicts lymph node status in melanoma patients using skin sample images.

The study by T. Okamoto from the Department of Dermatology, Yamanashi Daigaku Igakubu Daigakuin Sogo Kenkyubu Igakuiki, Japan, aimed to develop an artificial intelligence (AI) model that can predict the prognosis of malignant melanoma patients, specifically their sentinel lymph nodes (SLNs) status, using histopathological images of melanoma. The study used around 400 skin cutaneous melanoma samples from The Cancer Genome Atlas database for training and validation. The model was trained using an imagenet pretrained convnet followed by an attention-pooling layer, and the accuracy was evaluated using the area under ROC curve (AUROC). The best prediction AUROC was 0.65. The model is currently being validated with a dataset from the University of Yamanashi to improve its accuracy. The results suggest that the histological features of the primary melanoma can somewhat predict the status of lymph node metastasis.

View this study on jidonline.org →

Discuss this study in the Community →

Similar Research

5 / 1000+ results

research Diagnosis and Management of Melanoma of the Scalp: A Review of the Literature

3 citations, October 2021 in “Clinical, Cosmetic and Investigational Dermatology”

Scalp melanoma, a deadly skin cancer, is often found late due to its hard-to-see location, especially in older men. Early detection, possible treatments, and the role of hairdressers in spotting it early are discussed. More research is needed to improve detection and treatment.

research Metastatic Melanoma of the Tongue: A Rare Case

November 2012 in “Actas Dermo-Sifiliográficas”

An 86-year-old man had a rare tongue melanoma but refused treatment, showing the need for early cancer detection and treatment.

research Tumor Regression Predicts Higher Risk of Sentinel Node Involvement in Thin Cutaneous Melanomas

68 citations, September 2003 in “British Journal of Dermatology”

Shrinking skin cancer increases the chance of cancer in nearby lymph nodes.

research Footprints of the EADV: A Meeting Report from the 17th Congress of the European Academy of Dermatology and Venereology

4 citations, March 2009 in “British Journal of Dermatology”

The conference highlighted new dermatological treatments and emphasized early intervention and addressing conditions lacking evidence-based treatments.

research A Cross-Sectional Study of Clinical, Dermoscopic, Histopathological, and Molecular Patterns of Scalp Melanoma in Patients With or Without Androgenetic Alopecia

September 2022 in “Scientific Reports”

Scalp melanoma is more common and easier to diagnose early in people with androgenetic alopecia due to sun damage.

Deep Learning Model to Predict Sentinel Lymph Node Status in Melanoma Patients

Related Community Posts Join

community Scalp Sunburns cause permanent hair loss. UPF hats protect you. Watch if you use Tretinoin on the scalp

community Roughly one year on finasteride

community Testosterone and hair loss seeming irrelevance

community New potential hair loss treatment (news release)