Background 

Early melanoma detection has profound clinical impact with distant stages having a
32% 5-year relative survival rate. Traditionally, the automation of melanoma detection prior to biopsy has relied on broad-spectrum photography, thresholding in the frequency domain or analysis of electrical impedance. The advent of deep learning (DL) has enabled automation of dermoscopy.
However, most existing end-to-end DL approaches require annotated data, which is time-consuming to produce and cannot propose novel predictive markers. To address this, we utilized the Semantic Clustering by Adopting Nearest Neighbors (SCAN) algorithm, an unsupervised learning approach that decouples feature learning and clustering, enabling the automated detection of dermatoscopic features that predict disease.

Methods 

We employed the SCAN algorithm to analyze 7991 training and 2024 testing
dermatoscopic images of melanoma or benign nevi from the International Skin Imaging Collaboration dataset. Images are almost all Fitzpatrick type I-III. The model was trained to learn semantically meaningful features that were employed to build clusters of similar images.

Results 

The final clusters exhibited varying levels of homogeneity, with several clusters composed exclusively of one class (melanoma/benign nevi). Several highly predictive clusters for melanoma showed an absence of color uniformity, which is a Menzies method criterion to establish melanoma diagnosis. This indicates latent-space morphology congruent with established evidence-based practice.

Conclusion 

The application of the SCAN algorithm to dermatoscopic images presents a promising methodology for unsupervised learning in melanoma detection. Previous work has shown that AI models that offer explanations to clinicians, such as photos of similar lesions in that continuous area of the model’s latent space, boost physician satisfaction. The FDA approval process also prefers explainable paradigms to ensure model predictability spanning the input space. This study presents an unsupervised approach to melanoma detection via dermoscopy, which enables explainable AI and automated detection of features that predict disease. By providing explainability, the research addresses a key challenge in machine learning paradigms’ FDA approval pathway. Future research is warranted to see if analysis of nevi on dark skin (Fitzpatrick type >3) demonstrates alternate dermoscopic features, as has been previously reported in dermoscopic
literature.

End-to-End Semantic Clustering in Dermoscopy of Melanocytic Lesions

 Dermatology

poster

Welcome to the **largest national, multi-specialty research** event featuring research from nearly 700 medical students, residents, fellows, and international medical graduates.

Use the buttons below or navigation menu to access the event.
 


[![](https://assets.underline.io/uploads/markdown_image/1/image/3e33a8c754cc49610b30950617d813e7.png)](https://underline.io/events/434/sessions?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/551404d429c4e274f9a54cbdd7081918.png)](https://underline.io/events/434/posters?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/677d92f566b880cebd36905fc738fc10.png)](https://underline.io/events/434/lounge)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/c7392833c7261c3874c5b43fa2f4df19.png)](https://underline.io/events/434/help-desk)
 

#### Event Details

The 2023 American Medical Association Research Challenge includes a poster symposium hall and a semifinals hall with the top scored research. **Log in at any time throughout the event to:**

* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with participants** and provide feedback to help advance their research
* **Attend education sessions** with physician experts on key research topics

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge finals, present their research to an elite panel of judges, and compete to win a $10,000 grand prize sponsored by Laurel Road. 

### Grand Prize Sponsor

AMA would like to thank Laurel Road for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road is not involved in the judging or scoring process to select the winner. The winner will be announced on February 4, 2024 during the AMA Research Challenge finals. Payment of the grand prize will be directly from Laurel Road. See the AMA Research Challenge Official Rules for terms and conditions.

![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)

**There is no registration fee for this event! **

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals.

**Please use this link [here](https://www.ama-assn.org/about/events/ama-research-challenge) to register for free.**

Registration Is Required

AMA Research Challenge 2023

Join the AMA Research Challenge poster symposium and semifinals to explore top research posters, score posters in the semifinals (an AMA member exclusive opportunity) and attend education sessions with experienced physicians to learn tips to advance your research and career. 

Scott Heston

1

6

SHORT BIO

Presentations

End-to-End Semantic Clustering in Dermoscopy of Melanocytic Lesions

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES