# Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features

arXiv: https://arxiv.org/abs/1703.04559 · HTML: https://mlsanity.com/paper/1703.04559/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2017.

## Built on by (most cited first, 9 of 9)

- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions](https://mlsanity.com/paper/2201.01249/) (2022)
- [TATL: Task Agnostic Transfer Learning for Skin Attributes Detection](https://mlsanity.com/paper/2104.01641/) (2021)
- [Segmentation Style Discovery: Application to Skin Lesion Images](https://mlsanity.com/paper/2408.02787/) (2024)
- [Deep Learning Based Decision Support for Medicine -- A Case Study on Skin Cancer Diagnosis](https://mlsanity.com/paper/2103.05112/) (2021)
- [Early Melanoma Diagnosis with Sequential Dermoscopic Images](https://mlsanity.com/paper/2110.05976/) (2021)
- [Benchmarking of Lightweight Deep Learning Architectures for Skin Cancer Classification using ISIC 2017 Dataset](https://mlsanity.com/paper/2110.12270/) (2021)
- [Explainable Deep Image Classifiers for Skin Lesion Diagnosis](https://mlsanity.com/paper/2111.11863/) (2021)
- [A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding](https://mlsanity.com/paper/2512.21414/) (2025)

## Abstract (arXiv)

The presence of certain clinical dermoscopic features within a skin lesion may indicate melanoma, and automatically detecting these features may lead to more quantitative and reproducible diagnoses. We reformulate the task of classifying clinical dermoscopic features within superpixels as a segmentation problem, and propose a fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. Our neural network architecture uses interpolated feature maps from several intermediate network layers, and addresses imbalanced labels by minimizing a negative multi-label Dice-F1 score, where the score is computed across the mini-batch for each label. Our approach ranked first place in the 2017 ISIC-ISBI Part 2: Dermoscopic Feature Classification Task challenge over both the provided validation and test datasets, achieving a 0.895% area under the receiver operator characteristic curve score. We show how simple baseline models can outrank state-of-the-art approaches when using the official metrics of the challenge, and propose to use a fuzzy Jaccard Index that ignores the empty set (i.e., masks devoid of positive pixels) when ranking models. Our results suggest that (i) the classification of clinical dermoscopic features can be effectively approached as a segmentation problem, and (ii) the current metrics used to rank models may not well capture the efficacy of the model. We plan to make our trained model and code publicly available.