Dermatology Unit, Department of Medical, Surgical and Neurosciences, University of Siena, Italy.
Department of Information Engineering and Mathematics, University of Siena, Siena, Italy; Department of Economy Engineering Society and Buisiness, Tuscia University, Viterbo, Italy.
J Dermatol Sci. 2021 Feb;101(2):115-122. doi: 10.1016/j.jdermsci.2020.11.009. Epub 2020 Dec 2.
Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM).
We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL).
A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models.
In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %).
The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.
及时识别恶性黑色素瘤（MM）对全球皮肤科医生来说是一个挑战，也是死亡率的主要决定因素。皮肤镜检查受皮肤科医生经验的影响，在区分非典型痣（AN）和早期黑色素瘤（EM）方面无法达到足够的准确性和可重复性。
我们旨在开发一种深度卷积神经网络（DCNN）模型，以帮助皮肤科医生对非典型黑素细胞皮肤病变（aMSL）进行分类和管理。
从 idScore 数据集的 979 例具有挑战性的 aMSL 病例中得出训练集（630 张图像）、验证集（135 张）和测试集（214 张），其中整合了皮肤镜图像和临床数据（年龄、性别、身体部位和直径），并与组织学数据相关联。设计了一种 DCNN_aMSL 架构，然后对 aMSL 的皮肤镜图像和临床/病史数据进行训练，从而产生集成的“iDCNN_aMSL”模型。比较了 111 名不同经验水平的皮肤科医生对 aMSL 分类（直观诊断）和管理决策（无/长期随访；短期随访；切除/预防性切除）的反应与 DCNN 模型。
在病变分类研究中，iDCNN_aMSL 的准确率最高，达到 AUC = 90.3%，SE = 86.5%和 SP = 73.6%，而 DCNN_aMSL 的 SE = 89.2%，SP = 65.7%和皮肤科医生的直观诊断的 SE = 77.0%，SP = 61.4%。
iDCNN_aMSL 被证明是管理决策的最佳支持工具，减少了不适当切除的比例。所提出的 iDCNN_aMSL 模型可以为皮肤科医生提供准确的支持，帮助他们准确地区分 AN 和 EM，并通过降低他们的不适当切除率来做出医疗决策。
