相关实验视频

Updated: Jan 14, 2026

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

增强皮肤病诊断,以区分使用深度学习模型的行为性和脂质性角质炎

Ying-Ying Ren¹, Li-Hong Mei¹, Xiang-Dong Liu²

¹Department of Dermatology, Jinshan Hospital, Fudan University, Shanghai, China.

Frontiers in medicine

|October 20, 2025

概括

一个深度学习 (DL) 模型显著提高了皮肤科医生区分行动性角质炎 (AK) 和性角质炎 (SK) 的能力. 这种人工智能工具可以提高诊断的准确性,特别是对于经验较少的临床医生来说.

科学领域:

皮肤病学皮肤病学
人工智能的人工智能
医疗成像医学成像

背景情况:

从Seborrheic Keratosis (SK) 区分Actinic Keratosis (AK) 呈现出由于视觉相似性的诊断挑战.
准确的分类对于适当的治疗和患者的治疗结果至关重要.

研究的目的:

评估深度学习 (DL) 模型在帮助皮肤科医生准确分类AK与SK病变方面的有效性.
评估DL模型对诊断性能和决策的影响.

主要方法:

使用ViT-B/16架构的对比性语言图像预训练 (CLIP) 模型在2,307个患者病例中进行了训练.
该模型在三个独立的数据集中得到验证. 皮肤病学家的分类在使用DL模型预测之前和之后进行了比较.
诊断性能是使用接收器操作特征曲线下的面积 (AUC),净重新分类指数 (NRI) 和总综合歧视指数 (IDI) 来衡量的.

主要成果:

在DL模型中,在训练和验证队列中,DL模型实现了AUC从0.85到0.89不等.
皮肤科医生1的诊断性能从0.77提高到0.80 (AUC),具有显著的NRI (0.10) 和IDI (0.14) 变化.
皮肤科医生2显示了从0.69到0.79 (AUC) 的显著改善,具有显著的NRI (0.19) 和IDI (0.27) 变化.

结论:

DL模型显著提高了皮肤科医生在区分AK和SK的准确性.
人工智能工具有可能减少诊断主观性,并有助于早期检测癌前病变.
实施DL模型可以改变皮肤病诊断和治疗实践.

关键词:

行为性角质病.计算机辅助诊断是指计算机辅助的诊断.深度学习是一种深度学习.皮肤科医生协助皮肤科医生协助斑疹性角质炎的原因

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

相关概念视频

Skin Cancer

Skin Cancer

Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...

Renewal of Skin Epidermal Stem Cells

Renewal of Skin Epidermal Stem Cells

The skin is divided into epidermis, dermis, and hypodermis, the skin's outermost, middle, and inner layers. The human epidermal layer regularly undergoes renewal, where old, dead cells are replaced by new cells. Epidermal stem cells or EpiSCs divide and differentiate to restore the lost cells. For the renewal process, some EpiSCs continuously self-renew. In contrast, few others differentiate into transit-amplifying cells, which later form prickle or spinous cells, followed by granular...