Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
Department of Dermatology, Allergology and Environmental Medicine II, Hospital Thalkirchner Street, Munich, Germany.
Eur J Cancer. 2023 May;185:53-60. doi: 10.1016/j.ejca.2023.02.025. Epub 2023 Mar 5.
The clinical diagnosis of face and scalp lesions (FSL) is challenging due to overlapping features. Dermatologists encountering diagnostically 'unclear' lesions may benefit from artificial intelligence support via convolutional neural networks (CNN).
In a web-based classification task, dermatologists (n = 64) diagnosed a convenience sample of 100 FSL as 'benign', 'malignant', or 'unclear' and indicated their management decisions ('no action', 'follow-up', 'treatment/excision'). A market-approved CNN (Moleanalyzer-Pro®, FotoFinder Systems, Germany) was applied for binary classifications (benign/malignant) of dermoscopic images.
After reviewing one dermoscopic image per case, dermatologists labelled 562 of 6400 diagnoses (8.8%) as 'unclear' and mostly managed these by follow-up examinations (57.3%, n = 322) or excisions (42.5%, n = 239). Management was incorrect in 58.8% of 291 truly malignant cases (171 'follow-up' or 'no action') and 43.9% of 271 truly benign cases (119 'excision'). Accepting CNN classifications in unclear cases would have reduced false management decisions to 4.1% in truly malignant and 31.7% in truly benign lesions (both p < 0.01). After receiving full case information 239 diagnoses (3.7%) remained 'unclear' to dermatologists, now triggering more excisions (72.0%) than follow-up examinations (28.0%). These management decisions were incorrect in 32.8% of 116 truly malignant cases and 76.4% of 123 truly benign cases. Accepting CNN classifications would have reduced false management decisions to 6.9% in truly malignant lesions and to 38.2% in truly benign cases (both p < 0.01).
Dermatologists mostly managed diagnostically 'unclear' FSL by treatment/excision or follow-up examination. Following CNN classifications as guidance in unclear cases seems suitable to significantly reduce incorrect decisions.
由于面部和头皮病变（FSL）的特征重叠，临床诊断具有挑战性。遇到诊断上“不明确”的病变的皮肤科医生可能会受益于卷积神经网络（CNN）的人工智能支持。
在基于网络的分类任务中，皮肤科医生（n=64）诊断了 100 个 FSL 的便利样本，将其分为“良性”、“恶性”或“不明确”，并表示他们的管理决策（“不采取行动”、“随访”、“治疗/切除”）。一种市售的 CNN（Moleanalyzer-Pro®， FotoFinder Systems，德国）用于对皮肤镜图像进行二元分类（良性/恶性）。
在查看了每个病例的一个皮肤镜图像后，皮肤科医生将 6400 个诊断中的 562 个（8.8%）标记为“不明确”，并主要通过随访检查（57.3%，n=322）或切除（42.5%，n=239）来管理这些病变。在 291 例真正恶性病例中（171 例“随访”或“不采取行动”），58.8%的管理决策不正确，在 271 例真正良性病例中（119 例“切除”），43.9%的管理决策不正确。在不明确的病例中接受 CNN 分类将使真正恶性和真正良性病变的错误管理决策分别减少到 4.1%和 31.7%（均 p<0.01）。在收到完整的病例信息后，239 个诊断（3.7%）仍然对皮肤科医生来说“不明确”，现在触发了更多的切除（72.0%）而不是随访检查（28.0%）。在 116 例真正恶性病例中，32.8%的管理决策不正确，在 123 例真正良性病例中，76.4%的管理决策不正确。在真正恶性病变中，接受 CNN 分类可将错误管理决策减少到 6.9%，在真正良性病变中减少到 38.2%（均 p<0.01）。
皮肤科医生主要通过治疗/切除或随访检查来管理诊断上“不明确”的 FSL。在不明确的病例中遵循 CNN 分类作为指导似乎适合大大减少错误决策。
