Green A, Martin N, Pfitzner J, O'Rourke M, Knight N
Epidemiology Unit, Queensland Institute of Medical Research, Herston, Brisbane, Australia.
J Am Acad Dermatol. 1994 Dec;31(6):958-64. doi: 10.1016/s0190-9622(94)70264-0.
It is often difficult to differentiate early melanoma from benign pigmented lesions of similar clinical appearance.
Our purpose was to develop a computer image analysis system that has the potential for use as an adjunct to the clinical distinction of melanoma from less serious pigmented lesions.
The system, consisting of a hand-held device incorporating a color video camera and color frame grabber mounted in a microcomputer, was used in a pigmented lesion clinic. Analysis software extracted features relevant to the size, color, shape, and boundary of each lesion, and these features were correlated with clinical and histologic characteristics on which standard diagnoses of skin tumors are based. For discriminant analysis based on image analysis measurements, equal prior probabilities were assigned to two specified diagnostic groups, namely melanoma and "other pigmented lesions," most of which were melanocytic nevi.
In a 20-month period, video images of 164 unselected pigmented lesions for which complete diagnostic data were available were successfully captured using the camera. Sixteen of 18 melanomas, and 89% of pigmented lesions overall, were correctly classified by the image analysis system, compared with 83% based on clinical gradings of lesion characteristics.
Computer image analysis has the potential to provide a valuable diagnostic aid that could enable clinicians to make highly sensitive and specific diagnoses of early, curable melanoma.
早期黑色素瘤常难以与临床外观相似的良性色素性病变相鉴别。
我们的目的是开发一种计算机图像分析系统，该系统有可能作为辅助手段，用于将黑色素瘤与不太严重的色素性病变进行临床区分。
该系统由一个手持设备组成，该设备包含一个彩色摄像机和安装在微型计算机中的彩色图像采集卡，在色素性病变诊所中使用。分析软件提取与每个病变的大小、颜色、形状和边界相关的特征，这些特征与皮肤肿瘤标准诊断所依据的临床和组织学特征相关。对于基于图像分析测量的判别分析，将相等的先验概率分配给两个指定的诊断组，即黑色素瘤和“其他色素性病变”，其中大多数是黑素细胞痣。
在20个月的时间里，使用该摄像机成功捕获了164个未选择的色素性病变的视频图像，这些病变都有完整的诊断数据。图像分析系统正确分类了18例黑色素瘤中的16例，以及总体上89%的色素性病变，而基于病变特征临床分级的分类准确率为83%。
计算机图像分析有潜力提供有价值的诊断辅助，使临床医生能够对早期可治愈的黑色素瘤做出高度敏感和特异的诊断。
