Tailor A, Jurkovic D, Bourne T H, Collins W P, Campbell S
Academic Department of Obstetrics and Gynaecology, King's College School of Medicine and Dentistry, London, UK.
Br J Obstet Gynaecol. 1999 Jan;106(1):21-30. doi: 10.1111/j.1471-0528.1999.tb08080.x.
To generate a neural network algorithm which computes a probability of malignancy score for pre-operative discrimination between malignant and benign adnexal tumours.
A retrospective analysis of previously collected data. Information from 75% of the study group was used to train an artificial neural network and the remainder was used for validation.
The Gynaecological Ultrasound Research Unit at King's College Hospital, London.
Sixty-seven women with known adnexal mass who had been examined using transvaginal B-mode ultrasonography and colour Doppler imaging with pulse spectral analysis immediately before surgery. The excised masses were classified histologically as benign (n = 52) or malignant (n = 15), of which three were borderline.
The variables that were put into the artificial neural network were: age, menopausal status, maximum tumour diameter, tumour volume, locularity, the presence of papillary projections, the presence of random echogenicity, the presence of analysable blood flow velocity waveforms, the peak systolic velocity, time-averaged maximum velocity, the pulsatility index, and resistance index. Histological classification, categorised as benign or malignant, was the output result.
A variant of the back propagation method was selected to train the network. The overall architecture of the network with the best performance contained an input layer with four variables (age, time-averaged maximum velocity, papillary projection score and maximum tumour diameter), a hidden layer with three units and an output layer with one. The sensitivity and specificity at the optimum diagnostic decision value for the artificial neural network output (0.45) were 100% (95% CI 78.2%-100%) and 98.1% (95% CI 89.5%-100%), respectively. These values were significantly better than those obtained from the independent use of the resistance index, pulsatility index, time-averaged maximum velocity or peak systolic velocity at their optimum decision values (P < 0.01).
Artificial neural networks may be used on clinical and ultrasound derived end-points to accurately predict ovarian malignancy. There is a need for a prospective evaluation of this technique using a larger number of patients.
生成一种神经网络算法，用于计算术前鉴别恶性和良性附件肿瘤的恶性概率评分。
对先前收集的数据进行回顾性分析。研究组75%的信息用于训练人工神经网络，其余用于验证。
伦敦国王学院医院妇科超声研究室。
67名已知附件包块的女性，她们在手术前立即接受了经阴道B型超声检查和彩色多普勒成像及脉冲频谱分析。切除的包块经组织学分类为良性（n = 52）或恶性（n = 15），其中3例为交界性。
输入人工神经网络的变量有：年龄、绝经状态、肿瘤最大直径、肿瘤体积、分叶情况、乳头状突起的存在、随机回声的存在、可分析的血流速度波形的存在、收缩期峰值速度、时间平均最大速度、搏动指数和阻力指数。组织学分类为良性或恶性，是输出结果。
选择反向传播方法的一个变体来训练网络。性能最佳的网络总体架构包括一个具有四个变量（年龄、时间平均最大速度、乳头状突起评分和肿瘤最大直径）的输入层、一个具有三个单元的隐藏层和一个具有一个单元的输出层。人工神经网络输出的最佳诊断决策值（0.45）时的敏感性和特异性分别为100%（95%CI 78.2%-100%）和98.1%（95%CI 89.5%-100%）。这些值显著优于在其最佳决策值时单独使用阻力指数、搏动指数、时间平均最大速度或收缩期峰值速度所获得的值（P < 0.01）。
人工神经网络可用于临床和超声得出的终点指标，以准确预测卵巢恶性肿瘤。需要使用更多患者对该技术进行前瞻性评估。
