卷积神经网络自动检测体部CT脊柱溶骨性病变的原创研究
本研究开发并测试了一种基于U-Net架构的卷积神经网络,用于在胸部、腹部和盆腔CT扫描中检测脊柱溶骨性病变。结果显示平均全局敏感度为90.6%,局部敏感度为74.0%,局部阳性预测值为78.3%,全局特异度为63.3%。结论认为该任务训练的CNN在检测轴位CT图像上的脊柱溶骨性病变方面显示出良好的敏感度。
要点
- CNN对脊柱溶骨性病变的全局敏感度达90.6%,但局部敏感度仅74.0%,可能漏检多发病灶。
- 全局特异度63.3%,对照图像中28.8-44.9%至少出现一个假阳性病变,需注意假阳性。
- 正常骨和背景的Dice分数较高(0.95和0.99),但病变分割Dice仅0.61,提示病变边界分割欠精确。
局限性
- 测试集较小(60张图像),可能影响结果稳定性。
- 病变分割Dice分数较低(0.61),边界分割不精确。
- 全局特异度较低(63.3%),假阳性率较高。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop, train, and test a convolutional neural network (CNN) for detection of spinal lytic lesions in chest, abdomen, and pelvis CT scans.
MATERIALS AND METHODS: Cases of malignant spinal lytic lesions in CT scans were identified. Images were manually segmented for the following classes: (i) lesion, (ii) normal bone, (iii) background. If more than one lesion was on a single slice, all lesions were segmented. Images were stored as 128×128 pixel grayscale, with 10% segregated for testing. The training pipeline of the dataset included histogram equalization and data augmentation. A model was trained on Keras/Tensorflow using an 80/20 training/validation split, based on U-Net architecture. Additional testing of the model was performed on 1106 images of healthy controls. Global sensitivity measured detection of any lesion on a single image. Local sensitivity and positive predictive value (PPV) measured detection of all lesions on an image. Global specificity measured false positive rate in non-pathologic bone.
RESULTS: Six hundred images were obtained for model creation. The training set consisted of 540 images, which was augmented to 20,000. The test set consisted of 60 images. Model training was performed in triplicate. Mean Dice scores were 0.61 for lytic lesion, 0.95 for normal bone, and 0.99 for background. Mean global sensitivity was 90.6%, local sensitivity was 74.0%, local PPV was 78.3%, and global specificity was 63.3%. At least one false positive lesion was noted in 28.8-44.9% of control images.
CONCLUSION: A task-trained CNN showed good sensitivity in detecting spinal lytic lesions in axial CT images.
引用
- Chang, Huber, Yeh, et al. Original research: utilization of a convolutional neural network for automated detection of lytic spinal lesions on body CTs. Skeletal Radiol. 2023. PMID: 36651936. doi:10.1007/s00256-023-04283-x
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。