Artificial intelligence-aided lytic spinal bone metastasis classification on CT scans
Artificial intelligence-aided lytic spinal bone metastasis classification on CT scans
复制标题
CT扫描人工智能辅助溶解性脊柱骨转移分类
DOI：
10.1007/s11548-023-02880-8
复制
发表时间：
2023
影响因子：
3
通讯作者：
Tanigawa Noboru
中科院分区：
文献类型：
--
作者：
Koike Yuhei;Yui Midori;Nakamura Satoaki;Yoshida Asami;Takegawa Hideki;Anetai Yusuke;Hirota Kazuki;Tanigawa Noboru
目的脊柱骨转移直接影响生活质量，溶解性病变为主的患者出现神经系统症状和骨折的风险很高。为了使用常规计算机断层扫描 (CT) 扫描检测和分类溶解性脊柱骨转移，我们开发了一种基于深度学习 (DL) 的计算机辅助检测 (CAD) 系统。方法我们回顾性分析了 79 名患者的 2125 幅诊断和放射治疗 CT 图像。注释为肿瘤（阳性）或非肿瘤（阴性）的图像被随机分为训练（1782 个图像）和测试（343 个图像）数据集。 YOLOv5m 架构用于在整个 CT 扫描中检测椎骨。采用迁移学习技术的 InceptionV3 架构用于对显示椎骨存在的 CT 图像上是否存在溶解性病变进行分类。深度学习模型通过五重交叉验证进行评估。对于椎骨检测，使用交并集 (IoU) 来估计边界框精度。我们评估了受试者工作特征曲线的曲线下面积 (AUC)，以对病变进行分类。此外，我们还确定了准确度、精确度、召回率和 F1 分数。我们使用梯度加权类激活映射 (Grad-CAM) 技术进行视觉解释。结果每张图像的计算时间为 0.44 秒。测试数据集预测椎骨的平均 IoU 值为 0.923±0.052 (0.684–1.000)。在二元分类任务中，测试数据集的准确率、精确率、召回率、F1 分数和 AUC 值分别为 0.872、0.948、0.741、0.832 和 0.941。使用Grad-CAM技术构建的热图与溶解性病变的位置一致。结论我们使用两个DL模型的人工智能辅助CAD系统可以从整个CT图像中快速识别椎骨并检测溶解性脊柱骨转移，尽管需要更大的样本量进一步评估诊断准确性。
PurposeSpinal bone metastases directly affect quality of life, and patients with lytic-dominant lesions are at high risk for neurological symptoms and fractures. To detect and classify lytic spinal bone metastasis using routine computed tomography (CT) scans, we developed a deep learning (DL)-based computer-aided detection (CAD) system.MethodsWe retrospectively analyzed 2125 diagnostic and radiotherapeutic CT images of 79 patients. Images annotated as tumor (positive) or not (negative) were randomized into training (1782 images) and test (343 images) datasets. YOLOv5m architecture was used to detect vertebra on whole CT scans. InceptionV3 architecture with the transfer-learning technique was used to classify the presence/absence of lytic lesions on CT images showing the presence of vertebra. The DL models were evaluated via fivefold cross-validation. For vertebra detection, bounding box accuracy was estimated using intersection over union (IoU). We evaluated the area under the curve (AUC) of a receiver operating characteristic curve to classify lesions. Moreover, we determined the accuracy, precision, recall, and F1 score. We used the gradient-weighted class activation mapping (Grad-CAM) technique for visual interpretation.ResultsThe computation time was 0.44 s per image. The average IoU value of the predicted vertebra was 0.923 ± 0.052 (0.684–1.000) for test datasets. In the binary classification task, the accuracy, precision, recall, F1-score, and AUC value for test datasets were 0.872, 0.948, 0.741, 0.832, and 0.941, respectively. Heat maps constructed using the Grad-CAM technique were consistent with the location of lytic lesions.ConclusionOur artificial intelligence-aided CAD system using two DL models could rapidly identify vertebra bone from whole CT images and detect lytic spinal bone metastasis, although further evaluation of diagnostic accuracy is required with a larger sample size.
影响因子：
51.1
作者：
Sahgal, Arjun;Myrehaug, Sten D.;Parulekar, Wendy R.
通讯作者：
Parulekar, Wendy R.
影响因子：
2.8
作者：
Harada, Garrett K.;Siyaji, Zakariah K.;An, Howard S.
通讯作者：
An, Howard S.
影响因子：
2.8
作者：
Hornung, Alexander L.;Hornung, Christopher M.;Samartzis, Dino
通讯作者：
Samartzis, Dino