Liver tumor detection and classification from abdominal ultrasound images with CenterNet using contrastive learning
Liver tumor detection and classification from abdominal ultrasound images with CenterNet using contrastive learning
复制标题
使用 CenterNet 使用对比学习对腹部超声图像进行肝脏肿瘤检测和分类
DOI：
10.1117/12.2662969
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Kudo Masatoshi
中科院分区：
文献类型：
--
作者：
Hara Eigo;Doman Keisuke;Mekada Yoshito;Nishida Naoshi;Kudo Masatoshi
腹部超声检查被认为是非常具有挑战性的，因为它需要从处理设备时拍摄的移动图像进行诊断。先前的方法包括两阶段的推断步骤，其中检测输入超声图像中的肿瘤，然后对裁剪区域进行分类。然而，这种先前的方法可能是不准确的，因为肿瘤检测模型由于不能使用全局特征来针对裁剪的诊断图像进行分类而不适合。因此，我们提出了一种使用SimSiam来预训练CenterNet并仅使用单个模型进行推断的方法。该方法将分类精度提高了3%，内存使用率和推理速度分别提高了50%和33%。
Abdominal ultrasound examination is considered to be highly challenging because of its need to diagnose from moving images taken while handling devices. Previous method consisted of a two-stage inference step where tumors in the input ultrasound image was detected and then the cropped area was classified. However, this previous method may be inaccurate because the tumour detection model is not suitable due to the inability to use global features for classification against the cropped diagnostic image. Therefore, we propose a method that uses SimSiam to pretrain CenterNet and infer using only a single model. The proposed method improves classification accuracy by 3%, and improves memory usage and inference speed by 50% and 33% respectively.