Institute of Laser and Optoelectronics Technology, Fujian Provincial Key Laboratory for Photonics Technology, Key Laboratory of Optoelectronic Science and Technology for Medicine of Ministry of Education, Fujian Normal University, Fuzhou, China.
Department of Pathology, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
J Biophotonics. 2024 Nov;17(11):e202400233. doi: 10.1002/jbio.202400233. Epub 2024 Sep 11.
Gleason grading system is dependable for quantifying prostate cancer. This paper introduces a fast multiphoton microscopic imaging method via deep learning for automatic Gleason grading. Due to the contradiction between multiphoton microscopy (MPM) imaging speed and quality, a deep learning architecture (SwinIR) is used for image super-resolution to address this issue. The quality of low-resolution image is improved, which increased the acquisition speed from 7.55 s per frame to 0.24 s per frame. A classification network (Swin Transformer) was introduced for automated Gleason grading. The classification accuracy and Macro-F1 achieved by training on high-resolution images are respectively 90.9% and 90.9%. For training on super-resolution images, the classification accuracy and Macro-F1 are respectively 89.9% and 89.9%. It shows that super-resolution image can provide a comparable performance to high-resolution image. Our results suggested that MPM joint image super-resolution and automatic classification methods hold the potential to be a real-time clinical diagnostic tool for prostate cancer diagnosis.
格里森分级系统是可靠的前列腺癌量化工具。本文介绍了一种基于深度学习的快速多光子显微镜成像方法，用于自动格里森分级。由于多光子显微镜 (MPM) 成像速度和质量之间存在矛盾，因此使用深度学习架构 (SwinIR) 进行图像超分辨率处理来解决此问题。低分辨率图像的质量得到了改善，采集速度从每帧 7.55 秒提高到每帧 0.24 秒。引入了分类网络（Swin Transformer）用于自动化的格里森分级。在高分辨率图像上进行训练的分类准确率和宏 F1 分别达到 90.9%和 90.9%。在对超分辨率图像进行训练时，分类准确率和宏 F1 分别达到 89.9%和 89.9%。这表明超分辨率图像可以提供与高分辨率图像相当的性能。我们的结果表明，MPM 联合图像超分辨率和自动分类方法有可能成为前列腺癌诊断的实时临床诊断工具。
