Jiang Bohan, McNeil Andrew, Liu Yihao, Rudravaram Gaurav, Saknite Inga, Mbala-Kingebeni Placide, Mbaya Olivier Tshiani, Silaphet Tyra, Weiss Rachel, Dodd Lori E, Nussenblatt Veronique, Moyer Daniel, Landman Bennett A, Dawant Benoit M, Tkaczyk Eric R
Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA.
Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, USA.
Proc IEEE Int Symp Biomed Imaging. 2025 Apr;2025. doi: 10.1109/isbi60581.2025.10981147. Epub 2025 May 12.
Mpox is a viral illness with heavy cutaneous involvement. Automatic tracking of mpox lesion progression is critical in determining the resolution of evolving lesions. This work introduces a novel application of deep learning for lesion monitoring through alignment of dermatological hand photographs. By adapting the VoxelMorph framework for 2D photographic data, we explore key point alignment across serial images. We trained our neural network model on a unique dataset of 1,658 hand images and evaluated its performance on a test set of 254 images. Additionally, we validated the method's generalizability with a supplementary set of 500 images, which included extensive Mpox infection. Our findings indicate modest yet significant improvements in key points and lesion center registration across different regularization strengths. Although promising, the complexity of hand structure presents challenges, requiring cautious application and further refinement, especially in regions with intense spatial discontinuities, such as interdigital areas.
猴痘是一种伴有严重皮肤病变的病毒性疾病。自动跟踪猴痘病变进展对于确定不断演变的病变的消退情况至关重要。这项工作介绍了一种通过对齐皮肤科手部照片进行深度学习的新应用，用于病变监测。通过将VoxelMorph框架应用于二维摄影数据，我们探索了连续图像之间的关键点对齐。我们在一个由1658张手部图像组成的独特数据集上训练了我们的神经网络模型，并在一个由254张图像组成的测试集上评估了其性能。此外，我们用一组500张补充图像验证了该方法的通用性，其中包括广泛的猴痘感染情况。我们的研究结果表明，在不同的正则化强度下，关键点和病变中心配准有适度但显著的改善。尽管前景乐观，但手部结构的复杂性带来了挑战，需要谨慎应用并进一步完善，特别是在具有强烈空间不连续性的区域，如指间区域。
