Departamento de Ingeniería Industrial and Instituto de Innovación en Productividad y Logística CATENA-USFQ, Universidad San Francisco de Quito USFQ, Quito, 170157, Ecuador; Colegio de Ciencias e Ingenierías "El Politécnico", Universidad San Francisco de Quito USFQ, Quito, 170157, Ecuador.
Departamento de Investigación y Postgrados, Universidad Internacional del Ecuador UIDE, Quito, Ecuador.
Comput Biol Med. 2024 Jul;177:108670. doi: 10.1016/j.compbiomed.2024.108670. Epub 2024 May 28.
No-reference image quality assessment (IQA) is a critical step in medical image analysis, with the objective of predicting perceptual image quality without the need for a pristine reference image. The application of no-reference IQA to CT scans is valuable in providing an automated and objective approach to assessing scan quality, optimizing radiation dose, and improving overall healthcare efficiency. In this paper, we introduce DistilIQA, a novel distilled Vision Transformer network designed for no-reference CT image quality assessment. DistilIQA integrates convolutional operations and multi-head self-attention mechanisms by incorporating a powerful convolutional stem at the beginning of the traditional ViT network. Additionally, we present a two-step distillation methodology aimed at improving network performance and efficiency. In the initial step, a "teacher ensemble network" is constructed by training five vision Transformer networks using a five-fold division schema. In the second step, a "student network", comprising of a single Vision Transformer, is trained using the original labeled dataset and the predictions generated by the teacher network as new labels. DistilIQA is evaluated in the task of quality score prediction from low-dose chest CT scans obtained from the LDCT and Projection data of the Cancer Imaging Archive, along with low-dose abdominal CT images from the LDCTIQAC2023 Grand Challenge. Our results demonstrate DistilIQA's remarkable performance in both benchmarks, surpassing the capabilities of various CNNs and Transformer architectures. Moreover, our comprehensive experimental analysis demonstrates the effectiveness of incorporating convolutional operations within the ViT architecture and highlights the advantages of our distillation methodology.
无参考图像质量评估（IQA）是医学图像分析中的关键步骤，其目标是在无需原始参考图像的情况下预测感知图像质量。将无参考 IQA 应用于 CT 扫描对于提供一种自动和客观的方法来评估扫描质量、优化辐射剂量和提高整体医疗保健效率非常有价值。在本文中，我们介绍了 DistilIQA，这是一种专为无参考 CT 图像质量评估设计的新型蒸馏视觉转换器网络。DistilIQA 通过在传统 ViT 网络的开头集成强大的卷积主干，将卷积操作和多头自注意力机制集成在一起。此外，我们提出了一种两步蒸馏方法，旨在提高网络性能和效率。在初始步骤中，通过使用五折划分方案训练五个视觉转换器网络来构建“教师集成网络”。在第二步中，使用原始标记数据集和教师网络生成的预测作为新标签来训练由单个视觉转换器组成的“学生网络”。我们在从癌症成像档案的 LDCT 和投影数据以及 LDCTIQAC2023 大挑战中的低剂量腹部 CT 图像中获得的低剂量胸部 CT 扫描的质量分数预测任务中评估了 DistilIQA。我们的结果表明，DistilIQA 在这两个基准测试中都表现出色，超过了各种 CNN 和 Transformer 架构的能力。此外，我们全面的实验分析证明了在 ViT 架构中纳入卷积操作的有效性，并强调了我们的蒸馏方法的优势。
