With the rapid growth of high-speed deep-tissue imaging in biomedical research, there is an urgent need to develop a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress the perturbative noise in high-contrast images; however, for low photon budget multiphoton images, a high detector gain will not only boost the signals but also bring significant background noise. In such a stochastic resonance imaging regime, subthreshold signals may be detectable with the help of noise, meaning that a denoising filter capable of removing noise without sacrificing important cellular features, such as cell boundaries, is desirable.We propose a convolutional neural network-based denoising autoencoder method - a fully convolutional deep denoising autoencoder (DDAE) - to improve the quality of three-photon fluorescence (3PF) and third-harmonic generation (THG) microscopy images.The average of 200 acquired images of a given location served as the low-noise answer for the DDAE training. Compared with other conventional denoising methods, our DDAE model shows a better signal-to-noise ratio (28.86 and 21.66 for 3PF and THG, respectively), structural similarity (0.89 and 0.70 for 3PF and THG, respectively), and preservation of the nuclear or cellular boundaries (F1-score of 0.662 and 0.736 for 3PF and THG, respectively). It shows that DDAE is a better trade-off approach between structural similarity and preserving signal regions.The results of this study validate the effectiveness of the DDAE system in boundary-preserved image denoising.The proposed deep denoising system can enhance the quality of microscopic images and effectively support clinical evaluation and assessment.

Sheng-Yong Niu

Lun-Zhang Guo

Yue Li

Zhiming Zhang

Tzung-Dau Wang

Kai-Chun Liu

You-Jin Li

Yu Tsao

Tzu-Ming Liu

IEEE Journal of Translational Engineering in Health and Medicine

IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE 是一个开放获取的产品，它连接了工程和临床世界，专注于详细描述满足临床需求的先进技术解决方案以及临床结果和医疗保健相关性。该杂志为生物医学工程跨学科领域的最新技术方向提供了一个平台，包括工程、生命科学和医学。该杂志的一个独特之处在于它能够促进医生和工程师之间的合作，以展示广泛而引人注目的现实世界技术和工程解决方案，这些解决方案可以实施以提高患者护理和治疗结果的质量，从而降低成本并改善效率。该杂志为所有对生物医学工程感兴趣并通过美国医学协会直接接触医生和医学界的 IEEE 学会的成员提供了一个临床研究和相关最先进技术的活跃论坛。 AMA) 和其他临床学会。该期刊的范围包括但不限于以下主题：医疗设备、医疗保健提供系统、全球医疗保健计划和基于 ICT 的服务；与降低医疗保健成本的技术相关性；影响医疗保健管理、决策和政策的技术；用于解决特定临床需求的先进技术工作。

The IEEE Journal of Translational Engineering in Health and Medicine is an open-access journal that connects the engineering and clinical worlds. It focuses on providing detailed descriptions of advanced technological solutions that meet clinical needs, as well as their relevance to clinical outcomes and healthcare. The journal serves as a platform for the latest technological directions in the interdisciplinary field of biomedical engineering, including engineering, life sciences, and medicine. Its uniqueness lies in facilitating collaboration between physicians and engineers to showcase a wide range of compelling real-world technologies and engineering solutions that can be implemented to enhance the quality of patient care and treatment outcomes, while reducing costs and improving efficiency. The journal offers an active forum for all those interested in biomedical engineering, particularly for members of IEEE who directly engage with physicians and the medical community through the American Medical Association (AMA) and other clinical societies. The scope of the journal includes, but is not limited to, the following topics: medical devices, healthcare delivery systems, global healthcare initiatives, and ICT-based services; technologies related to reducing healthcare costs; technologies that impact healthcare management, decision-making, and policy; and advanced technological work aimed at addressing specific clinical needs.

IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE 是一本开放获取的期刊，旨在连接工程与临床领域。它专注于详细描述满足临床需求的先进技术解决方案，以及这些解决方案在临床结果和医疗保健中的相关性。该期刊为生物医学工程的跨学科领域提供了一个平台，涵盖工程、生命科学和医学等最新技术方向。其独特之处在于促进医生与工程师之间的合作，展示广泛且引人注目的现实世界技术和工程解决方案，这些解决方案旨在提高患者护理和治疗结果的质量，同时降低成本并提升效率。该期刊为所有对生物医学工程感兴趣的研究者提供了一个活跃的论坛，尤其是通过美国医学协会（AMA）与医生和医学界直接接触的IEEE学会成员。期刊的范围包括但不限于以下主题：医疗设备、医疗保健提供系统、全球医疗保健计划和基于信息通信技术（ICT）的服务；与降低医疗保健成本相关的技术；影响医疗保健管理、决策和政策的技术；以及用于解决特定临床需求的先进技术研究。

Boundary-Preserved Deep Denoising of Stochastic Resonance Enhanced Multiphoton Images

The results of this study validate the effectiveness of the DDAE system in boundary-preserved image denoising and show that D DAE is a better trade-off approach between structural similarity and preserving signal regions.

Category	Quartile
医学	3
医学, 工程生物医学	3

Boundary-Preserved Deep Denoising of Stochastic Resonance Enhanced Multiphoton Images

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
ENGINEERING, BIOMEDICAL	2