Search

Fruits are important agricultural products in the current society. The demands for high-quality fruits have promoted the development of various nondestructive firmness evaluation methods in recent 20 years. The nondestructive and fast techniques used in the prediction of the firmness of various fruits can be divided into two categories: optical-based methods and mechanical-based methods. Optical-based methods mainly refer to visible/near-infrared (Vis/NIR) spectroscopy, hyperspectral or multispectral imaging (HIS/MSI), spatially resolved reflectance spectroscopy (SRRS), laser light backscatter imaging (LLBI), and others. Mechanical-based methods including several techniques such as micro-deformation, vibration measurements, acoustic impact response, falling impact, hammer impact, and ultrasonic methods. Fundamental principles, as well as measured performances of mechanical-based methods and optical-based methods for measuring the firmness of fruit, are discussed in detail in this paper. The techniques that can be applied to on-line sorting are considered emphatically. Both mechanical-based and optical-based methods have advantages and disadvantages in predicting fruit firmness. The correlations between the firmness measured by mechanical-based methods and puncture firmness are poor in some studies, and the optical methods also have not obtained satisfactory results. Therefore, the on-line measurement of fruit firmness with high accuracy is still facing some challenges. [ABSTRACT FROM AUTHOR]

All three contrast-enhanced (CE) phases (e.g., Arterial, Portal Venous, and Delay) are crucial for diagnosing liver tumors. However, acquiring all three phases is constrained due to contrast agents (CAs) risks, long imaging time, and strict imaging criteria. In this paper, we propose a novel Common-Unique Decomposition Driven Diffusion Model (CUDD-DM), capable of converting any two input phases in three phases into the remaining one, thereby reducing patient wait time, conserving medical resources, and reducing the use of CAs. 1) The Common-Unique Feature Decomposition Module, by utilizing spectral decomposition to capture both common and unique features among different inputs, not only learns correlations in highly similar areas between two input phases but also learns differences in different areas, thereby laying a foundation for the synthesis of remaining phase. 2) The Multi-scale Temporal Reset Gates Module, by bidirectional comparing lesions in current and multiple historical slices, maximizes reliance on previous slices when no lesions and minimizes this reliance when lesions are present, thereby preventing interference between consecutive slices. 3) The Diffusion Model-Driven Lesion Detail Synthesis Module, by employing a continuous and progressive generation process, accurately captures detailed features between data distributions, thereby avoiding the loss of detail caused by traditional methods (e.g., GAN) that overfocus on global distributions. Extensive experiments on a generalized CE liver tumor dataset have demonstrated that our CUDD-DM achieves state-of-the-art performance (improved the SSIM by at least 2.2% (lesions area 5.3%) comparing the seven leading methods). These results demonstrate that CUDD-DM advances CE liver tumor imaging technology.