Smart product-service system (Smart PSS), as an emerging digital paradigm, should meet user expectations and optimize their experience with a higher degree of sustainability. As a complex solution bundle with digital technology, its innovative design method differs from the existing method for traditional products. For a reason that massive user-generated data can be collected in the usage stage, which can be utilized to obtain new user requirements and calculate the user satisfaction degree. According to the real-time user preference information, some modules can be upgraded or adjusted in order to extend the lifecycle of the sustainable Smart PSS. Nevertheless, few studies focus on conducting innovative design by concerning massive information collected in the usage stage in a sustainable Smart PSS environment, let alone a novel approach to support the information re-use in product development of other fields. Aiming to fill this gap, a new innovative design methodology is proposed by combining Function-Behavior-Structure (FBS) and Kano model to guide Smart PSS development. User requirements and behaviors are predicted and analysed by forecasting and collecting information from the perspective of information. As an illustrative case study, a self-service medicine vending system is described to explain the proposed approach. This research provides guidance for Smart PSS in the medical field.

When deciding on a kidney tumor’s diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.