Trap-related charge-carrier recombination fundamentally limits the performance of perovskite solar cells and other optoelectronic devices. While improved fabrication and passivation techniques have reduced trap densities, the properties of trap states and their impact on the charge-carrier dynamics in metal-halide perovskites are still under debate. Here, a unified model is presented of the radiative and nonradiative recombination channels in a mixed formamidinium-cesium lead iodide perovskite, including charge-carrier trapping, de-trapping and accumulation, as well as higher-order recombination mechanisms. A fast initial photoluminescence (PL) decay component observed after pulsed photogeneration is demonstrated to result from rapid localization of free charge carriers in unoccupied trap states, which may be followed by de-trapping, or nonradiative recombination with free carriers of opposite charge. Such initial decay components are shown to be highly sensitive to remnant charge carriers that accumulate in traps under pulsedlaser excitation, with partial trap occupation masking the trap density actually present in the material. Finally, such modelling reveals a change in trap density at the phase transition, and disentangles the radiative and nonradiative charge recombination channels present in FA 0.95 Cs 0.05 PbI 3, accurately predicting the experimentally recorded PL efficiencies between 50 and 295 K, and demonstrating that bimolecular recombination is a fully radiative process.

Semi-automatic and fully automatic contouring tools have emerged as an alternative to fully manual segmentation to reduce time spent contouring and to increase contour quality and consistency. Particularly, fully automatic segmentation has seen exceptional improvements through the use of deep learning in recent years. These fully automatic methods may not require user interactions, but the resulting contours are often not suitable to be used in clinical practice without a review by the clinician. Furthermore, they need large amounts of labeled data to be available for training. This review presents alternatives to manual or fully automatic segmentation methods along the spectrum of variable user interactivity and data availability. The challenge lies to determine how much user interaction is necessary and how this user interaction can be used most effectively. While deep learning is already widely used for fully automatic tools, interactive methods are just at the starting point to be transformed by it. Interaction between clinician and machine, via artificial intelligence, can go both ways and this review will present the avenues that are being pursued to improve medical image segmentation.

To investigate a deep learning approach that enables 3D segmentation of an arbitrary structure of interest given a user provided 2D contour for context. Such an approach could decrease delineation times and improve contouring consistency, particularly for anatomical structures for which no automatic segmentation tools exist. Methods: A series of deep learning segmentation models using a Recurrent Residual U-Net with attention gates was trained with a successively expanding training set. Contextual information was provided to the models, using a previously contoured slice as an input, in addition to the slice to be contoured. In total, 6 models were developed, and 19 different anatomical structures were used for training and testing. Each of the models was evaluated for all 19 structures, even if they were excluded from the training set, in order to assess the model's ability to segment unseen structures of interest. Each model's performance was evaluated using the Dice Similarity Coefficient (DSC), Hausdorff distance and relative Added Path Length (APL). Results: The segmentation performance for seen and unseen structures improved when the training set was expanded by addition of structures previously excluded from the training set. A model trained exclusively on heart structures achieved a DSC of 0.33, HD of 44 mm and relative APL of 0.85 when segmenting the spleen, whereas a model trained on a diverse set of structures, but still excluding the spleen, achieved a DSC of 0.80, HD of 13 mm and relative APL of 0.35. Iterative prediction performed better compared to direct prediction when considering unseen structures. Conclusions: Training a contextual deep learning model on a diverse set of structures increases the segmentation performance for the structures in the training set, but importantly enables the model to generalize and make predictions even for unseen structures that were not represented in the training set. This shows that user-provided context can be incorporated into deep learning contouring to facilitate semi-automatic segmentation of CT images for any given structure. Such an approach can enable faster de-novo contouring in clinical practice.

No abstract