Spectral energy balancing system with massive MIMO based hybrid beam forming for wireless 6G communication using dual deep learning model

This work aims to provide an effective hybrid beam forming method with Dual-Deep-Network to overcome overhead for mm-wave massive MIMO systems. In this paper, a Dual-Deep-Network technique is described for the extraction of statistical structures from a hybrid beam forming model based on mmWave logics, as well as training logic for the network map functions. The proposed approach of DDN is trained with proper data sequences used for communication and the training phase is conducted with the norms of numerous channel variants. With the nature of diverse channel states, a Dual-Deep-Network is required to manipulate the level of presence and abilities even after training as well. The performance level improvements are practically summarized in both the transmission and reception entities with the help of the proposed hybrid network architecture and the associated Dual Deep Network algorithm. Specifically, the BER versus SNR and spectral efficiency versus SNR are evaluated as well as the resulting accuracy levels are cross validated with numerous classical communication techniques. This paper shows the processing difficulties of the proposed approach and typically cross-validates with other beam forming logics. The computational cost and performance estimations are improved, and the metrics are clearly visualized on this paper based on improved beamforming procedures as well as the proposed approach of DDN based Multi-Resolution Code Book performance metrics are estimated clearly with proper mathematical model investigations. With 7Kbits/s/Hz and 1e-1, respectively, the key metrics of spectral efficiency and BER are enhanced.

Joint liver and hepatic lesion segmentation in MRI using a hybrid CNN with transformer layers

Backgound and Objective: Deep learning-based segmentation of the liver and hepatic lesions therein steadily gains relevance in clinical practice due to the increasing incidence of liver cancer each year. Whereas various network variants with overall promising results in the field of medical image segmentation have been successfully developed over the last years, almost all of them struggle with the challenge of accurately segmenting hepatic lesions in magnetic resonance imaging (MRI). This led to the idea of combining elements of convolutional and transformer-based architectures to overcome the existing limitations.

METHODS

This work presents a hybrid network called SWTR-Unet, consisting of a pretrained ResNet, transformer blocks as well as a common Unet-style decoder path. This network was primarily applied to single-modality non-contrast-enhanced liver MRI and additionally to the publicly available computed tomography (CT) data of the liver tumor segmentation (LiTS) challenge to verify the applicability on other modalities. For a broader evaluation, multiple state-of-the-art networks were implemented and applied, ensuring direct comparability. Furthermore, correlation analysis and an ablation study were carried out, to investigate various influencing factors on the segmentation accuracy of the presented method.

RESULTS

With Dice similarity scores of averaged 98±2% for liver and 81±28% lesion segmentation on the MRI dataset and 97±2% and 79±25%, respectively on the CT dataset, the proposed SWTR-Unet proved to be a precise approach for liver and hepatic lesion segmentation with state-of-the-art results for MRI and competing accuracy in CT imaging.

CONCLUSION

The achieved segmentation accuracy was found to be on par with manually performed expert segmentations as indicated by inter-observer variabilities for liver lesion segmentation. In conclusion, the presented method could save valuable time and resources in clinical practice.