A 3D WUCT system using a single ultrasound transducer is designed and automated. The dataset consist of the WUCT reconstruction results dataset used to train U-Net based semantic segmentation model. Also, dataset i) to study the effect of increase in the number of virtual transducer on reconstruction quality and, ii) effect of variation in the applied pulse width on the reconstruction are provided. The U-Net based semantic segmentation model is trained and used to evaluate dice coefficient corresponding to the phantom’s actual profile and reconstructed profile. The model’s segmentation accuracy is 95.12% and IOU score is 0.7785 on the validation dataset. The accuracy of the generated result is found to be upto 94% similar to the actual profile.
The data set are organised as-
i) AI Smantic segmentaion dataset consisting of original image and their corresponding and an augmented dataset.\
ii) Transducer response data with change in Pulse width and Rise/fall edge time.
iii) Dataset for change in Resolution.
iv) Dataset for change in Pulse-width