This thesis presents my original research on assessing human soft tissue pathologies through the application of artificial intelligence (AI) to medical imaging. The significance of this work lies in the development of automated systems that enhance the understanding of human soft tissue-related pathologies. These systems aim to support more reliable clinical decision-making and enable earlier interventions by minimizing human error and variability, ultimately improving patient outcomes.
This study aims to predict the 1-year survival time of patients with metastatic melanoma using a binary classification approach. The dataset consists of CT scans from 71 patients diagnosed with metastatic melanoma, all studied at Université Clermont Auvergne Hospital, France. The number of lesions per patient ranges from 1 to 11. The survival time is predicted by feeding the CT scan data into a 3D Convolutional Neural Network (CNN), which serves as the model to anticipate the survival outcome based on the available imaging data.
In this project, a gesture-controlled pick-and-place robot was proposed with a drive system. This design is wirelessly controllable using a hand module. The main purpose was to aid physically disabled people to manipulate an object as they wish. Moreover, it will be useful in industrial work as it has the option of mobility, a trait that conventional pick-and-place robots do not have.