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.
The main goal of this project was to develop tissue (WM, GM, and CSF) segmentation methods in brain MRI images. The dataset used is IBSR18, which contains 18 skull-stripped and bias field-corrected T1-w images with different spatial resolutions (pixel spacing), and there is a heterogeneity in image intensities that hinders segmentation. System architecture used - Data → Pre-processing → Segmentation (3D patch-wise segmentation using 3D U-Net).
The main objective of this project was to design a computer-aided diagnosis system to develop a deep learning algorithm for diagnosis in histological patches to classify benign vs malignant patches. System architecture used - Image → Normalization → Per instance standardization → Aggressive Data Augmentation → Classification.
The main goal of this project was to design a computer-aided diagnosis system to classify dermoscopic images and determine whether any case belongs to Nevus or lesion. System architecture - Image → Normalization → Per instance standardization → Aggressive Data Augmentation → Classification.
This project aims to register 3D CT lung images, which was tested on the first 4 cases available on 4DCT DIR-Lab Challenge. Where data is available with 300 landmark annotations. Evaluation is made using TRE 3D Euclidean distance between transformed landmarks.
The goal of this project was to demonstrate pedicle screw placement for spine fusion. Steps - 1) Trajectory planning (Type of movement is Point to point), 2) Software simulation of robotic spine surgery (Stäubli Robotics Suite), and 3) Testing demo surgery using Tx60 Stabuli.
The main aim of this project was to design a computer-aided diagnosis system that can detect mass/masses in mammograms to help the screening procedure. System architecture - Image → Candidate extraction → Feature extraction → Classification.
This project proposes a discrete image reconstruction algorithm using parallel beam geometry where a set of X-ray beams are passed through the object of interest and intensity variations of the beams at input and output are measured. To reconstruct, filtered back projection is used, which uses a 1D filter on the projection data before back projecting (2D or 3D) the data onto the image space.
The VIZN application provides an environment where users will be able to test some performance related to the eyesight, observing the evolution over time by means of innovative user controls. In this project, all the tests were prepared in a scientific way.