Publications

Screening Mammography Breast Cancer Detection

Abstract

Breast cancer is a leading cause of cancer-related deaths, but current programs are expensive and prone to false positives, leading to unnecessary follow-up and patient anxiety. This paper proposes a solution to automated breast cancer detection, to improve the efficiency and accuracy of screening programs. Different methodologies were tested against the RSNA dataset of radiographic breast images of roughly 20,000 female patients and yielded an average validation case pF1 score of 0.56 across methods.

Chakraborty, D. (2023). Screening Mammography Breast Cancer Detection. arXiv preprint. arXiv:2307.11274.


Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment

Abstract

We leverage the fast physics simulator, MuJoCo to run tasks in a continuous control environment and reveal details like the observation space, action space, rewards, etc. for each task. We benchmark value-based methods for continuous control by comparing Q-learning and SARSA through a discretization approach, and using them as baselines, progressively moving into one of the state-of-the-art deep policy gradient method DDPG. Over a large number of episodes, Qlearning outscored SARSA, but DDPG outperformed both in a small number of episodes. Lastly, we also fine-tuned the model hyper-parameters expecting to squeeze more performance but using lesser time and resources. We anticipated that the new design for DDPG would vastly improve performance, yet after only a few episodes, we were able to achieve decent average rewards. We expect to improve the performance provided adequate time and computational resources.

Vaddadi Sai Rahul & Chakraborty, D. (2023). Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment. arXiv preprint. arXiv:2307.11166.


Multimodal Segmentation of Brain Tumours in Volumetric MRI Scans of the Brain Using Time-Distributed U-Net

Abstract

Brain tumour segmentation poses a challenging task even in the eyes of a trained medical practitioner. Traditional machine learning algorithms require hand-coding features from images before they can learn to identify the regions. Deep learning can solve the problem of detecting tumours with precision and even segment it. Neural networks can learn a hierarchical representation of features from the data by itself. We use a time-distributed architecture for U-Net based deep convolutional neural networks (TD-UNET). We tested our network against the MICCAI BRATS 2015 dataset that comprised 220 high-graded gliomas (HGG) and 54 low-graded gliomas (LGG) and yielded a test case accuracy of 58.3%.

Dutta, J., Chakraborty, D., Mondal, D. (2020). Multimodal Segmentation of Brain Tumours in Volumetric MRI Scans of the Brain Using Time-Distributed U-Net. In: Das, A., Nayak, J., Naik, B., Pati, S., Pelusi, D. (eds) Computational Intelligence in Pattern Recognition. Advances in Intelligent Systems and Computing, vol 999. Springer, Singapore. https://doi.org/10.1007/978-981-13-9042-5_62