Publications

2025

1. 

   Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images

   Lakshika Rathi, Giacomo Nebbia, Ken Chang, and 14 more authors

   In Ethics and Fairness in Medical Imaging, 2025

   Abs Bib

   Recent research has revealed the remarkable ability of artificial intelligence (AI) to identify features related to an individual’s self-reported race in medical images, but what such features may be remains an unanswered question. In this work, we aim to identify image regions relevant to race prediction. We argue that previous methods toward this goal (namely, occlusion maps) are not sufficient as they are unable to locate such regions, and we propose to use Cycle-GANs as an alternative. Specifically, we train a Race-specific Cycle-GAN to artificially transform images from patients of one race to images from patients of a different race. We then obtain difference maps by computing the pixel-wise difference between original and transformed image. Difference maps highlight pixels whose values are crucial for an image to be considered as belonging to a patient of a specific race. Additionally, we examine whether such regions are gender dependent by subgrouping our analysis for male and female patients. We show how difference maps are able to identify relevant image regions when previously introduced methods fail, and that, while some differences do exist between genders, the relevant regions mainly overlap.

   @inproceedings{10.1007/978-3-031-72787-0_13,
     author = {Rathi, Lakshika and Nebbia, Giacomo and Chang, Ken and Kumar, Sourav and Gupta, Aarushi and Ahmed, Syed Rakin and Patel, Jay and Clark, Christopher and Veturi, Yoga Advaith and Coyner, Aaron and Rana, Aakanksha and Bridge, Christopher and McNamara, Stephen and Campbell, J. Peter and Li, Matthew and Kalpathy-Cramer, Jayashree and Singh, Praveer},
     editor = {Puyol-Ant{\'o}n, Esther and Zamzmi, Ghada and Feragen, Aasa and King, Andrew P. and Cheplygina, Veronika and Ganz-Benjaminsen, Melanie and Ferrante, Enzo and Glocker, Ben and Petersen, Eike and Baxter, John S. H. and Rekik, Islem and Eagleson, Roy},
     title = {Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images},
     booktitle = {Ethics and Fairness in Medical Imaging},
     year = {2025},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {129--139},
     isbn = {978-3-031-72787-0},
   }

2024

1. COMSNETS

   

   Quantum Autoencoders for Learning Quantum Channel Codes

   Lakshika Rathi, Stephen DiAdamo, and Alireza Shabani

   In 2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS), 2024

   Abs Bib

   This work investigates the application of quantum machine learning techniques for classical and quantum communication across different qubit channel models. By employing parameterized quantum circuits and a flexible channel noise model, we develop a machine learning framework to generate quantum channel codes and evaluate their effectiveness. We explore classical, entanglement-assisted, and quantum communication scenarios within our framework. Applying it to various quantum channel models as proof of concept, we demonstrate strong performance in each case. Our results highlight the potential of quantum machine learning in advancing research on quantum communication systems, enabling a better understanding of capacity bounds under modulation constraints, various communication settings, and diverse channel models.

   @inproceedings{10427450,
     author = {Rathi, Lakshika and DiAdamo, Stephen and Shabani, Alireza},
     booktitle = {2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)},
     title = {Quantum Autoencoders for Learning Quantum Channel Codes},
     year = {2024},
     volume = {},
     number = {},
     pages = {988-993},
     keywords = {Codes;Quantum channels;Qubit;Quantum mechanics;Machine learning;Channel models;Integrated circuit modeling;Channel coding;quantum communication;quantum machine learning;quantum Shannon theory;quantum channel capacity;classical-quantum communication},
     doi = {10.1109/COMSNETS59351.2024.10427450},
   }

2023

1. 

   3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds

   Lakshika Rathi, Edith Tretschk, Christian Theobalt, and 2 more authors

   In The British Machine Vision Conference (BMVC), 2023

   Abs Bib Code Website

   Existing methods for learning 3D representations are deep neural networks trained and tested on classical hardware. Quantum machine learning architectures, despite their theoretically predicted advantages in terms of speed and the representational capacity, have so far not been considered for this problem nor for tasks involving 3D data in general. This paper thus introduces the first quantum auto-encoder for 3D point clouds. Our 3D-QAE approach is fully quantum, i.e. all its data processing components are designed for quantum hardware. It is trained on collections of 3D point clouds to produce their compressed representations. Along with finding a suitable architecture, the core challenges in designing such a fully quantum model include 3D data normalisation and parameter optimisation, and we propose solutions for both these tasks. Experiments on simulated gate-based quantum hardware demonstrate that our method outperforms simple classical baselines, paving the way for a new research direction in 3D computer vision.

   @inproceedings{Rathi2023,
     author = {Rathi, Lakshika and Tretschk, Edith and Theobalt, Christian and Dabral, Rishabh and Golyanik, Vladislav},
     title = {{3D-QAE}: Fully Quantum Auto-Encoding of 3D Point Clouds},
     booktitle = {The British Machine Vision Conference (BMVC)},
     year = {2023},
   }