Sheethal Bhat

Informatik 5

Address

Martenstrasse 3
91058 Erlangen
10

Contact

sheethal.bhat@fau.de
lme.tf.fau.de/persons/sheethal-bhat/

Sheethal Bhat

Professional Employment:

  • 2026-2031:
    Research Associate at Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg 
  • 2023-2026:
    Research student at Siemens Healthineers, Erlangen
  • 2021-2022:
    Student HiWi/Research Assistant, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
  • 2008-2014:
    Low power Imaging Power and Performance Systems Architect, Intel Corp., Portland, Oregon, USA
  • 2007-2008:
    Student Research Assistant, Carnegie Mellon University, Pittsburgh, USA
  • 2004-2006:
    Software developer, IBM Software Services, Bangalore, India

Education: 

  • 03/2023-03/2026:
    Ph.D. Researcher at Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg 
  • 10/2020-12/2022:
    MSc. Information and Communication Theory (ICT), Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
    Thesis : Normals vs Abnormal Chest X-Ray Classification Using Self-supervised Contrastive Learning
  • 01/2007-06/2008:
    MSc. Image Processing and Pattern Recognition, Carnegie Mellon University, Pittsburgh, USA
  • 08/2000-06/2004:
    BTech. Electronics and Communications Engineering, Sri Jayachamarajendra College of Engineering, Mysuru, India

Granted

  • Image-text deep neural network algorithm for patch-wise prediction of pathology findings,
    Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Florin-C Ghesu, Sasa Grbic, US Patent App. 18/985,120, (2025)
  • Method, apparatus, system, and computer readable medium for image processing software module configuration,
    Sheethal Bhat, Madhu Athreya, YLE Chang, US Patent 9,800,781, (2017)
  • Image capture Sensor configurations,
    R Chukka, R Poornachandran, S Dadu, AK Mishra, Sheethal Bhat, US Patent 9,723,212, (2017)
  • System, method, and apparatus for an edgee-preserving smooth filter for low power architecture,
    J Zhou, O Nestares, Sheethal Bhat, Madhu Athreya, US Patent 8,471,865, (2013)

Filed

  • Confidential - 2025

2023

  • Self-Supervised Learning on Chest X-Rays to improve classification and localization

    (Non-FAU Project)

    Project leader:
    Term: March 1, 2023 - March 1, 2026
    Abstract

    Chest X-Rays (CXR) serve as crucial diagnostic tools for pulmonary and cardiothoracic diseases, generating millions of images daily, a number on the rise due to decreasing acquisition costs. However, there's a pronounced scarcity of radiologists to interpret these images. Traditionally, CXR research has centered on enhancing classification accuracy, often achieving state-of-the-art results. Despite progress, there remain rare and intricate findings challenging for both human radiologists and AI systems to diagnose. Our investigation focuses on leveraging self-supervised image-text models to enhance the classification and localization of diverse findings. These self-supervised models eliminate the need for annotations, enabling the Deep Learning system to effectively learn from extensive public and private datasets.

2026

Journal Articles

Conference Contributions

Unpublished Publications

2025

Journal Articles

Conference Contributions

Miscellaneous

2024

Conference Contributions

2023

Journal Articles

2008

Conference Contributions

2023

  • : Best Masters thesis in ICT-Media systems (Siemens-Healthineers) – 2023

2013

  • : Divisional Recognition Award (Intel Inc. USA) – 2013

2012

  • : Divisional Recognition Award (Intel Inc. USA) – 2012

2009

  • : Spontaneous Recognition Award (Intel Inc. USA) – 2009

2006

Current Theses & Projects

Title Type Student Period Status
Multi-Task Learning for ECG Analysis with Self- and Semi-Supervised Representation Learning MA thesis Mehran Pashaei Aug 2026 – Feb 2027 running
Few shot classification using Patch-CLIP on Mammograms Project Mahmoud Afifi Apr 2026 running
Extending Patch-CLIP to unsupervised detection MA thesis Weijun Dou running
Alzheimers subtype classification and analysis Project Fayaiz Uddin May 2026 – Oct 2026 running
Quantifying Documentation Quality as a Proxy for Quality Culture: Assessing the Impact of Long-Text Fields on an Inspection Risk Model MA thesis Brij Dipakbhai Vachhani Feb 2026 – Aug 2026 running
Improving Weak Localization in Chest X-Ray Vision–Language Models Using Anatomy-Aware and Semi-Supervised Refinement MA thesis Harshvardhan Agarwal running
Improved Zero-shot Pathology detection in medical images MA thesis Atharv Dharmadhikari running

Open Positions

Title Type Student Period
Federated Learning for Heterogeneous Medical Image Segmentation MA thesis Aug 2026 – Mar 2027
AI-Based Prediction of Post-Operative Neurological Deficits in Glioma Patients MA thesis Sep 2026 – Mar 2027
MRI as a biomarker for Brain Amyloid deposition MA thesis Jun 2026 – Mar 2027

Completed Theses & Projects

Title Type Student Period Status
3D grounding DINO on the RATIC dataset Project Siqi Chen Nov 2025 – May 2026 finished
3D cross attention grounding for 3D Grounding DINO Project Jingxuan Nov 2025 – May 2026 finished
3D feature enhancer for 3D Grounding DINO Project Keyi Hou Nov 2025 – May 2026 finished
3D Swin Implementation as input to 3D Grounding DINO Project Gong Han Nov 2025 – May 2026 finished
Benchmarking DL models for Abdominal Multi-Organ Segmentation on the RATIC Dataset Project Lukas Bayer Nov 2025 – Mar 2026 finished
Coordination Under Uncertainty in Multi-Team ADAS Testing MA thesis Priyadharshan Velmurugan Dec 2025 – Jun 2026 finished
Evaluate few-shot detection on VinDR-CXR Project Mahdi Qanbari Apr 2025 – Nov 2025 finished
RAG-Enhanced Low-Cost Vision-Language Models for Diabetic Retinopathy Classification and Automated Medical Report Generation MA thesis Abdelrahman Abdelmonem Abdelrazek Zaian Nov 2025 – May 2026 finished
Evaluate LORA finetuning for detection guided segmentation in CT images MA thesis Robaitul Islam Jan 2026 – Jul 2026 finished
Evaluation and Fusion of Vision-Language and Computer Vision Models for On-road Scenario Extraction in Autonomous Vehicles MA thesis Abdul Basit Dost Sep 2025 – Mar 2026 finished
Prototype-Aligned Latent Space Refinement in Vision-Language Models for Robust Zero-Shot Chest X-Ray Classification MA thesis Florian Kittler Nov 2025 – May 2026 finished
Addressing Data Scarcity in 3D Trauma Detection through Semi-Supervised Learning and Vertex Relative Position Encoding Project Shivam Chaudhary Aug 2025 – Mar 2026 finished
Dynamic Gap Closure Forecasting in the DAX Index MA thesis Samarth Khajuria Mar 2025 – Sep 2025 finished
Unsupervised detection Project Daniel Rosenberger Feb 2025 – Sep 2025 finished
Enhancing Breast Abnormality Detection on Mammograms with Advanced Vision-Language Models MA thesis Karim Mohamed Khalifa Abouzeid Elbarbary Jan 2025 – Jul 2025 finished
Evaluation of stenosis detection in angiography images Project Muhammad Musab Ansari Oct 2024 – Mar 2025 finished
Comparative Evaluation of Deep Learning Models for Chest X-ray Lesion Detection Project Shubham Gupta Jul 2024 – Jan 2025 finished
Evaluate Simpleshot: Simple implementation of few-shot classification on CXRs Project Samarth Khajuria Sep 2024 – Sep 2024 finished
Deep-learning based long-tailed multi-label chest X-ray disease classification MA thesis Rajesh Madhipati Dec 2024 – May 2025 finished
Evaluation of detection performance on CXR dataset using DETR pipeline Project Anshul Dhingra Oct 2023 – Jul 2024 finished
Improving Few Shot Classification in Chest X-rays MA thesis Hamza Naeem Jul 2024 – Jan 2025 finished
Review of Zero-shot, Few-shot classification, detection and segmentation methods in Medical Imaging Project Abushanab, Mohammad Yahia, Maged Badawi Oct 2023 – Apr 2024 finished
Evaluation of MedKLIP for Zero-shot and Fine-tuned classification of CXRs Project Sushmetha Arumugam Oct 2023 – Apr 2024 finished
Improvements in SSL image-text learnings on CXR images MA thesis Prakhar Bharadwaj Mar 2024 – Aug 2024 finished
AI-Driven Monuments Identification System and its details Project Hamza Naeem Oct 2023 – Jan 2024 finished