Sheethal Bhat

Sheethal Bhat

Researcher

Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 09.158
Martensstraße 3
91058 Erlangen

Office hours

 

Education: 

  • Since 03/2023:
    Ph.D. Researcher at Pattern Recognition Lab and Siemens Healthineers
  • 10/2020-12/2022:
    Student at Friedrich-Alexander-Universität Erlangen-Nürnberg, Information and Communication Theory (ICT)
    Masters thesis : Normals vs Abnormal Chest X-Ray classification using Self-supervised Contrastive Learning.
  • 01/2007-06/2008:
    Student at Carnegie Mellon University, Pittsburgh, USA, Image processing and Pattern recognition

Professional Employment:

  • 2004-2006:
    IBM Software Services, Bangalore, India
  • 2008-2014:
    Low power imaging Power and Performance systems Architect, Intel, USA

2023

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

    (Non-FAU Project)

    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.

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

No matching records found.

 

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

Type Title Status
Project Evaluate few-shot detection on VinDR-CXR finished
MA thesis RAG-Enhanced Low-Cost Vision-Language Models for Diabetic Retinopathy Classification and Automated Reporting running
MA thesis Evaluate LORA finetuning for detection guided segmentation in CT images running
MA thesis Improving localization of VL models in CXRs running
MA thesis Leveraging data for improved contrastive loss in CXR classification running
MA thesis Scene detection and automatic scene description – External running
Project 3D detection of Abdominal Trauma in CT images using cross-attention running
MA thesis Dynamic Gap Closure Forecasting in the DAX Index finished
Project Unsupervised detection finished
MA thesis Improved Zero-shot Pathology detection in medical images running
MA thesis Enhancing Breast Abnormality Detection on Mammograms with Advanced Vision-Language Models finished
Project Evaluation of stenosis detection in angiography images finished
Project Comparative Evaluation of Deep Learning Models for Chest X-ray Lesion Detection finished
Project Evaluate Simpleshot: Simple implementation of few-shot classification on CXRs finished
MA thesis Deep-learning based long-tailed multi-label chest X-ray disease classification finished
Project Evaluation of detection performance on CXR dataset using DETR pipeline finished
Project Evaluation of few-shot localization in Chest X-Rays (CXRs) open
MA thesis Improving Few Shot Classification in Chest X-rays finished
Project Review of Zero-shot, Few-shot classification, detection and segmentation methods in Medical Imaging finished
Project Evaluation of MedKLIP for Zero-shot and Fine-tuned classification of CXRs finished
MA thesis Improvements in SSL image-text learnings on CXR images finished
Project AI-Driven Monuments Identification System and its details finished