Deepta Rajan

Deepta Rajan
IBM Research · Multimodal Analytics

About

22
Publications
1,689
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
342
Citations
Additional affiliations
June 2015 - November 2018
IBM Research
Position
  • Researcher

Publications

Publications (22)
Article
Full-text available
The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this c...
Preprint
Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models. Commonly referred to as counterfactuals, the synthesized explanations are required to contain discernible changes (for easy interpretability) while also...
Preprint
Full-text available
Artificial intelligence methods such as deep neural networks promise unprecedented capabilities in healthcare, from diagnosing diseases to prescribing treatments. While this can eventually produce a valuable suite of tools for automating clinical workflows, a critical step forward is to ensure that the predictive models are reliable and to enable a...
Preprint
Full-text available
With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence. Existing approaches for ensuring the distribution of model pre...
Chapter
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. In supervised and semi-supervised learning, prediction calibration has emerged as a key technique to achieve improved generalization and...
Article
Full-text available
Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and eff...
Preprint
Full-text available
Automated diagnostic assistants in healthcare necessitate accurate AI models that can be trained with limited labeled data, can cope with severe class imbalances and can support simultaneous prediction of multiple disease conditions. To this end, we present a novel few-shot learning approach that utilizes a number of key components to enable robust...
Preprint
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is often addressed by incorporating uncertainty quantification strategies, the latter challenge is addressed using...
Preprint
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar to heteroscedastic neural networks that produce var...
Preprint
Full-text available
The hypothesis that computational models can be reliable enough to be adopted in prognosis and patient care is revolutionizing healthcare. Deep learning, in particular, has been a game changer in building predictive models, thereby leading to community-wide data curation efforts. However, due to the inherent variabilities in population characterist...
Conference Paper
Processing temporal sequences is central to a variety of applications in health care, and in particular multichannel Electrocardiogram (ECG) is a highly prevalent diagnostic modality that relies on robust sequence modeling. While Recurrent Neural Networks (RNNs) have led to significant advances in automated diagnosis with time-series data, they per...
Article
Full-text available
Processing temporal sequences is central to a variety of applications in health care, and in particular multi-channel Electrocardiogram (ECG) is a highly prevalent diagnostic modality that relies on robust sequence modeling. While Recurrent Neural Networks (RNNs) have led to significant advances in automated diagnosis with time-series data, they pe...
Conference Paper
Full-text available
With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Recurrent Neural Network (RNN) architectures with Long Short-Term Memory (LSTM) units, deep neural networks have achieved state-of-the-art results in several clinical predic...
Article
Full-text available
With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Recurrent Neural Network (RNN) architectures with Long Short-Term Memory (LSTM) units, deep neural networks have achieved state-of-the-art results in several clinical predic...
Article
The objective of this project is to develop and design mobile content for introducing engineering technology to high school students. More specifically, we intend to work on a sequence of modules that will establish connections between high school mathematics and physics to modern technologies associated with smart phones, iPods and other high-tech...
Conference Paper
The recent sensing capabilities of mobile devices along with their interactivity and popularity in the student community can be used to create a unique learning environment in engineering education. Android Java-DSP (AJDSP) is a mobile educational application that interfaces with sensors and enables simulation and visualization of signal processing...
Conference Paper
By exploiting the interactivity and processing power of mobile technologies, an immersive learning experience can be created. iJDSP and AJDSP are mobile graphical programming applications for simulation and visualization of signal processing concepts, developed to complement instruction to students from the STEM fields. In this paper, the enhanced...
Conference Paper
Full-text available
Internet and multimedia technologies have had a profound impact in STEM education in the past decade. The increase in the use of mobile devices among students adds another novel dimension to course design and delivery. Furthermore, the traditional textbooks are being replaced and supplemented by inexpensive and mobile e-books, and hence there is an...
Article
Full-text available
In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from MR images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain magnetic resonance images considering their intensit...
Conference Paper
In this paper, we describe a pixel based approach for automated segmentation of tumor components from MR images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. Since it is trivial to obtain sparse codes for pixel values, we propose to consider their non-linear similarities...

Network

Cited By

Projects