Search Results for author: Sameer Antani

Found 19 papers, 1 papers with code

Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric Chest X-ray images

no code implementations20 Sep 2023 Sivaramakrishnan Rajaraman, Ghada Zamzmi, Feng Yang, Zhaohui Liang, Zhiyun Xue, Sameer Antani

Model initialization techniques are vital for improving the performance and reliability of deep learning models in medical computer vision applications.

Semantically Redundant Training Data Removal and Deep Model Classification Performance: A Study with Chest X-rays

no code implementations18 Sep 2023 Sivaramakrishnan Rajaraman, Ghada Zamzmi, Feng Yang, Zhaohui Liang, Zhiyun Xue, Sameer Antani

Deep learning (DL) has demonstrated its innate capacity to independently learn hierarchical features from complex and multi-dimensional data.

Attribute

Does image resolution impact chest X-ray based fine-grained Tuberculosis-consistent lesion segmentation?

no code implementations10 Jan 2023 Sivaramakrishnan Rajaraman, Feng Yang, Ghada Zamzmi, Zhiyun Xue, Sameer Antani

Literature is sparse in discussing the optimal image resolution to train these models for segmenting the Tuberculosis (TB)-consistent lesions in CXRs.

Lesion Segmentation

Generalizability of Deep Adult Lung Segmentation Models to the Pediatric Population: A Retrospective Study

no code implementations4 Nov 2022 Sivaramakrishnan Rajaraman, Feng Yang, Ghada Zamzmi, Zhiyun Xue, Sameer Antani

In this work, our goal is to (i) analyze the generalizability of deep adult lung segmentation models to the pediatric population and (ii) improve performance through a stage-wise, systematic approach consisting of CXR modality-specific weight initializations, stacked ensembles, and an ensemble of stacked ensembles.

Domain Generalization MS-SSIM +3

Functional Parcellation of fMRI data using multistage k-means clustering

no code implementations19 Feb 2022 Harshit Parmar, Brian Nutter, Rodney Long, Sameer Antani, Sunanda Mitra

Conclusion: The multistage k-means approach can provide functional parcellations of the brain using resting state fMRI data.

Clustering

Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets

no code implementations18 Jan 2022 Anabik Pal, Zhiyun Xue, Sameer Antani

We believe that the present research shows a novel direction in developing criteria-specific custom deep models for cervical image classification by combining images from different sources unlabeled and/or labeled with varying criteria, and addressing image access restrictions.

Classification Image Classification +1

A bone suppression model ensemble to improve COVID-19 detection in chest X-rays

no code implementations5 Nov 2021 Sivaramakrishnan Rajaraman, Gregg Cohen, Lillian Spear, Les Folio, Sameer Antani

It is observed that the bone suppression model ensemble outperformed the individual models in terms of MS-SSIM and other metrics.

MS-SSIM SSIM

Multi-loss ensemble deep learning for chest X-ray classification

no code implementations29 Sep 2021 Sivaramakrishnan Rajaraman, Ghada Zamzmi, Sameer Antani

Currently, the cross-entropy loss remains the de-facto loss function for training deep learning classifiers.

Classification Image Classification +2

Does deep learning model calibration improve performance in class-imbalanced medical image classification?

no code implementations29 Sep 2021 Sivaramakrishnan Rajaraman, Prasanth Ganesan, Sameer Antani

In this study, we perform a systematic analysis of the effect of model calibration on its performance on two medical image modalities, namely, chest X-rays and fundus images, using various deep learning classifier backbones.

Image Classification Medical Image Classification

Trilateral Attention Network for Real-time Medical Image Segmentation

no code implementations17 Jun 2021 Ghada Zamzmi, Vandana Sachdev, Sameer Antani

The performance of the segmentation stage highly relies on the extracted set of spatial features and the receptive fields.

Cardiac Segmentation Image Segmentation +2

Chest X-Ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findings

no code implementations9 Apr 2021 Sivaramakrishnan Rajaraman, Ghada Zamzmi, Les Folio, Philip Alderson, Sameer Antani

However, the presence of bony structures such as ribs and clavicles can obscure subtle abnormalities, resulting in diagnostic errors.

General Classification

Improved Semantic Segmentation of Tuberculosis-consistent findings in Chest X-rays Using Augmented Training of Modality-specific U-Net Models with Weak Localizations

no code implementations21 Feb 2021 Sivaramakrishnan Rajaraman, Les Folio, Jane Dimperio, Philip Alderson, Sameer Antani

We observe that our augmented training strategy helped the CXR modality-specific U-Net models achieve superior performance with test data derived from the TBX11K CXR training distribution as well as from cross-institutional collections (p < 0. 05).

Decision Making Object Localization +2

Synthetic Sample Selection via Reinforcement Learning

no code implementations26 Aug 2020 Jiarong Ye, Yuan Xue, L. Rodney Long, Sameer Antani, Zhiyun Xue, Keith Cheng, Xiaolei Huang

However, the quality control of synthetic images for data augmentation purposes is under-investigated, and some of the generated images are not realistic and may contain misleading features that distort data distribution when mixed with real images.

Data Augmentation Image Classification +2

Unified Representation Learning for Efficient Medical Image Analysis

no code implementations19 Jun 2020 Ghada Zamzmi, Sivaramakrishnan Rajaraman, Sameer Antani

We explore different fine-tuning strategies to demonstrate the impact of the strategy on the performance of target medical image tasks.

General Classification Image Denoising +3

Selective Synthetic Augmentation with Quality Assurance

no code implementations9 Dec 2019 Yuan Xue, Jiarong Ye, Rodney Long, Sameer Antani, Zhiyun Xue, Xiaolei Huang

To mitigate these issues, we investigate a novel data augmentation pipeline that selectively adds new synthetic images generated by conditional Adversarial Networks (cGANs), rather than extending directly the training set with synthetic images.

Classification Data Augmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.