Scholars@Duke
Fakrul Islam Tushar

Selected Publications

Automatic quality control in computed tomography volumes segmentation using a small set of XCAT as reference images

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2023 Deep learning methods have performed superiorly to segment organs of interest from Computed Tomography images than traditional methods. However, the trained models do not generalize well at the inference phase, and manual validation and correction are not ... Full text Cite

Multi-label annotation of text reports from computed tomography of the chest, abdomen, and pelvis using deep learning.

Journal Article BMC Med Inform Decis Mak · April 15, 2022 BACKGROUND: There is progress to be made in building artificially intelligent systems to detect abnormalities that are not only accurate but can handle the true breadth of findings that radiologists encounter in body (chest, abdomen, and pelvis) computed t ... Full text Open Access Link to item Cite

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning.

Journal Article Radiol Artif Intell · January 2022 PURPOSE: To design multidisease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports. MATERIALS AND METHODS: This retrospective study included a total of 12 092 patients (mean age, ... Full text Link to item Cite

Quality or quantity: toward a unified approach for multi-organ segmentation in body CT

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2022 Organ segmentation of medical images is a key step in virtual imaging trials. However, organ segmentation datasets are limited in in terms of quality (because labels cover only a few organs) and quantity (since case numbers are limited). In this study, we ... Full text Cite

Virtual versus reality: external validation of COVID-19 classifiers using XCAT phantoms for chest radiography

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2022 Many published studies use deep learning models to predict COVID-19 from chest x-ray (CXR) images, often reporting high performances. However, the models do not generalize well on independent external testing. Common limitations include the lack of medical ... Full text Cite

Virtual vs. reality: External validation of COVID-19 classifiers using XCAT phantoms for chest computed tomography

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2022 Research studies of artificial intelligence models in medical imaging have been hampered by poor generalization. This problem has been especially concerning over the last year with numerous applications of deep learning for COVID-19 diagnosis. Virtual imag ... Full text Cite

Co-occurring diseases heavily influence the performance of weakly supervised learning models for classification of chest CT

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2022 Despite the potential of weakly supervised learning to automatically annotate massive amounts of data, little is known about its limitations for use in computer-aided diagnosis (CAD). For CT specifically, interpreting the performance of CAD algorithms can ... Full text Cite

Multi-Label Annotation of Chest Abdomen Pelvis Computed Tomography Text Reports Using Deep Learning

Journal Article · February 4, 2021 Purpose: To develop high throughput multi-label annotators for body (chest, abdomen, and pelvis) Computed Tomography (CT) reports that can be applied across a variety of abnormalities, organs, and disease states. Approach: We used a dictionary approach t ... Link to item Cite

DSNet: Automatic dermoscopic skin lesion segmentation.

Journal Article Computers in biology and medicine · May 2020 Background and objectiveAutomatic segmentation of skin lesions is considered a crucial step in Computer-aided Diagnosis (CAD) systems for melanoma detection. Despite its significance, skin lesion segmentation remains an unsolved challenge due to t ... Full text Cite

Weakly supervised 3D classification of chest CT using aggregated multi-resolution deep segmentation features

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2020 Weakly supervised disease classification of CT imaging suffers from poor localization owing to case-level annotations, where even a positive scan can hold hundreds to thousands of negative slices along multiple planes. Furthermore, although deep learning s ... Full text Cite

Attention-guided classification of abnormalities in semi-structured computed tomography reports

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2020 Lack of annotated data is a major challenge to machine learning algorithms, particularly in the field of radiology. Algorithms that can efficiently extract labels in a fast and precise manner are in high demand. Weak supervision is a compromise solution, p ... Full text Cite

Brain Tissue Segmentation Using NeuroNet With Different Pre-processing Techniques

Conference 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR) · May 2019 Full text Cite

Classification of chest CT using case-level weak supervision

Conference Progress in Biomedical Optics and Imaging - Proceedings of SPIE · January 1, 2019 Our goal is to investigate using only case-level labels extracted automatically from radiology reports to construct a multi-disease classifier for CT scans with deep learning method. We chose four lung diseases as a start: atelectasis, pulmonary edema, nod ... Full text Cite