Publications by authors named "Fakrul Islam Tushar"
In this paper, we introduce a novel concordance-based predictive uncertainty (CPU)-Index, which integrates insights from subgroup analysis and personalized AI time-to-event models. Through its application in refining lung cancer screening (LCS) predictions generated by an individualized AI time-to-event model trained with fused data of low dose CT (LDCT) radiomics with patient demographics, we demonstrate its effectiveness, resulting in improved risk assessment compared to the Lung CT Screening Reporting & Data System (Lung-RADS). Subgroup-based Lung-RADS faces challenges in representing individual variations and relies on a limited set of predefined characteristics, resulting in variable predictions.
View Article and Find Full Text PDFImportance: Clinical imaging trials are crucial for evaluation of medical innovations, but the process is inefficient, expensive, and ethically-constrained. Virtual imaging trial (VIT) approach addresses these limitations by emulating the components of a clinical trial. An rendition of the National Lung Screening Trial (NCLS) via Virtual Lung Screening Trial (VLST) demonstrates the promise of VITs to expedite clinical trials, reduce risks to subjects, and facilitate the optimal use of imaging technologies in clinical settings.
View Article and Find Full Text PDFArticle Synopsis
- The study aims to enhance AI systems for detecting various abnormalities in CT scans by creating efficient, automated multi-label annotators to reduce reliance on manual annotation.
- The researchers developed rule-based algorithms to extract disease information from radiology reports for three organ systems and used attention-guided RNNs to improve classification accuracy.
- Results showed high accuracy in the manual validation of the algorithms, and automated models successfully analyzed over 261,000 reports, demonstrating the potential for improved disease detection with AI.
Article Synopsis
- The study aimed to create classifiers for identifying multiple diseases in body CT scans, using labels automatically extracted from radiology reports across three organ systems: lungs, liver, and kidneys.
- It involved analyzing over 12,000 patient CT scans from 2012 to 2017 and utilized a 3D DenseVNet model to segment organs and classify disease presence or absence.
- Results showed high accuracy in the label extraction and AUC values for the classifiers, indicating effectiveness in diagnosing various conditions like emphysema and kidney stones across the different organ systems.
Background And Objective: Automatic 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 their variability in color, texture, and shapes and indistinguishable boundaries.
Methods: Through this study, we present a new and automatic semantic segmentation network for robust skin lesion segmentation named Dermoscopic Skin Network (DSNet).