Publications by authors named "M Pakkal"
Article Synopsis
- This study evaluated the effectiveness of ultra-low-dose chest CT (uLDCT) compared to standard low-dose chest CT (LDCT) in detecting fungal infections in immunocompromised patients.
- One hundred patients underwent both types of scans, and three radiologists assessed the image quality and confidence in finding major and minor fungal infection signs.
- The results showed uLDCT achieved high accuracy for detecting fungal disease, notably with an effective dose significantly lower (one quarter) than LDCT, making it a viable option for patients with a BMI under 30.
Rationale: A well-defined curriculum with goals and objectives is an inherent part of every radiology training program.
Materials And Methods: Following a needs assessment, the Canadian Society of Thoracic Radiology Education Committee developed a thoracic imaging curriculum using a mixed- method approach, complimentary to the cardiac curriculum published as a separate document.
Results: The Thoracic Imaging Curriculum consists of two separate yet complimentary parts: a Core Curriculum, aimed at residents in-training, with the main goal of building a strong foundational knowledge, and an Advanced Curriculum, designed to build upon the core knowledge and guide a more in-depth subspecialty training.
Rationale: Well-defined curriculum with goals and objectives is an inherent part of every radiology residency program.
Materials And Methods: Following a needs assessment, the Canadian Society of Thoracic Radiology education committee developed a cardiac imaging curriculum using a mixed method collaborative approach.
Results: The Cardiovascular Imaging Curricula consist each of two separate yet complimentary granular parts: a Core Curriculum, aimed at residents in-training, with the main goal of building a strong foundational knowledge and an Advanced Curriculum, designed to build upon the core knowledge and guide a more in-depth fellowship subspecialty training.
Purpose: Lung cancer screening programs generate a high volume of low-dose computed tomography (LDCT) reports that contain valuable information, typically in a free-text format. High-performance named-entity recognition (NER) models can extract relevant information from these reports automatically for inter-radiologist quality control.
Methods: Using LDCT report data from a longitudinal lung cancer screening program (8,305 reports; 3,124 participants; 2006-2019), we trained a rule-based model and two bidirectional long short-term memory (Bi-LSTM) NER neural network models to detect clinically relevant information from LDCT reports.