Seminar September 12TH, 2023

Diego Hernando  

Title: Quantitative Diffusion MRI of the Abdomen

Abstract: Diffusion MRI has enormous potential and utility in the evaluation of various abdominal and pelvic disease processes including cancer and noncancer imaging of the liver, prostate, and other organs. Quantitative diffusion MRI is based on acquisitions with multiple diffusion encodings followed by quantitative mapping of diffusion parameters that are sensitive to tissue microstructure. Compared to qualitative diffusion-weighted MRI, quantitative diffusion MRI can improve standardization of tissue characterization as needed for disease detection, staging, and treatment monitoring. However, similar to many other quantitative MRI methods, diffusion MRI faces multiple challenges including acquisition artifacts, signal modeling limitations, and biological variability. In abdominal and pelvic diffusion MRI, technical acquisition challenges include physiologic motion (respiratory, peristaltic, and pulsatile), image distortions, and low signal-to-noise ratio. If unaddressed, these challenges lead to poor technical performance (bias and precision) and clinical outcomes of quantitative diffusion MRI. Emerging and novel technical developments seek to address these challenges and may enable reliable quantitative diffusion MRI of the abdomen and pelvis. Through systematic validation in phantoms, volunteers, and patients, including multicenter studies to assess reproducibility, these emerging techniques may finally demonstrate the potential of quantitative diffusion MRI for abdominal and pelvic imaging applications.

Bio: Diego Hernando is an Associate Professor in the Departments of Radiology and Medical Physics at the University of Wisconsin. He is originally from Valladolid, Spain, where he attended college with a focus in Telecommunication Engineering. At the University of Wisconsin, Diego is the Director of quantitative body MRI in the Department of Radiology and leads an active NIH-funded research group devoted to the development and translational validation of quantitative imaging techniques. Diego is particularly interested in contributing to the transformation of MRI into a truly quantitative imaging modality. By measuring physically meaningful properties of tissue, his group aims to develop quantitative imaging biomarkers to improve the detection, staging and treatment monitoring of various diseases.

Francisco Madariaga  

Title: Guiding Visual Attention with Language Specification for chest x-ray anomaly classification.

Abstract: Efforts to tackle highly imbalanced classification tasks in healthcare have been numerous, especially in the realm of radiological chest x-ray report generation—a persistently challenging task. This undertaking comprises two phases: firstly, the detection of an anomaly within the chest x-ray and secondly, leveraging that classification to generate a free-text radiological report. To address the anomaly detection, this research proposes the use of a novel framework named "Guiding visual Attention with Language Specification" (GALS). GALS uniquely employs a which use a high-level language specification as advice to drive the classification evidence to task-relevant features while minimizing attention to distractors. Subsequently, this technique supervises the classifier's spatial attention to improve precision in identifying relevant features and ignore distracting context.

Bio: Industrial Engineer graduated from the University of Concepción. His interest in the field of artificial intelligence led him to pursue the Diploma in Artificial Intelligence at the Pontificia Universidad Católica de Chile. Currently, he continues to deepen his knowledge as a master's student in Engineering Sciences, with a mention in Computer Science at the same university, where he researches the automatic generation of radiological reports from medical imaging.