This tutorial presents explainable information retrieval (ExIR), an emerging area focused on fostering responsible and trustworthy deployment of machine learning systems in the context of information retrieval. As the field has rapidly evolved in the past 4-5 years, numerous approaches have been proposed that focus on different access modes, stakeholders, and model development stages. This tutorial aims to introduce IR-centric notions, classification, and evaluation styles in ExIR, while focusing on IR-specific tasks such as ranking, text classification, and learning-to-rank systems. We will delve into method families and their adaptations to IR, extensively covering post-hoc methods, axiomatic and probing approaches, and recent advances in interpretability-by-design approaches. We will also discuss ExIR applications for different stakeholders, such as researchers, practitioners, and end-users, in contexts like web search, patent and legal search, and high-stakes decision-making tasks. To facilitate practical understanding, we will provide a hands-on session on applying ExIR methods, reducing the entry barrier for students, researchers, and practitioners alike.

@en

Predicting pediatric spinal deformity (PSD) from X-ray images collected on the patient’s initial visit is a challenging task. This work builds on our previous method and provides a novel bio-informed framework based on a mechanistic machine learning technique with dynamic patient-specific parameters to predict PSD. We provide a geometry-based bone growth model that can be utilized in a range of applications to enhance the bio-informed mechanistic machine learning framework. The proposed technique is utilized to examine and predict spine curvature in PSD cases such as adolescent idiopathic scoliosis. The best fit of a segmented 3D volumetric geometry of the human spine acquired from 2D X-ray images is employed. Using an active contour model based on gradient vector flow snakes, the anteroposterior and lateral views of the X-ray images are segmented to derive the 2D contours surrounding each vertebra. Using minimal user input, the snake parameters are calibrated and automatically computed over the dataset, resulting in fast image segmentation and data collection. The 2D segmented outlines of each vertebra are transformed into a 3D image segmentation result. The Iterative Closest Point mesh registration technique is then used to establish a mesh morphing approach and creates a 3D atlas spine model. Using the comprehensive 3D volumetric model, one can automatically extract spinal geometry data as inputs to the mechanistic machine learning network. Moreover, the proposed bio-informed deep learning network with the modified bone growth model achieves competitive or even superior performance against other state-of-the-art learning-based methods.Please check and confirm if the author names and initials are correct for “Yongjie Jessica Zhang” and “Wing Kam Liu”.We confirm they are correct.

@en

Scoliosis, an abnormal curvature of the human spinal column, is characterized by a lateral deviation of the spine, accompanied by axial rotation of the vertebrae. Adolescent Idiopathic Scoliosis (AIS) is the most common type, affecting children between ages 8 to 18 when bone growth is at its maximum rate. We propose a mechanistic machine learning algorithm in order to study patient-specific AIS curve progression, which is associated with the bone growth and other genetic and environmental factors. Two different frameworks are used to analyse and predict curve progression, one with implementing clinical data extracted from 2D X-ray images and the other one with incorporating both clinical data and physical equations governing the non-uniform bone growth. The physical equations governing bone growth are affiliated with calculating all stress components at each region. The stress values are evaluated through a surrogate finite element simulation and a bone growth model on a detailed patient-specific geometry of the human spine. We also propose a patient-specific framework to generate the volumetric model of human spine which is partitioned into different tissues for both vertebra and intervertebral disc. It is shown that implementing physical equations governing bone growth into the prediction framework will notably improve the prediction results as compared to only using clinical data for prediction. In addition, we can predict curve progression at ages outside the range of training samples.@en