E-grāmata: Applications of Medical Artificial Intelligence: Third International Workshop, AMAI 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings

Exploring CNN and Transformer-based Architectures to Improve Image
Segmentation for Chronic Wound Measurement.- From Pixel Scores to Clinical
Impacts: The Implicit Choices in FROC Metric Design and Their
Consequences.- Head CT Scan Motion Artifact Correction via Diffusion-Based
Generative Models.- SP-NAS: Surgical Phase Recognition-based Navigation
Adjustment System for distal gastrectomy.- Transforming Multimodal Models
into Action Models for Radiotherapy.- Enhanced Interpretability in
Histopathological Images via Combined Tissue and Cell-Level Graph
Analysis.- Targeted Visual Prompting for Medical Visual Question
Answering.- Deep Learning for Resolving 3D Microstructural Changes in the
Fibrotic Liver.- Predicting Falls through Muscle Weakness from a Single Whole
Body Image: A Multimodal Contrastive Learning Framework.- Optimizing ICU
Readmission Prediction: A Comparative Evaluation of AI Tools.- Source
Matters: Source Dataset Impact on Model Robustness in Medical
Imaging.- Evaluating Perceived Workload, Usability and Usefulness of
Artificial Intelligence Systems in Low-Resource Settings: Semi-Automated
Classification and Detection of Community Acquired Pneumonia.- Incremental
Augmentation Strategies for Personalised Continual Learning in Digital
Pathology Contexts.- Assessing Generalization Capabilities of Malaria
Diagnostic Models from Thin Blood Smears.- Automated Feedback System for
Surgical Skill Improvement in Endoscopic Sinus Surgery.- Quantifying Knee
Cartilage Shape and Lesion: From Image to Metrics.- RadImageGAN A
Multi-modal Dataset-Scale Generative AI for Medical Imaging.- Ensemble-KAN:
Leveraging Kolmogorov Arnold Networks to Discriminate Individuals with
Psychiatric Disorders from Controls.- SCIsegV2: A Universal Tool for
Segmentation of Intramedullary Lesions in Spinal Cord Injury.- EHRmonize: A
Framework for Medical Concept Abstraction from Electronic Health Records
using Large Language Models.- Evaluating the Impact of Pulse Oximetry Bias in
Machine Learning under Counterfactual Thinking.- Normative Modeling with
Focal Loss and Adversarial Autoencoders for Alzheimers Disease Diagnosis and
Biomarker Identification.- One-Shot Medical Video Object Segmentation via
Temporal Contrastive Memory Networks.- Data-Efficient Radiology Report
Generation via Similar Report Features Enhancement.