Luyang Luo
YOU?
Author Swipe
View article: Large-scale generative tumor synthesis in computed tomography images for improving tumor recognition
Large-scale generative tumor synthesis in computed tomography images for improving tumor recognition Open
AI-driven tumor recognition unlocks new possibilities for precise tumor screening and diagnosis. However, the progress is heavily hampered by the scarcity of annotated datasets, demanding extensive efforts by radiologists. To this end, we …
View article: Voice-guided Orchestrated Intelligence for Clinical Evaluation (VOICE): A Voice AI Agent System for Prehospital Stroke Assessment
Voice-guided Orchestrated Intelligence for Clinical Evaluation (VOICE): A Voice AI Agent System for Prehospital Stroke Assessment Open
We developed a voice-driven artificial intelligence (AI) system that guides anyone - from paramedics to family members - through expert-level stroke evaluations using natural conversation, while also enabling smartphone video capture of ke…
View article: A large model for non-invasive and personalized management of breast cancer from multiparametric MRI
A large model for non-invasive and personalized management of breast cancer from multiparametric MRI Open
Breast Magnetic Resonance Imaging (MRI) demonstrates the highest sensitivity for breast cancer detection among imaging modalities and is standard practice for high-risk women. Interpreting the multi-sequence MRI is time-consuming and prone…
View article: Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation
Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation Open
Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To…
View article: HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification Open
Fine-grained classification of whole slide images (WSIs) is essential in precision oncology, enabling precise cancer diagnosis and personalized treatment strategies. The core of this task involves distinguishing subtle morphological variat…
View article: Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks
Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks Open
The increasing demand for transparent and reliable models, particularly in high-stakes decision-making areas such as medical image analysis, has led to the emergence of eXplainable Artificial Intelligence (XAI). Post-hoc XAI techniques, wh…
View article: SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition
SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition Open
Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed by video fine-tuning" for high-dimensional video data inevit…
View article: Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition
Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition Open
Existing state-of-the-art methods for surgical phase recognition either rely on the extraction of spatial-temporal features at a short-range temporal resolution or adopt the sequential extraction of the spatial and temporal features across…
View article: Multimodal Data Integration for Precision Oncology: Challenges and Future Directions
Multimodal Data Integration for Precision Oncology: Challenges and Future Directions Open
The essence of precision oncology lies in its commitment to tailor targeted treatments and care measures to each patient based on the individual characteristics of the tumor. The inherent heterogeneity of tumors necessitates gathering info…
View article: Development and validation of an interpretable model integrating multimodal information for improving ovarian cancer diagnosis
Development and validation of an interpretable model integrating multimodal information for improving ovarian cancer diagnosis Open
Ovarian cancer, a group of heterogeneous diseases, presents with extensive characteristics with the highest mortality among gynecological malignancies. Accurate and early diagnosis of ovarian cancer is of great significance. Here, we prese…
View article: MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment Open
Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis. However, the stringent trustworthiness requirements intrinsic to the medical field have catalyzed research into the utilization…
View article: XCoOp: Explainable Prompt Learning for Computer-Aided Diagnosis via Concept-guided Context Optimization
XCoOp: Explainable Prompt Learning for Computer-Aided Diagnosis via Concept-guided Context Optimization Open
Utilizing potent representations of the large vision-language models (VLMs) to accomplish various downstream tasks has attracted increasing attention. Within this research field, soft prompt learning has become a representative approach fo…
View article: Medical Image Debiasing by Learning Adaptive Agreement from a Biased Council
Medical Image Debiasing by Learning Adaptive Agreement from a Biased Council Open
Deep learning could be prone to learning shortcuts raised by dataset bias and result in inaccurate, unreliable, and unfair models, which impedes its adoption in real-world clinical applications. Despite its significance, there is a dearth …
View article: MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment Open
Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis. However, the stringent trustworthiness requirements intrinsic to the medical field have catalyzed research into the utilization…
View article: Iterative Semi-Supervised Learning for Abdominal Organs and Tumor Segmentation
Iterative Semi-Supervised Learning for Abdominal Organs and Tumor Segmentation Open
Deep-learning (DL) based methods are playing an important role in the task of abdominal organs and tumors segmentation in CT scans. However, the large requirements of annotated datasets heavily limit its development. The FLARE23 challenge …
View article: Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images
Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images Open
Deep learning (DL)-based rib fracture detection has shown promise of playing an important role in preventing mortality and improving patient outcome. Normally, developing DL-based object detection models requires a huge amount of bounding …
View article: Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder
Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder Open
Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses t…
View article: Scale-aware Super-resolution Network with Dual Affinity Learning for Lesion Segmentation from Medical Images
Scale-aware Super-resolution Network with Dual Affinity Learning for Lesion Segmentation from Medical Images Open
Convolutional Neural Networks (CNNs) have shown remarkable progress in medical image segmentation. However, lesion segmentation remains a challenge to state-of-the-art CNN-based algorithms due to the variance in scales and shapes. On the o…
View article: Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning–based Radiograph Diagnosis: A Multicenter Study
Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning–based Radiograph Diagnosis: A Multicenter Study Open
Fine-grained annotations overcame shortcut learning and enabled DL models to identify correct lesion patterns, improving the generalizability of the models.Keywords: Computer-aided Diagnosis, Conventional Radiography, Convolutional Neural …
View article: Rethinking annotation granularity for overcoming deep shortcut learning: A retrospective study on chest radiographs.
Rethinking annotation granularity for overcoming deep shortcut learning: A retrospective study on chest radiographs. Open
Deep learning has demonstrated radiograph screening performances that are comparable or superior to radiologists. However, recent studies show that deep models for thoracic disease classification usually show degraded performance when appl…
View article: OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays
OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays Open
Chest X-ray (CXR) is the most typical diagnostic X-ray examination for screening various thoracic diseases. Automatically localizing lesions from CXR is promising for alleviating radiologists' reading burden. However, CXR datasets are ofte…
View article: Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images
Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images Open
The novel coronavirus disease 2019 (COVID-19) characterized by atypical pneumonia has caused millions of deaths worldwide. Automatically segmenting lesions from chest Computed Tomography (CT) is a promising way to assist doctors in COVID-1…
View article: Deep Mining External Imperfect Data for Chest X-ray Disease Screening
Deep Mining External Imperfect Data for Chest X-ray Disease Screening Open
Deep learning approaches have demonstrated remarkable progress in automatic Chest X-ray analysis. The data-driven feature of deep models requires training data to cover a large distribution. Therefore, it is substantial to integrate knowle…
View article: Unifying Structure Analysis and Surrogate-driven Function Regression for Glaucoma OCT Image Screening
Unifying Structure Analysis and Surrogate-driven Function Regression for Glaucoma OCT Image Screening Open
Optical Coherence Tomography (OCT) imaging plays an important role in glaucoma diagnosis in clinical practice. Early detection and timely treatment can prevent glaucoma patients from permanent vision loss. However, only a dearth of automat…
View article: Deep Angular Embedding and Feature Correlation Attention for Breast MRI Cancer Analysis
Deep Angular Embedding and Feature Correlation Attention for Breast MRI Cancer Analysis Open
Accurate and automatic analysis of breast MRI plays an important role in early diagnosis and successful treatment planning for breast cancer. Due to the heterogeneity nature, accurate diagnosis of tumors remains a challenging task. In this…