Medical imaging has witnessed remarkable progress but usually requires a...
Micro-ultrasound (micro-US) is a novel 29-MHz ultrasound technique that
...
Early diagnosis of prostate cancer significantly improves a patient's 5-...
The Diffusion Probabilistic Model (DPM) has emerged as a highly effectiv...
This paper presents a simple and effective visual prompting method for
a...
Learning medical visual representations directly from paired radiology
r...
Adversarial training (AT) with samples generated by Fast Gradient Sign M...
This paper studies the potential of distilling knowledge from pre-traine...
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component f...
The recent success of Vision Transformers is shaking the long dominance ...
Image pre-training, the current de-facto paradigm for a wide range of vi...
Federated learning (FL) is a distributed learning paradigm that enables
...
Deep neural networks are powerful tools for representation learning, but...
The spleen is one of the most commonly injured solid organs in blunt
abd...
A collection of the accepted abstracts for the Machine Learning for Heal...
Despite the routine use of electronic health record (EHR) data by
radiol...
Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause o...
Batch Normalization (BN) is one of the key components for accelerating
n...
Leveraging temporal information has been regarded as essential for devel...
Although deep neural networks have been a dominant method for many 2D vi...
In this paper, we present a novel unsupervised domain adaptation (UDA)
m...
Non-Local (NL) blocks have been widely studied in various vision tasks.
...
3D Convolution Neural Networks (CNNs) have been widely applied to 3D sce...
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancer...
Tubular structure segmentation in medical images, e.g., segmenting vesse...
In this paper, we study physical adversarial attacks on object detectors...
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancer...
Automatic abnormality detection in abdominal CT scans can help doctors
i...
Trauma is the worldwide leading cause of death and disability in those
y...
Accurate multi-organ abdominal CT segmentation is essential to many clin...
Person re-identification (re-ID) has attracted much attention recently d...
The recent development of adversarial attack has proven that ensemble-ba...
Accurate and robust segmentation of abdominal organs on CT is essential ...
Deep convolutional neural networks (CNNs), especially fully convolutiona...
Multi-organ segmentation is a critical problem in medical image analysis...
Though convolutional neural networks have achieved state-of-the-art
perf...
It is very attractive to formulate vision in terms of pattern theory
Mum...
We aim at segmenting small organs (e.g., the pancreas) from abdominal CT...
Automatic segmentation of an organ and its cystic region is a prerequisi...
It has been well demonstrated that adversarial examples, i.e., natural i...
Deep neural networks have been widely adopted for automatic organ
segmen...