Lung and pancreatic tumor characterization in the deep learning era: novel supervised and unsupervised learning approaches

S Hussein, P Kandel, CW Bolan… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Risk stratification (characterization) of tumors from radiology images can be more accurate
and faster with computer-aided diagnosis (CAD) tools. Tumor characterization through such …

Highly accurate model for prediction of lung nodule malignancy with CT scans

JL Causey, J Zhang, S Ma, B Jiang, JA Qualls… - Scientific reports, 2018 - nature.com
Computed tomography (CT) examinations are commonly used to predict lung nodule
malignancy in patients, which are shown to improve noninvasive early diagnosis of lung …

FUIQA: fetal ultrasound image quality assessment with deep convolutional networks

L Wu, JZ Cheng, S Li, B Lei, T Wang… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
The quality of ultrasound (US) images for the obstetric examination is crucial for accurate
biometric measurement. However, manual quality control is a labor intensive process and …

Risk stratification of lung nodules using 3D CNN-based multi-task learning

S Hussein, K Cao, Q Song, U Bagci - … , IPMI 2017, Boone, NC, USA, June …, 2017 - Springer
Risk stratification of lung nodules is a task of primary importance in lung cancer diagnosis.
Any improvement in robust and accurate nodule characterization can assist in identifying …

Dense deconvolutional network for skin lesion segmentation

H Li, X He, F Zhou, Z Yu, D Ni, S Chen… - IEEE journal of …, 2018 - ieeexplore.ieee.org
Automatic delineation of skin lesion contours from dermoscopy images is a basic step in the
process of diagnosis and treatment of skin lesions. However, it is a challenging task due to …

Multi-task deep model with margin ranking loss for lung nodule analysis

L Liu, Q Dou, H Chen, J Qin… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Lung cancer is the leading cause of cancer deaths worldwide and early diagnosis of lung
nodule is of great importance for therapeutic treatment and saving lives. Automated lung …

Ultrasound standard plane detection using a composite neural network framework

H Chen, L Wu, Q Dou, J Qin, S Li… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Ultrasound (US) imaging is a widely used screening tool for obstetric examination and
diagnosis. Accurate acquisition of fetal standard planes with key anatomical structures is …

Class-specific mutual information variation for feature selection

W Gao, L Hu, P Zhang - Pattern Recognition, 2018 - Elsevier
Feature selection plays a critical role in pattern recognition. Feature selection aims to
eliminate irrelevant and redundant features. A drawback of traditional feature selection …

Automatic scoring of multiple semantic attributes with multi-task feature leverage: a study on pulmonary nodules in CT images

S Chen, J Qin, X Ji, B Lei, T Wang, D Ni… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
The gap between the computational and semantic features is the one of major factors that
bottlenecks the computer-aided diagnosis (CAD) performance from clinical usage. To bridge …

Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels

FJS Bragman, R Tanno, S Ourselin… - Proceedings of the …, 2019 - openaccess.thecvf.com
The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on
the design of feature sharing between tasks within the architecture. The number of possible …