Jinzheng Cai

Jinzheng Cai

Auto-generated profile, based on publicly available information

Jinzheng Cai

PAII Inc., Bethesda, MD 20817, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2019 in Medical Image Analysis
Verified
Journal Article
Closed access
JCJinzheng Cai
Jinzheng Cai
ZZZizhao Zhang
Zizhao Zhang
LCLei Cui
Lei Cui
YZYefeng Zheng
Yefeng Zheng
LYLin Yang
Lin Yang

28 December 2020 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
KYKe Yan
Ke Yan
JCJinzheng Cai
Jinzheng Cai
YZYoujing Zheng
Youjing Zheng
AHAdam P Harrison
Adam P Harrison
DJDakai Jin
Dakai Jin
LLLe Lu
Le Lu
Large-scale datasets with high-quality labels are desired for training accurate deep learning models. However, due to the annotation cost, datasets in medical imaging are often either partially-labeled or small. For example, DeepLesion is such a large-scale CT image dataset with lesions of various types, but it also has many unlabeled lesions (missing annotations). When training a lesion detector on a partially-labeled dataset, the missing annotations will generate incorrect negative signals and degrade the performance. Besides DeepLesion, there are several small single-type datasets, such as LUNA for lung nodules and LiTS for liver tumors. These datasets have heterogeneous label scopes, i.e., different lesion types are labeled in different datasets with other types ignored. In this work, we aim to develop a universal lesion detection algorithm to detect a variety of lesions. The problem of heterogeneous and partial labels is tackled. First, we build a simple yet effective lesion detection framework named Lesion ENSemble (LENS). LENS can efficiently learn from multiple heterogeneous lesion datasets in a multi-task fashion and leverage their synergy by proposal fusion. Next, we propose strategies to mine missing annotations from partially-labeled datasets by exploiting clinical prior knowledge and cross-dataset knowledge transfer. Finally, we train our framework on four public lesion datasets and evaluate it on 800 manually-labeled sub-volumes in DeepLesion. Our method brings a relative improvement of 49% compared to the current state-of-the-art approach in the metric of average sensitivity. We have publicly released our manual 3D annotations of DeepLesion in.

13 September 2018
Verified
Book Chapter
Closed access
PDF file
JCJinzheng Cai
Jinzheng Cai
YTYoubao Tang
Youbao Tang
LLLe Lu
Le Lu
AHAdam P Harrison
Adam P Harrison
KYKe Yan
Ke Yan
RSRonald M. Summers
Ronald M. Summers

18 September 2018 in Pattern Recognition
Verified
Journal Article
Closed access
JCJinzheng Cai
Jinzheng Cai
FXFuyong Xing
Fuyong Xing
ABAbhinandan Batra
Abhinandan Batra
FLFujun Liu
Fujun Liu
GWGlenn A. Walter
Glenn A. Walter
LYLin Yang
Lin Yang

26 September 2018
Verified
Book Chapter
Closed access
PDF file
JCJinzheng Cai
Jinzheng Cai
LLLe Lu
Le Lu
AHAdam P Harrison
Adam P Harrison
XSXiaoshuang Shi
Xiaoshuang Shi
Pingjun ChenPingjun Chen
Pingjun Chen
LYLin Yang
Lin Yang

7 September 2020 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
JCJinzheng Cai
Jinzheng Cai
AHAdam P Harrison
Adam P Harrison
YZYoujing Zheng
Youjing Zheng
KYKe Yan
Ke Yan
YHYuankai Huo
Yuankai Huo
LLLe Lu
Le Lu
The acquisition of large-scale medical image data, necessary for training machine learning algorithms, is hampered by associated expert-driven annotation costs. Mining hospital archives can address this problem, but labels often incomplete or noisy, e.g., 50% of the lesions in DeepLesion are left unlabeled. Thus, effective label harvesting methods are critical. This is the goal of our work, where we introduce Lesion-Harvester—a powerful system to harvest missing annotations from lesion datasets at high precision. Accepting the need for some degree of expert labor, we use a small fully-labeled image subset to intelligently mine annotations from the remainder. To do this, we chain together a highly sensitive lesion proposal generator (LPG) and a very selective lesion proposal classifier (LPC). Using a new hard negative suppression loss, the resulting harvested and hard-negative proposals are then employed to iteratively finetune our LPG. While our framework is generic, we optimize our performance by proposing a new 3D contextual LPG and by using a global-local multi-view LPC. Experiments on DeepLesion demonstrate that Lesion- Harvester can discover an additional 9; 805 lesions at a precision of 90%. We publicly release the harvested lesions, along with a new test set of completely annotated DeepLesion volumes. We also present a pseudo 3D IoU evaluation metric that corresponds much better to the real 3D IoU than current DeepLesion evaluation metrics. To quantify the downstream benefits of Lesion-Harvester we show that augmenting the DeepLesion annotations with our harvested lesions allows state-of-the-art detectors to boost their average precision by 7 to 10%.