Biomedical Image Segmentation via Representative Annotation

Deep learning has been applied successfully to many biomedical image segmentation tasks. However, due to the diversity and complexity of biomedical image data, manual annotation for training common deep learning models is very timeconsuming and labor-intensive, especially because normally only biomedical experts can annotate image data well. Human experts are often involved in a long and iterative process of annotation, as in active learning type annotation schemes. In this paper, we propose representative annotation (RA), a new deep learning framework for reducing annotation effort in biomedical image segmentation. RA uses unsupervised networks for feature extraction and selects representative image patches for annotation in the latent space of learned feature descriptors, which implicitly characterizes the underlying data while minimizing redundancy. A fully convolutional network (FCN) is then trained using the annotated selected image patches for image segmentation. Our RA scheme offers three compelling advantages: (1) It leverages the ability of deep neural networks to learn better representations of image data; (2) it performs one-shot selection for manual annotation and frees annotators from the iterative process of common active learning based annotation schemes; (3) it can be deployed to 3D images with simple extensions. We evaluate our RA approach using three datasets (two 2D and one 3D) and show our framework yields competitive segmentation results comparing with state-of-the-art methods.

Download Full-text

PyConvU-Net: a lightweight and multiscale network for biomedical image segmentation

BMC Bioinformatics ◽

10.1186/s12859-020-03943-2 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Changyong Li ◽

Yongxian Fan ◽

Xiaodong Cai

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

State Of The Art ◽

Experimental Results ◽

Actual Situation ◽

Controlled Experiments ◽

Biomedical Image ◽

Segmentation Methods ◽

Art Performance

Abstract Background With the development of deep learning (DL), more and more methods based on deep learning are proposed and achieve state-of-the-art performance in biomedical image segmentation. However, these methods are usually complex and require the support of powerful computing resources. According to the actual situation, it is impractical that we use huge computing resources in clinical situations. Thus, it is significant to develop accurate DL based biomedical image segmentation methods which depend on resources-constraint computing. Results A lightweight and multiscale network called PyConvU-Net is proposed to potentially work with low-resources computing. Through strictly controlled experiments, PyConvU-Net predictions have a good performance on three biomedical image segmentation tasks with the fewest parameters. Conclusions Our experimental results preliminarily demonstrate the potential of proposed PyConvU-Net in biomedical image segmentation with resources-constraint computing.

Download Full-text

Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation

Medical Image Computing and Computer Assisted Intervention − MICCAI 2017 - Lecture Notes in Computer Science ◽

10.1007/978-3-319-66179-7_46 ◽

2017 ◽

pp. 399-407 ◽

Cited By ~ 89

Author(s):

Lin Yang ◽

Yizhe Zhang ◽

Jianxu Chen ◽

Siyuan Zhang ◽

Danny Z. Chen

Keyword(s):

Image Segmentation ◽

Active Learning ◽

Biomedical Image ◽

Learning Framework

Download Full-text

Performance Analysis of Deep Learning Models for Biomedical Image Segmentation

Deep Learning for Biomedical Applications ◽

10.1201/9780367855611-5 ◽

2021 ◽

pp. 83-100

Author(s):

T. K. Saj Sachin ◽

V. Sowmya ◽

K. P. Soman

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Performance Analysis ◽

Learning Models ◽

Biomedical Image

Download Full-text

DDeep3M: Docker-powered deep learning for biomedical image segmentation

Journal of Neuroscience Methods ◽

10.1016/j.jneumeth.2020.108804 ◽

2020 ◽

Vol 342 ◽

pp. 108804

Author(s):

Xinglong Wu ◽

Shangbin Chen ◽

Jin Huang ◽

Anan Li ◽

Rong Xiao ◽

...

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Biomedical Image

Download Full-text

A New Ensemble Learning Framework for 3D Biomedical Image Segmentation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015909 ◽

2019 ◽

Vol 33 ◽

pp. 5909-5916 ◽

Cited By ~ 6

Author(s):

Hao Zheng ◽

Yizhe Zhang ◽

Lin Yang ◽

Peixian Liang ◽

Zhuo Zhao ◽

...

Keyword(s):

Image Segmentation ◽

Ensemble Learning ◽

State Of The Art ◽

3D Models ◽

Superior Performance ◽

3D Image ◽

Convolutional Network ◽

Biomedical Image ◽

Learning Framework ◽

2D And 3D

3D image segmentation plays an important role in biomedical image analysis. Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. Yet, 2D and 3D models have their own strengths and weaknesses, and by unifying them together, one may be able to achieve more accurate results. In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models. First, we develop a fully convolutional network based meta-learner to learn how to improve the results from 2D and 3D models (base-learners). Then, to minimize over-fitting for our sophisticated meta-learner, we devise a new training method that uses the results of the baselearners as multiple versions of “ground truths”. Furthermore, since our new meta-learner training scheme does not depend on manual annotation, it can utilize abundant unlabeled 3D image data to further improve the model. Extensive experiments on two public datasets (the HVSMR 2016 Challenge dataset and the mouse piriform cortex dataset) show that our approach is effective under fully-supervised, semisupervised, and transductive settings, and attains superior performance over state-of-the-art image segmentation methods.

Download Full-text

Exploitation of deep learning in the automatic detection of cracks on paved roads

GEOMATICA ◽

10.1139/geomat-2019-0008 ◽

2019 ◽

Vol 73 (2) ◽

pp. 29-44

Author(s):

Won Mo Jung ◽

Faizaan Naveed ◽

Baoxin Hu ◽

Jianguo Wang ◽

Ningyuan Li

Keyword(s):

Deep Learning ◽

State Of The Art ◽

Ground Truth ◽

Learning Networks ◽

Test Image ◽

Convolutional Network ◽

Image Patches ◽

Severity Levels ◽

First Time ◽

Different Levels

With the advance of deep learning networks, their applications in the assessment of pavement conditions are gaining more attention. A convolutional neural network (CNN) is the most commonly used network in image classification. In terms of pavement assessment, most existing CNNs are designed to only distinguish between cracks and non-cracks. Few networks classify cracks in different levels of severity. Information on the severity of pavement cracks is critical for pavement repair services. In this study, the state-of-the-art CNN used in the detection of pavement cracks was improved to localize the cracks and identify their distress levels based on three categories (low, medium, and high). In addition, a fully convolutional network (FCN) was, for the first time, utilized in the detection of pavement cracks. These designed architectures were validated using the data acquired on four highways in Ontario, Canada, and compared with the ground truth that was provided by the Ministry of Transportation of Ontario (MTO). The results showed that with the improved CNN, the prediction precision on a series of test image patches were 72.9%, 73.9%, and 73.1% for cracks with the severity levels of low, medium, and high, respectively. The precision for the FCN was tested on whole pavement images, resulting in 62.8%, 63.3%, and 66.4%, respectively, for cracks with the severity levels of low, medium, and high. It is worth mentioning that the ground truth contained some uncertainties, which partially contributed to the relatively low precision.

Download Full-text

Biomedical Image Segmentation and Analysis in Deep Learning

10.53901/nmhw0hk324f ◽

2021 ◽

Vol 2 (1) ◽

Author(s):

Tuan Anh Tran ◽

Tien Dung Cao ◽

Vu-Khanh Tran ◽

◽

Keyword(s):

Deep Learning ◽

Image Data ◽

Patient Treatment ◽

Biomedical Data ◽

Biomedical Image Processing ◽

Human Organ ◽

Biomedical Image ◽

Breast Segmentation ◽

Effective Diagnosis ◽

Disease Analysis

Biomedical Image Processing, such as human organ segmentation and disease analysis, is a modern ﬁeld in medicine development and patient treatment. Besides there are many kinds of image formats, the diversity and complexity of biomedical data is still a big issue to all of researchers in their applications. In order to deal with the problem, deep learning give us a successful and effective solutions. Unet and LSTM are two general approaches to the most of case of medical image data. While Unet helps to teach a machine in learning data from each image accompanied with its labelled information, LSTM helps to remember states from many slices of images by times. Unet gives us the segmentation of tumor, abnormal things from biomedical images and then the LSTM gives us the effective diagnosis on a patient disease. In this paper, we show some scenarios of using Unets and LSTM to segment and analysis on many kinds of human organ images and results of brain, retinal, skin, lung and breast segmentation.

Download Full-text

Systematic comparison of incomplete-supervision approaches for biomedical imaging classification

10.21203/rs.3.rs-798207/v1 ◽

2021 ◽

Author(s):

Sayedali Shetab Boushehri ◽

Ahmad Qasim ◽

Dominik Waibel ◽

Fabian Schmich ◽

Carsten Marr

Keyword(s):

Active Learning ◽

Supervised Learning ◽

Learning Algorithms ◽

Image Data ◽

Classification Performance ◽

Natural Image ◽

Training Methods ◽

Training Strategy ◽

Biomedical Image ◽

Model Training

Abstract Deep learning based classification of biomedical images requires manual annotation by experts, which is time-consuming and expensive. Incomplete-supervision approaches including active learning, pre-training and semi-supervised learning address this issue and aim to increase classification performance with a limited number of annotated images. Up to now, these approaches have been mostly benchmarked on natural image datasets, where image complexity and class balance typically differ considerably from biomedical classification tasks. In addition, it is not clear how to combine them to improve classification performance on biomedical image data. We thus performed an extensive grid search combining seven active learning algorithms, three pre-training methods and two training strategies as well as respective baselines (random sampling, random initialization, and supervised learning). For four biomedical datasets, we started training with 1% of labeled data and increased it by 5% iteratively, using 4-fold cross-validation in each cycle. We found that the contribution of pre-training and semi-supervised learning can reach up to 20% macro F1-score in each cycle. In contrast, the state-of-the-art active learning algorithms contribute less than 5% to macro F1-score in each cycle. Based on performance, implementation ease and computation requirements, we recommend the combination of BADGE active learning, ImageNet-weights pre-training, and pseudo-labeling as training strategy, which reached over 90% of fully supervised results with only 25% of annotated data for three out of four datasets. We believe that our study is an important step towards annotation and resource efficient model training for biomedical classification challenges.

Download Full-text