Segmenting Brain Tissues from Chinese Visible Human Dataset by Deep-Learned Features with Stacked Autoencoder

Trends in DNN Model Based Classification and Segmentation of Brain Tumor Detection

Background:

Due to the complexities of scrutinizing and diagnosing brain tumors from MR images, brain tumor analysis has become one of the most indispensable concerns. Characterization of a brain tumor before any treatment, such as radiotherapy, requires decisive treatment planning and accurate implementation. As a result, early detection of brain tumors is imperative for better clinical outcomes and subsequent patient survival.

Introduction:

Brain tumor segmentation is a crucial task in medical image analysis. Because of tumor heterogeneity and varied intensity patterns, manual segmentation takes a long time, limiting the use of accurate quantitative interventions in clinical practice. Automated computer-based brain tumor image processing has become more valuable with technological advancement. With various imaging and statistical analysis tools, deep learning algorithms offer a viable option to enable health care practitioners to rule out the disease and estimate the growth.

Methods:

This article presents a comprehensive evaluation of conventional machine learning models as well as evolving deep learning techniques for brain tumor segmentation and classification.

Conclusion:

In this manuscript, a hierarchical review has been presented for brain tumor segmentation and detection. It is found that the segmentation methods hold a wide margin of improvement in the context of the implementation of adaptive thresholding and segmentation methods, the feature training and mapping requires redundancy correction, the input data training needs to be more exhaustive and the detection algorithms are required to be robust in terms of handling online input data analysis/tumor detection.

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

Gross Anatomy Education in China during the Covid-19 Pandemic: A National Survey

The Covid-19 pandemic launched the use of online courses in Chinese medical schools during February 2020. To evaluate the state of gross anatomy education in China during the pandemic, a nationwide survey was conducted through convenience sampling by email or respondent invitations on social media. A total of 359 questionnaires were received from the respondents. The first response from a given school was included in the study to represent that school, thus, 77 questionnaires were used for analyses. Schools represented were from all provinces in mainland China as well as Hong Kong and Macao. The survey found that before the pandemic, 74.0% and 33.8% of the 77 schools conducted online theoretical and practical sessions, respectively, on gross anatomy, and 36 (46.8% of 77) had temporarily suspended practical sessions at the time the survey was conducted. Body donation programs were also affected with 26.0% and 27.3% of the 77 schools having suspended donation programs or saw a decreased number of donations. During the pandemic, 40.3% of the 77 schools kept or initiated the implementation of active learning, and online assessment was continued in 49.4% of the 77 medical schools. Another 26 (33.8%) schools initiated online assessment during the pandemic. A total of 359 answers were included for the analysis of the "teachers' perception of the online teaching experience." Over half (51.0%) of the 359 responded teachers were very statisfied or satisfied with the effectiveness of online teaching during the pandemic. A total of 36.2% of these respondents preferred to implement online teaching of theoretical sessions after the pandemic, and 89 (24.8%) teachers were keen to return to traditional face-to-face anatomy education.

Myocardium Detection by Deep SSAE Feature and Within-Class Neighborhood Preserved Support Vector Classifier and Regressor

Automatic detection of left ventricle myocardium is essential to subsequent cardiac image registration and tissue segmentation. However, it is considered challenging mainly because of the complex and varying shape of the myocardium and surrounding tissues across slices and phases. In this study, a hybrid model is proposed to detect myocardium in cardiac magnetic resonance (MR) images combining region proposal and deep feature classification and regression. The model firstly generates candidate regions using new structural similarity-enhanced supervoxel over-segmentation plus hierarchical clustering. Then it adopts a deep stacked sparse autoencoder (SSAE) network to learn the discriminative deep feature to represent the regions. Finally, the features are fed to train a novel nonlinear within-class neighborhood preserved soft margin support vector (C-SVC) classifier and multiple-output support vector (ε-SVR) regressor for refining the location of myocardium. To improve the stability and generalization, the model also takes hard negative sample mining strategy to fine-tune the SSAE and the classifier. The proposed model with impacts of different components were extensively evaluated and compared to related methods on public cardiac data set. Experimental results verified the effectiveness of proposed integrated components, and demonstrated that it was robust in myocardium localization and outperformed the state-of-the-art methods in terms of typical metrics. This study would be beneficial in some cardiac image processing such as region-of-interest cropping and left ventricle volume measurement.

Automatic Vertebrae Localization and Identification by Combining Deep SSAE Contextual Features and Structured Regression Forest

Automatic vertebrae localization and identification in medical computed tomography (CT) scans is of great value for computer-aided spine diseases diagnosis. In order to overcome the disadvantages of the approaches employing hand-crafted, low-level features and based on field-of-view priori assumption of spine structure, an automatic method is proposed to localize and identify vertebrae by combining deep stacked sparse autoencoder (SSAE) contextual features and structured regression forest (SRF). The method employs SSAE to learn image deep contextual features instead of hand-crafted ones by building larger-range input samples to improve their contextual discrimination ability. In the localization and identification stage, it incorporates the SRF model to achieve whole spine localization, then screens those vertebrae within the image, thus relieves the assumption that the part of spine in the field of image is visible. In the end, the output distribution of SRF and spine CT scans properties are assembled to develop a two-stage progressive refining strategy, where the mean-shift kernel density estimation and Otsu method instead of Markov random field (MRF) are adopted to reduce model complexity and refine vertebrae localization results. Extensive evaluation was performed on a challenging data set of 98 spine CT scans. Compared with the hidden Markov model and the method based on convolutional neural network (CNN), the proposed approach could effectively and automatically locate and identify spinal targets in CT scans, and achieve higher localization accuracy, low model complexity, and no need for any assumptions about visual field in CT scans.

Automated Segmentation of Hyperintense Regions in FLAIR MRI Using Deep Learning

We present a deep convolutional neural network application based on autoencoders aimed at segmentation of increased signal regions in fluid-attenuated inversion recovery magnetic resonance imaging images. The convolutional autoencoders were trained on the publicly available Brain Tumor Image Segmentation Benchmark (BRATS) data set, and the accuracy was evaluated on a data set where 3 expert segmentations were available. The simultaneous truth and performance level estimation (STAPLE) algorithm was used to provide the ground truth for comparison, and Dice coefficient, Jaccard coefficient, true positive fraction, and false negative fraction were calculated. The proposed technique was within the interobserver variability with respect to Dice, Jaccard, and true positive fraction. The developed method can be used to produce automatic segmentations of tumor regions corresponding to signal-increased fluid-attenuated inversion recovery regions.