Deep Learning- and Expert Knowledge-Based Feature Extraction and Performance Evaluation in Breast Histopathology Images

Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers.

A Bit-Tracking Knowledge-Based Query Tree for RFID Tag Identification in IoT Systems

In an IoT (Internet of Things) system where each IoT device has one/many RFID tags, there might be many RFID tags. However, when multiple tags respond to the reader’s interrogation at the same time, their signals collide. Due to the collision, the reader must request the colliding tags to retransmit their IDs, resulting in higher communication overhead and longer identification time. Therefore, this paper presents a Bit-tracking Knowledge-based Query Tree (BKQT), which uses two techniques: knowledge, which stores all the tag IDs that can possibly occur, and bit tracking, which allows the reader to detect the locations of the collided bits in a collision slot. BKQT constructs a query tree for all possible tags, called a k-tree, by using knowledge while it constructs bit-collision cases and the corresponding actions for each node in this k-tree by using bit tracking. In the identification process, BKQT traverses this constructed k-tree and thus identifies the colliding tags faster by taking the actions according to the happening bit-collision cases. From the simulation results, BKQT can improve the identification time by 44.3%, 46.4%, and 25.1%, compared with the previous knowledge-based protocols, Knowledge Query Tree (KQT), Heuristic Query Tree (H-QT), Query Tree with Shortcutting and Couple Resolution (QTSC), respectively.

Combined strategy of knowledge-based rule selection and historical data percentile-based range determination to improve an autoverification system for clinical chemistry test results

Background

Current autoverification, which is only knowledge‐based, has low efficiency. Regular historical data analysis may improve autoverification range determination. We attempted to enhance autoverification by selecting autoverification rules by knowledge and ranges from historical data. This new system was compared with the original knowledge‐based system.

Methods

New types of rules, extreme values, and consistency checks were added and the autoverification workflow was rearranged to construct a framework. Criteria for creating rules for extreme value ranges, limit checks, consistency checks, and delta checks were determined by analyzing historical Zhongshan laboratory data. The new system's effectiveness was evaluated using pooled data from 20 centers. Efficiency improvement was assessed by a multicenter process.

Results

Effectiveness was evaluated by the true positive rate, true negative rate, and overall consistency rate, as compared to manual verification, which were 77.55%, 78.53%, and 78.3%, respectively for the new system. The original overall consistency rate was 56.2%. The new pass rates, indicating efficiency, were increased by 19%‒51% among hospitals. Further customization using individualized data increased this rate.

Conclusions

The improved system showed a comparable effectiveness and markedly increased efficiency. This transferable system could be further improved and popularized by utilizing historical data from each hospital.

Coordinating Shared Tasks in Human-Robot Collaboration by Commands

Human-robot collaboration is gaining more and more interest in industrial settings, as collaborative robots are considered safe and robot actions can be programmed easily by, for example, physical interaction. Despite this, robot programming mostly focuses on automated robot motions and interactive tasks or coordination between human and robot still requires additional developments. For example, the selection of which tasks or actions a robot should do next might not be known beforehand or might change at the last moment. Within a human-robot collaborative setting, the coordination of complex shared tasks, is therefore more suited to a human, where a robot would act upon requested commands.In this work we explore the utilization of commands to coordinate a shared task between a human and a robot, in a shared work space. Based on a known set of higher-level actions (e.g., pick-and-placement, hand-over, kitting) and the commands that trigger them, both a speech-based and graphical command-based interface are developed to investigate its use. While speech-based interaction might be more intuitive for coordination, in industrial settings background sounds and noise might hinder its capabilities. The graphical command-based interface circumvents this, while still demonstrating the capabilities of coordination. The developed architecture follows a knowledge-based approach, where the actions available to the robot are checked at runtime whether they suit the task and the current state of the world. Experimental results on industrially relevant assembly, kitting and hand-over tasks in a laboratory setting demonstrate that graphical command-based and speech-based coordination with high-level commands is effective for collaboration between a human and a robot.

Knowledge-based dose prediction models to inform gynecologic brachytherapy needle supplementation for locally advanced cervical cancer

PURPOSE

The use of interstitial needles, combined with intracavitary applicators, enables customized dose distributions and is beneficial for complex cases, but increases procedure time. Overall, applicator selection is not standardized and depends on physician expertise and preference. The purpose of this study is to determine whether dose prediction models can guide needle supplementation decision-making for cervical cancer.

MATERIALS AND METHODS

Intracavitary knowledge-based models for organ-at-risk (OAR) dose estimation were trained and validated for tandem-and-ring/ovoids (T&R/T&O) implants. Models were applied to hybrid cases with 1-3 implanted needles to predict OAR dose without needles. As a reference, 70/67 hybrid T&R/T&O cases were replanned without needles, following a standardized procedure guided by dose predictions. If a replanned dose exceeded the dose objective, the case was categorized as requiring needles. Receiver operating characteristic (ROC) curves of needle classification accuracy were generated. Optimal classification thresholds were determined from the Youden Index.

RESULTS

Needle supplementation reduced dose to OARs. However, 67%/39% of replans for T&R/T&O met all dose constraints without needles. The ROC for T&R/T&O models had an area-under-curve of 0.89/0.86, proving high classification accuracy. The optimal threshold of 99%/101% of the dose limit for T&R/T&O resulted in classification sensitivity and specificity of 78%/86% and 85%/78%.

CONCLUSIONS

Needle supplementation reduced OAR dose for most cases but was not always required to meet standard dose objectives, particularly for T&R cases. Our knowledge-based dose prediction model accurately identified cases that could have met constraints without needle supplementation, suggesting that such models may be beneficial for applicator selection.

Replacing Manual Planning of Whole Breast Irradiation With Knowledge-Based Automatic Optimization by Virtual Tangential-Fields Arc Therapy

Purpose

To implement Knowledge Based (KB) automatic planning for right and left-sided whole breast treatment through a new volumetric technique (ViTAT, Virtual Tangential-fields Arc Therapy) mimicking conventional tangential fields (TF) irradiation.

Materials and Method

A total of 193 clinical plans delivering TF with wedged or field-in-field beams were selected to train two KB-models for right(R) and left(L) sided breast cancer patients using the RapidPlan (RP) tool implemented in the Varian Eclipse system. Then, a template for ViTAT optimization, incorporating individual KB-optimized constraints, was interactively fine-tuned. ViTAT plans consisted of four arcs (6 MV) with start/stop angles consistent with the TF geometry variability within our population; the delivery was completely blocked along the arcs, apart from the first and last 20° of rotation for each arc. Optimized fine-tuned KB templates for automatic plan optimization were generated. Validation tests were performed on 60 new patients equally divided in R and L breast treatment: KB automatic ViTAT-plans (KB-ViTAT) were compared against the original TF plans in terms of OARs/PTVs dose-volume parameters. Wilcoxon-tests were used to assess the statistically significant differences.

Results

KB models were successfully generated for both L and R sides. Overall, 1(3%) and 7(23%) out of 30 automatic KB-ViTAT plans were unacceptable compared to TF for R and L side, respectively. After the manual refinement of the start/stop angles, KB-ViTAT plans well fitted TF-performances for these patients as well. PTV coverage was comparable, while PTV D_1% was improved with KB-ViTAT by R:0.4/L:0.2 Gy (p < 0.05); ipsilateral OARs D_mean were similar with a slight (i.e., few % volume) improvement/worsening in the 15–35 Gy/2–15 Gy range, respectively. KB-ViTAT better spared contralateral OARs: D_mean of contralateral OARs was 0.1 Gy lower (p < 0.05); integral dose was R:5%/L:8% lower (p < 0.05) than TF. The overall time for the automatic plan optimization and final dose calculation was 12 ± 2 minutes.

Conclusions

Fully automatic KB-optimization of ViTAT can efficiently replace manually optimized TF planning for whole breast irradiation. This approach was clinically implemented in our institute and may be suggested as a large-scale strategy for efficiently replacing manual planning with large sparing of time, elimination of inter-planner variability and of, seldomly occurring, sub-optimal manual plans.

Applying Answer Set Programming for Knowledge-Based Link Prediction on Social Interaction Networks

Link prediction targets the prediction of possible future links in a social network, i. e., we aim to predict the next most likely links of the network given the current state. However, predicting the future solely based on (scarce) historic data is often challenging. In this paper, we investigate, if we can make use of additional (domain) knowledge to tackle this problem. For this purpose, we apply answer set programming (ASP) for formalizing the domain knowledge for social network (and graph) analysis. In particular, we investigate link prediction via ASP based on node proximity and its enhancement with background knowledge, in order to test intuitions that common features, e. g., a common educational background of students, imply common interests. In addition, then the applied ASP formalism enables explanation-aware prediction approaches.

A knowledge-based approach to automated planning for hepatocellular carcinoma

PURPOSE

To build a knowledge-based model of liver cancer for Auto-Planning, a function in Pinnacle, which is used as an automated inverse intensity modulated radiation therapy (IMRT) planning system.

METHODS AND MATERIALS

Fifty Tomotherapy patients were enrolled to extract the dose-volume histograms (DVHs) information and construct the protocol for Auto-Planning model. Twenty more patients were chosen additionally to test the model. Manual planning and automatic planning were performed blindly for all twenty test patients with the same machine and treatment planning system. The dose distributions of target and organs at risks (OARs), along with the working time for planning, were evaluated.

RESULTS

Statistically significant results showed that automated plans performed better in target conformity index (CI) while mean target dose was 0.5 Gy higher than manual plans. The differences between target homogeneity indexes (HI) of the two methods were not statistically significant. Additionally, the doses of normal liver, left kidney, and small bowel were significantly reduced with automated plan. Particularly, mean dose and V15 of normal liver were 1.4 Gy and 40.5 cc lower with automated plans respectively. Mean doses of left kidney and small bowel were reduced with automated plans by 1.2 Gy and 2.1 Gy respectively. In contrast, working time was also significantly reduced with automated planning.

CONCLUSIONS

Auto-Planning shows availability and effectiveness in our knowledge-based model for liver cancer.

Knowledge-based entropies improve the identification of native protein structures

Evaluating protein structures requires reliable free energies with good estimates of both potential energies and entropies. Although there are many demonstrated successes from using knowledge-based potential energies, computing entropies of proteins has lagged far behind. Here we take an entirely different approach and evaluate knowledge-based conformational entropies of proteins based on the observed frequencies of contact changes between amino acids in a set of 167 diverse proteins, each of which has two alternative structures. The results show that charged and polar interactions break more often than hydrophobic pairs. This pattern correlates strongly with the average solvent exposure of amino acids in globular proteins, as well as with polarity indices and the sizes of the amino acids. Knowledge-based entropies are derived by using the inverse Boltzmann relationship, in a manner analogous to the way that knowledge-based potentials have been extracted. Including these new knowledge-based entropies almost doubles the performance of knowledge-based potentials in selecting the native protein structures from decoy sets. Beyond the overall energy-entropy compensation, a similar compensation is seen for individual pairs of interacting amino acids. The entropies in this report have immediate applications for 3D structure prediction, protein model assessment, and protein engineering and design.

ITScorePro: an efficient scoring program for evaluating the energy scores of protein structures for structure prediction

One important component in protein structure prediction is to evaluate the free energy of a given conformation. Given the enormous number of possible conformations for a sequence, it is extremely challenging to quickly and accurately score the energies of these conformations and predict a reasonable structure within a practical computational time. Here, we describe an efficient program for energy evaluation, referred to as ITScorePro (Copyright © 2012). The energy scoring function in the ITScorePro program is based on the distance-dependent, pairwise atomic potentials for protein structure prediction that we recently derived by using statistical mechanics principles (Huang and Zou, Proteins 79:2648-2661, 2011). ITScorePro is a stand-alone program and can also be easily implemented in other software suites for protein structure prediction.

Statistical mechanics-based method to extract atomic distance-dependent potentials from protein structures

In this study, we have developed a statistical mechanics-based iterative method to extract statistical atomic interaction potentials from known, nonredundant protein structures. Our method circumvents the long-standing reference state problem in deriving traditional knowledge-based scoring functions, by using rapid iterations through a physical, global convergence function. The rapid convergence of this physics-based method, unlike other parameter optimization methods, warrants the feasibility of deriving distance-dependent, all-atom statistical potentials to keep the scoring accuracy. The derived potentials, referred to as ITScore/Pro, have been validated using three diverse benchmarks: the high-resolution decoy set, the AMBER benchmark decoy set, and the CASP8 decoy set. Significant improvement in performance has been achieved. Finally, comparisons between the potentials of our model and potentials of a knowledge-based scoring function with a randomized reference state have revealed the reason for the better performance of our scoring function, which could provide useful insight into the development of other physical scoring functions. The potentials developed in this study are generally applicable for structural selection in protein structure prediction.

Consistent refinement of submitted models at CASP using a knowledge-based potential

Protein structure refinement is an important but unsolved problem; it must be solved if we are to predict biological function that is very sensitive to structural details. Specifically, critical assessment of techniques for protein structure prediction (CASP) shows that the accuracy of predictions in the comparative modeling category is often worse than that of the template on which the homology model is based. Here we describe a refinement protocol that is able to consistently refine submitted predictions for all categories at CASP7. The protocol uses direct energy minimization of the knowledge-based potential of mean force that is based on the interaction statistics of 167 atom types (Summa and Levitt, Proc Natl Acad Sci USA 2007; 104:3177-3182). Our protocol is thus computationally very efficient; it only takes a few minutes of CPU time to run typical protein models (300 residues). We observe an average structural improvement of 1% in GDT_TS, for predictions that have low and medium homology to known PDB structures (Global Distance Test score or GDT_TS between 50 and 80%). We also observe a marked improvement in the stereochemistry of the models. The level of improvement varies amongst the various participants at CASP, but we see large improvements (>10% increase in GDT_TS) even for models predicted by the best performing groups at CASP7. In addition, our protocol consistently improved the best predicted models in the refinement category at CASP7 and CASP8. These improvements in structure and stereochemistry prove the usefulness of our computationally inexpensive, powerful and automatic refinement protocol.

Integrating information from existing databases for enhanced function annotation of genes, genomes and networks

Uncovering functional associations for genes and gene products remains one of the most significant challenges in biology. The classical approaches, such as homology detection, are mainly suited for predicting approximate molecular function of a protein and should be used in context with other methods. Several studies have emerged that employ knowledge-based procedures to extract functional data for genes from a variety of biological sources. However, data derived from a single biological resource often provides only a limited perspective on their functional associations largely due to systematic bias in the underlying data. The post-genomic era has witnessed the emergence of knowledge-based studies that aim to decipher functional associations by combining several biological evidence types. These are expected to provide better insights into the functional aspects of diverse genes, genomes and networks.