Artificial intelligence innovation in healthcare: Relevance of reporting guidelines for clinical translation from bench to bedside.

Artificial intelligence (AI) and digital innovation are transforming healthcare. Technologies such as machine learning in image analysis, natural language processing in medical chatbots and electronic medical record extraction have the potential to improve screening, diagnostics and prognostication, leading to precision medicine and preventive health. However, it is crucial to ensure that AI research is conducted with scientific rigour to facilitate clinical implementation. Therefore, reporting guidelines have been developed to standardise and streamline the development and validation of AI technologies in health. This commentary proposes a structured approach to utilise these reporting guidelines for the translation of promising AI techniques from research and development into clinical translation, and eventual widespread implementation from bench to bedside.

Development of a multiplex Luminex assay for detecting swine antibodies to structural and nonstructural proteins of foot-and-mouth disease virus in Taiwan.

BACKGROUND/PURPOSE(S): Foot-and-mouth disease (FMD) and swine vesicular disease (SVD) are serious vesicular diseases that have devastated swine populations throughout the world. The aim of this study was to develop a multianalyte profiling (xMAP) Luminex assay for the differential detection of antibodies to the FMD virus of structural proteins (SP) and nonstructural proteins (NSP). METHODS: After the xMAP was optimized, it detected antibodies to SP-VP1 and NSP-3ABC of the FMD virus in a single serum sample. These tests were also compared with 3ABC polypeptide blocking enzyme-linked immunosorbent assay (ELISA) and virus neutralization test (VNT) methods for the differential diagnosis and assessment of immune status, respectively. RESULTS: To detect SP antibodies in 661 sera from infected naïve pigs and vaccinated pigs, the diagnostic sensitivity (DSn) and diagnostic specificity (DSp) of the xMAP were 90.0-98.7% and 93.0-96.5%, respectively. To detect NSP antibodies, the DSn was 90% and the DSp ranged from 93.3% to 99.1%. The xMAP can detect the immune response to SP and NSP as early as 4 days postinfection and 8 days postinfection, respectively. Furthermore, the SP and NSP antibodies in all 15 vaccinated but unprotected pigs were detected by xMAP. A comparison of SP and NSP antibodies detected in the sera of the infected samples indicated that the results from the xMAP had a high positive correlation with results from the VNT and a 3ABC polypeptide blocking ELISA assay. However, simultaneous quantitation detected that xMAP had no relationship with the VNT. Furthermore, the specificity was 93.3-94.9% with 3ABC polypeptide blocking ELISA for the FMDV-NSP antibody. CONCLUSION: The results indicated that xMAP has the potential to detect antibodies to FMDV-SP-VP1 and NSP-3ABC and to distinguish FMDV-infected pigs from pigs infected with the swine vesicular disease virus.

3D Reasoning from Blocks to Stability.

Objects occupy physical space and obey physical laws. To truly understand a scene, we must reason about the space that objects in it occupy, and how each objects is supported stably by each other. In other words, we seek to understand which objects would, if moved, cause other objects to fall. This 3D volumetric reasoning is important for many scene understanding tasks, ranging from segmentation of objects to perception of a rich 3D, physically well-founded, interpretations of the scene. In this paper, we propose a new algorithm to parse a single RGB-D image with 3D block units while jointly reasoning about the segments, volumes, supporting relationships, and object stability. Our algorithm is based on the intuition that a good 3D representation of the scene is one that fits the depth data well, and is a stable, self-supporting arrangement of objects (i.e., one that does not topple). We design an energy function for representing the quality of the block representation based on these properties. Our algorithm fits 3D blocks to the depth values corresponding to image segments, and iteratively optimizes the energy function. Our proposed algorithm is the first to consider stability of objects in complex arrangements for reasoning about the underlying structure of the scene. Experimental results show that our stability-reasoning framework improves RGB-D segmentation and scene volumetric representation.

Tensor total-variation regularized deconvolution kegularlzea ueconvolution for efficient low-dose CT perfusion.

Acute brain diseases such as acute stroke and transit ischemic attacks are the leading causes of mortality and morbidity worldwide, responsible for 9% of total death every year. 'Time is brain' is a widely accepted concept in acute cerebrovascular disease treatment. Efficient and accurate computational framework for hemodynamic parameters estimation can save critical time for thrombolytic therapy. Meanwhile the high level of accumulated radiation dosage due to continuous image acquisition in CT perfusion (CTP) raised concerns on patient safety and public health. However, low-radiation will lead to increased noise and artifacts which require more sophisticated and time-consuming algorithms for robust estimation. We propose a novel efficient framework using tensor total-variation (TTV) regularization to achieve both high efficiency and accuracy in deconvolution for low-dose CTP. The method reduces the necessary radiation dose to only 8% of the original level and outperforms the state-of-art algorithms with estimation error reduced by 40%. It also corrects over-estimation of cerebral blood flow (CBF) and under-estimation of mean transit time (MTT), at both normal and reduced sampling rate. An efficient computational algorithm is proposed to find the solution with fast convergence.

Improving low-dose blood-brain barrier permeability quantification using sparse high-dose induced prior for Patlak model.

Blood-brain barrier permeability (BBBP) measurements extracted from the perfusion computed tomography (PCT) using the Patlak model can be a valuable indicator to predict hemorrhagic transformation in patients with acute stroke. Unfortunately, the standard Patlak model based PCT requires excessive radiation exposure, which raised attention on radiation safety. Minimizing radiation dose is of high value in clinical practice but can degrade the image quality due to the introduced severe noise. The purpose of this work is to construct high quality BBBP maps from low-dose PCT data by using the brain structural similarity between different individuals and the relations between the high- and low-dose maps. The proposed sparse high-dose induced (shd-Patlak) model performs by building a high-dose induced prior for the Patlak model with a set of location adaptive dictionaries, followed by an optimized estimation of BBBP map with the prior regularized Patlak model. Evaluation with the simulated low-dose clinical brain PCT datasets clearly demonstrate that the shd-Patlak model can achieve more significant gains than the standard Patlak model with improved visual quality, higher fidelity to the gold standard and more accurate details for clinical analysis.

Development of a Luminex assay for the detection of swine antibodies to non-structural proteins of foot-and-mouth disease virus.

Foot-and mouth disease (FMD), swine vesicular disease (SVD), and vesicular stomatitis (VS) are highly contagious vesicular diseases of swine but are not easy to differentiate clinically. For the purpose of instant detecting of FMD and differentiating it from the other vesicular diseases, a Luminex assay was developed. Sera from 64 infected, 307 vaccinated, and 280 naïve pigs were tested by the Luminex assay. Diagnostic sensitivity of the assay was 100%. Diagnostic specificity of the assay was 98.7% in vaccinated pigs and 97.5% to 100% in naïve pigs. Agreement between the results from the Luminex assay and those from a 3ABC polypeptide blocking ELISA was 96.3% with kappa statistics of 0.92. The Luminex assay can detect the immune response to NSP-3ABC in swine as early as eight days post-infection. Moreover, all of the 15 vaccinated but unprotected pigs were all detected by the Luminex assay. The results indicated that the Luminex assay has potential with specificity in detecting antibodies to FMDV 3ABC NSP and in distinguishing FMDV-infected pigs from with either SVDV or VSV.

Classification of cerebral lymphomas and glioblastomas featuring luminance distribution analysis.

Differentiating lymphomas and glioblastomas is important for proper treatment planning. A number of works have been proposed but there are still some problems. For example, many works depend on thresholding a single feature value, which is susceptible to noise. In other cases, experienced observers are required to extract the feature values or to provide some interactions with the system. Even if experts are involved, interobserver variance becomes another problem. In addition, most of the works use only one or a few slice(s) because 3D tumor segmentation is time consuming. In this paper, we propose a tumor classification system that analyzes the luminance distribution of the whole tumor region. Typical cases are classified by the luminance range thresholding and the apparent diffusion coefficients (ADC) thresholding. Nontypical cases are classified by a support vector machine (SVM). Most of the processing elements are semiautomatic. Therefore, even novice users can use the system easily and get the same results as experts. The experiments were conducted using 40 MRI datasets. The classification accuracy of the proposed method was 91.1% without the ADC thresholding and 95.4% with the ADC thresholding. On the other hand, the baseline method, the conventional ADC thresholding, yielded only 67.5% accuracy.

Towards robust deconvolution of low-dose perfusion CT: sparse perfusion deconvolution using online dictionary learning.

Computed tomography perfusion (CTP) is an important functional imaging modality in the evaluation of cerebrovascular diseases, particularly in acute stroke and vasospasm. However, the post-processed parametric maps of blood flow tend to be noisy, especially in low-dose CTP, due to the noisy contrast enhancement profile and the oscillatory nature of the results generated by the current computational methods. In this paper, we propose a robust sparse perfusion deconvolution method (SPD) to estimate cerebral blood flow in CTP performed at low radiation dose. We first build a dictionary from high-dose perfusion maps using online dictionary learning and then perform deconvolution-based hemodynamic parameters estimation on the low-dose CTP data. Our method is validated on clinical data of patients with normal and pathological CBF maps. The results show that we achieve superior performance than existing methods, and potentially improve the differentiation between normal and ischemic tissue in the brain.

Tissue-specific sparse deconvolution for low-dose CT perfusion.

Sparse perfusion deconvolution has been recently proposed to effectively improve the image quality and diagnostic accuracy of low-dose perfusion CT by extracting the complementary information from the high-dose perfusion maps to restore the low-dose using a joint spatio-temporal model. However the low-contrast tissue classes where infarct core and ischemic penumbra usually occur in cerebral perfusion CT tend to be over-smoothed, leading to loss of essential biomarkers. In this paper, we extend this line of work by introducing tissue-specific sparse deconvolution to preserve the subtle perfusion information in the low-contrast tissue classes by learning tissue-specific dictionaries for each tissue class, and restore the low-dose perfusion maps by joining the tissue segments reconstructed from the corresponding dictionaries. Extensive validation on clinical datasets of patients with cerebrovascular disease demonstrates the superior performance of our proposed method with the advantage of better differentiation between abnormal and normal tissue in these patients.

Sparsity-based deconvolution of low-dose perfusion CT using learned dictionaries.

Computational tomography perfusion (CTP) is an important functional imaging modality in the evaluation of cerebrovascular diseases, such as stroke and vasospasm. However, the post-processed parametric maps of blood flow tend to be noisy, especially in low-dose CTP, due to the noisy contrast enhancement profile and the oscillatory nature of the results generated by the current computational methods. In this paper, we propose a novel sparsity-base deconvolution method to estimate cerebral blood flow in CTP performed at low-dose. We first built an overcomplete dictionary from high-dose perfusion maps and then performed deconvolution-based hemodynamic parameters estimation on the low-dose CTP data. Our method is validated on a clinical dataset of ischemic patients. The results show that we achieve superior performance than existing methods, and potentially improve the differentiation between normal and ischemic tissue in the brain.

Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models.

Scene understanding includes many related subtasks, such as scene categorization, depth estimation, object detection, etc. Each of these subtasks is often notoriously hard, and state-of-the-art classifiers already exist for many of them. These classifiers operate on the same raw image and provide correlated outputs. It is desirable to have an algorithm that can capture such correlation without requiring any changes to the inner workings of any classifier. We propose Feedback Enabled Cascaded Classification Models (FE-CCM), that jointly optimizes all the subtasks while requiring only a "black box" interface to the original classifier for each subtask. We use a two-layer cascade of classifiers, which are repeated instantiations of the original ones, with the output of the first layer fed into the second layer as input. Our training method involves a feedback step that allows later classifiers to provide earlier classifiers information about which error modes to focus on. We show that our method significantly improves performance in all the subtasks in the domain of scene understanding, where we consider depth estimation, scene categorization, event categorization, object detection, geometric labeling, and saliency detection. Our method also improves performance in two robotic applications: an object-grasping robot and an object-finding robot.

Exploring tiny images: the roles of appearance and contextual information for machine and human object recognition.

Typically, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. In this paper, we explore the roles that appearance and contextual information play in object recognition. Through machine experiments and human studies, we show that the importance of contextual information varies with the quality of the appearance information, such as an image's resolution. Our machine experiments explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. With the use of our context model, our algorithm achieves state-of-the-art performance on the MSRC and Corel data sets. We perform recognition tests for machines and human subjects on low and high resolution images, which vary significantly in the amount of appearance information present, using just the object appearance information, the combination of appearance and context, as well as just context without object appearance information (blind recognition). We also explore the impact of the different sources of context (co-occurrence, relative-location, and relative-scale). We find that the importance of different types of contextual information varies significantly across data sets such as MSRC and PASCAL.

Differentiation of foot-and-mouth disease-infected pigs from vaccinated pigs using antibody-detecting sandwich ELISA.

The presence of serum antibodies for nonstructural proteins of the foot-and-mouth disease virus (FMDV) can differentiate FMDV-infected animals from vaccinated animals. In this study, a sandwich ELISA was developed for rapid detection of the foot-and-mouth disease (FMD) antibodies; it was based on an Escherichia coli-expressed, highly conserved region of the 3ABC nonstructural protein of the FMDV O/TW/99 strain and a monoclonal antibody derived from the expressed protein. The diagnostic sensitivity of the assay was 98.4%, and the diagnostic specificity was 100% for naïve and vaccinated pigs; the detection ability of the assay was comparable those of the PrioCHECK and UBI kits. There was 97.5, 93.4 and 66.6% agreement between the results obtained from our ELISA and those obtained from the PrioCHECK, UBI and CHEKIT kits, respectively. The kappa statistics were 0.95, 0.87 and 0.37, respectively. Moreover, antibodies for nonstructural proteins of the serotypes A, C, Asia 1, SAT 1, SAT 2 and SAT 3 were also detected in bovine sera. Furthermore, the absence of cross-reactions generated by different antibody titers against the swine vesicular disease virus and vesicular stomatitis virus (VSV) was also highlighted in this assay's specificity.

A hierarchical visual model for video object summarization.

We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of windows which possibly contain the object of interest, and then determine which window(s) truly contain the object of interest. Our method enjoys several favorable properties. First, compared to approaches where a single descriptor is used to describe a whole frame, each window's feature descriptor has the chance of genuinely describing the object of interest; hence it is less affected by background clutter. Second, by considering the temporal continuity of a video instead of treating frames as independent, we can hypothesize the location of the windows more accurately. Third, by infusing prior knowledge into the patch-level model, we can precisely follow the trajectory of the object of interest. This allows us to largely reduce the number of windows and hence reduce the chance of overfitting the data during learning. We demonstrate the effectiveness of the method by comparing it to several other semi-supervised learning approaches on challenging video clips.

Reinterpreting the application of gabor filters as a manipulation of the margin in linear support vector machines.

Linear filters are ubiquitously used as a preprocessing step for many classification tasks in computer vision. In particular, applying Gabor filters followed by a classification stage, such as a support vector machine (SVM), is now common practice in computer vision applications like face identity and expression recognition. A fundamental problem occurs, however, with respect to the high dimensionality of the concatenated Gabor filter responses in terms of memory requirements and computational efficiency during training and testing. In this paper, we demonstrate how the preprocessing step of applying a bank of linear filters can be reinterpreted as manipulating the type of margin being maximized within the linear SVM. This new interpretation leads to sizable memory and computational advantages with respect to existing approaches. The reinterpreted formulation turns out to be independent of the number of filters, thereby allowing the examination of the feature spaces derived from arbitrarily large number of linear filters, a hitherto untestable prospect. Further, this new interpretation of filter banks gives new insights, other than the often cited biological motivations, into why the preprocessing of images with filter banks, like Gabor filters, improves classification performance.

Development of a chromatographic strip assay for detection of porcine antibodies to 3ABC non-structural protein of foot-and-mouth disease virus serotype O.

A chromatographic strip assay was developed for rapid detection of serum antibodies to non-structural protein of foot-and-mouth disease virus. The assay was based on Escherichia coli-expressed 3ABC non-structural protein and an immunochromatographic technique, which shortened the detection time to about one hour. The sensitivity of the assay was determined to be 96.8% for infected pigs; its specificity was 100% for naïve pigs and 98.8% for vaccinated pigs. In the experimentally infected pigs, anti-3ABC antibodies were detectable from eight days post-infection until the end of the study, 34 days post-infection. The performance of this assay was comparable to that of two commercial ELISA kits, Ceditest FMDV-NS and UBI FMDV NS EIA, and was better than that of CHEKIT FMD-3ABC po. Given its advantages of instant testing and quantitative measurement, this assay has potential as a useful tool for rapid on-farm diagnosis of foot-and-mouth disease.

Development of a reverse transcription multiplex real-time PCR for the detection and genotyping of classical swine fever virus.

A reverse transcription multiplex real-time PCR (RT-MRT-PCR) was developed for rapid detection and genotyping of classical swine fever virus (CSFV). The universal primers and specific TaqMan probes for each of the three genotypes, genotypes 1, 2, and 3, were designed within the 3'-UTR of the CSFV. Non-CSFV swine virus and clinical samples from specific pathogen-free (SPF) pigs were both demonstrated to be CSFV-negative by RT-MRT-PCR. The diagnostic sensitivity of RT-MRT-PCR was determined to be 1 viral copy/microl for each genotype of standard plasmid. For the analytical sensitivity experiment, 100 samples of 14 CSFV genotype 1 strains and 86 samples from CSFV outbreak farms were all detected as CSFV-positive by RT-MRT-PCR, and the genotype results were consistent with the results of sequencing from a previous study. The intra-assay and inter-assay variations of RT-MRT-PCR were below 3% in all experiments. The sensitivity of RT-MRT-PCR was the same as the reverse transcription nested PCR (RT-nPCR) and higher than reverse transcription PCR (RT-PCR) and viral isolation from clinical samples. This assay was used further to evaluate the duration of viremia of wild-type CSFV in vaccinated exposed pigs. The results indicated that pigs vaccinated with the E2 subunit vaccine had longer viremia than pigs given the C-strain vaccine, which is compatible with the findings of previous studies. Thus, the new RT-MRT-PCR is a rapid, reproducible, sensitive, and specific genotyping tool for CSFV detection.

The Painful Face - Pain Expression Recognition Using Active Appearance Models.

Pain is typically assessed by patient self-report. Self-reported pain, however, is difficult to interpret and may be impaired or in some circumstances (i.e., young children and the severely ill) not even possible. To circumvent these problems behavioral scientists have identified reliable and valid facial indicators of pain. Hitherto, these methods have required manual measurement by highly skilled human observers. In this paper we explore an approach for automatically recognizing acute pain without the need for human observers. Specifically, our study was restricted to automatically detecting pain in adult patients with rotator cuff injuries. The system employed video input of the patients as they moved their affected and unaffected shoulder. Two types of ground truth were considered. Sequence-level ground truth consisted of Likert-type ratings by skilled observers. Frame-level ground truth was calculated from presence/absence and intensity of facial actions previously associated with pain. Active appearance models (AAM) were used to decouple shape and appearance in the digitized face images. Support vector machines (SVM) were compared for several representations from the AAM and of ground truth of varying granularity. We explored two questions pertinent to the construction, design and development of automatic pain detection systems. First, at what level (i.e., sequence- or frame-level) should datasets be labeled in order to obtain satisfactory automatic pain detection performance? Second, how important is it, at both levels of labeling, that we non-rigidly register the face?

A subspace model-based approach to face relighting under unknown lighting and poses.

We present a new approach to face relighting by jointly estimating the pose, reflectance functions, and lighting from as few as one image of a face. Upon such estimation, we can synthesize the face image under any prescribed new lighting condition. In contrast to commonly used face shape models or shape-dependent models, we neither recover nor assume the 3-D face shape during the estimation process. Instead, we train a pose- and pixel-dependent subspace model of the reflectance function using a face database that contains samples of pose and illumination for a large number of individuals (e.g., the CMU PIE database and the Yale database). Using this subspace model, we can estimate the pose, the reflectance functions, and the lighting condition of any given face image. Our approach lends itself to practical applications thanks to many desirable properties, including the preservation of the non-Lambertian skin reflectance properties and facial hair, as well as reproduction of various shadows on the face. Extensive experiments show that, compared to recent representative face relighting techniques, our method successfully produces better results, in terms of subjective and objective quality, without reconstructing a 3-D shape.