Meta Ordinal Regression Forest for Medical Image Classification With Ordinal Labels

The performance of medical image classification has been enhanced by deep convolutional neural networks(CNNs),which are typically trained with cross-entropy(CE)loss.However,when the label presents an intrinsic ordinal property in nature,e.g.,the development from benign to malignant tumor,CE loss cannot take into account such ordinal information to allow for better generalization.To improve model generalization with ordinal information,we propose a novel meta ordinal regression forest(MORF)method for medical image classification with ordinal labels,which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning framework.The merits of the proposed MORF come from the following two components:A tree-wise weighting net(TWW-Net)and a grouped feature selection(GFS)module.First,the TWW-Net assigns each tree in the forest with a specific weight that is mapped from the classification loss of the corresponding tree.Hence,all the trees possess varying weights,which is helpful for alleviating the tree-wise prediction variance.Second,the GFS module enables a dynamic forest rather than a fixed one that was previously used,allowing for random feature perturbation.During training,we alternatively optimize the parameters of the CNN backbone and TWW-Net in the meta-learning framework through calculating the Hessian matrix.Experimental results on two medical image classification datasets with ordinal labels,i.e.,LIDC-IDRI and Breast Ultrasound datasets,demonstrate the superior performances of our MORF method over existing state-of-the-art methods.

Using the hierarchical ordinal regression model to analyse the intensity of urinary schistosomiasis infection in school children in Lusaka Province,Zambia

Background:Urinary schistosomiasis has been a major public health problem in Zambia for many years.However,the disease profile may vary in different locale due to the changing ecosystem that contributes to the risk of acquiring the disease.The objective of this study was to quantify risk factors associated with the intensity of urinary schistosomiasis infection in school children in Lusaka Province,Zambia,in order to better understand local transmission.Methods:Data were obtained from 1912 school children,in 20 communities,in the districts of Luangwa and Kafue in Lusaka Province.Both individual-and community-level covariates were incorporated into an ordinal logistic regression model to predict the probability of an infection being a certain intensity in a three-category outcome response:0=no infection,1=light infection,and 2=moderate/heavy infection.Random effects were introduced to capture unobserved heterogeneity.Results:Overall,the risk of urinary schistosomiasis was strongly associated with age,altitude at which the child lived,and sex.Weak associations were observed with the normalized difference vegetation index,maximum temperature,and snail abundance.Detailed analysis indicated that the association between infection intensities and age and altitude were category-specific.Particularly,infection intensity was lower in children aged between 5 and 9 years compared to those aged 10 to 15 years(OR=0.72,95%CI=0.51-0.99).However,the age-specific risk changed at different levels of infection,such that when comparing children with light infection to those who were not infected,age was associated with a lower odds(category 1 vs category 0:OR=0.71,95%CI:0.50-0.99),yet such a relation was not significant when considering children who were moderately or heavily infected compared to those with a light or no infection(category 2 vs category 0:OR=0.96,95%CI:0.45-1.64).Overall,we observed that children living in the valley were less likely to acquire urinary schistosomiasis compared to those living in plateau areas(OR=0.48,95%CI:0.16-0.71).However,category-specific effects showed no significant association in category 1(light infection),whereas in category 2(moderate/high infection),the risk was still significantly lower for those living in the valley compared to those living in plateau areas(OR=0.18,95%CI:0.04-0.75).Conclusions:This study demonstrates the importance of understanding the dynamics and heterogeneity of infection in control efforts,and further suggests that apart from the well-researched factors of Schistosoma intensity,various other factors influence transmission.Control programmes need to take into consideration the varying infection intensities of the disease so that effective interventions can be designed.

Does Hospital Ownership Influence Hand Hygiene Compliance?

The issue as to whether hospital ownership has an impact on the quality of care has long been a serious concern. Hand hygiene（HH） compliance is regarded as an important indicator of the quality of care in the control of hospital-acquired infections. However, little information is available on whether hospital ownership influences HH compliance. In this study, of 229 hospitals selected from Hubei province in China, 152 were public and 77 were private hospitals. A total of 23 652 healthcare workers（HCWs） were surveyed, using a convenience sampling. HH compliance, the WHO＇s ＂My Five Moments for hand hygiene＂（5 MHH）, among HCWs, together with the factors of hospital ownership, training frequency, bed occupancy rates, etc. were collected. Univariate analysis and ordinal logistic regression analysis were used to analyze factors affecting HH compliance. Overall, HH compliance rates were 67% and 79% for public and private hospitals, respectively. The HH compliance rates of HCWs and 5 MHH were between 55% and 95%, and influenced by hospital ownership（P〈0.05）, excluding compliance rate at the moment after body fluid exposure, and other influence factors included training frequency and bed occupancy rate（P〈0.05）. HH compliance is better in private than in public hospitals. Hospital ownership is a significant factor affecting HH compliance, in addition to training frequency and bed occupancy rate.

Multivariate Analyses for Finding Significant Track Irregularities to Generate an Optimal Track Maintenance Schedule

We first discuss the relationship between the optimal track maintenance scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displacement (LLID). The results of applying the cluster analysis technique to the sampling data showed that maintenance operation is required for approximately 10% of the total lots, and these lots were further classified into three groups according to the degree of maintenance need. To analyze the background factors for detecting abnormal LLID lots, a principal component analysis was performed;the results showed that the first principal component represents LLIDs from the viewpoints of the rail structure, equipment, and operating conditions. Binomial and ordinal logit regression models (LRMs) were used to quantitatively investigate the determinants of abnormal LLIDs. Binomial LRM was used to characterize the abnormal LLIDs, whereas ordinal LRM was used to distinguish the degree of influence of factors that are considered to have a significant impact on LLIDs.

Ordinal-Class Core Vector Machine

Ordinal regression is one of the most important tasks of relation learning, and several techniques based on support vector machines （SVMs） have also been proposed for tackling it, but the scalability aspect of these approaches to handle large datasets still needs much of exploration. In this paper, we will extend the recent proposed algorithm Core Vector Machine （CVM） to the ordinal-class data, and propose a new algorithm named as Ordinal-Class Core Vector Machine （OCVM）. Similar with CVM, its asymptotic time complexity is linear with the number of training samples, while the space complexity is independent with the number of training samples. We also give some analysis for OCVM, which mainly includes two parts, the first one shows that OCVM can guarantee that the biases are unique and properly ordered under some situation; the second one illustrates the approximate convergence of the solution from the viewpoints of objective function and KKT conditions. Experiments on several synthetic and real world datasets demonstrate that OCVM scales well with the size of the dataset and can achieve comparable generalization performance with existing SVM implementations.

Visual perception on the architectural elements of the built heritage of a historic temple town： A case study of Kumbakonam, India

This paper aims to investigate the changes in the virtual perception on the built heritage at the traditional core setttement of Kumbakonam Town at Tamitnadu and to analyze their implica- tions. Specifically, the major objectives of the study are （1） to identify the architectural elements that manifest the built heritage of Kumbakonam Town and （2） to assess the contMbutions of these elements to the changes in the visuat perception of the town. To achieve these objectives, this study adopts an empirical model that analyzes the architectural elements of the buildings in the study area. Direct observations and documentations of 373 buildings are collected to analyze those etements that contribute to the changes in the visual perception on the built heritage of Kumbakonam Town. An ordinary regression model is used to examine the characteristics of the built heritage across the chariot processional route of the town. Several architectural elements, including pitasters, horizontal cornices, arched windows, and ornamental parapets, improve the image of the town. These empirical findings support the policy framework that enhances the visual perception of Kumbakonam Town.

Using random-parameter and fixed-parameter ordered models to explore temporal stability in factors affecting drivers' injury severity in single-vehicle collisions

Understanding the temporal stability in the factors influencing drivers' injury severity in single-vehicle collisions would help evaluating the effectiveness of implementing different safety treatments so that researchers could understand whether any safety improvements,observed after applying a certain safety treatment, are attributed to the specific treatment or simply attributed to the temporal instability of the factors being addressed. This study investigates the temporal stability of the factors affecting drivers' injury severity in singlevehicle collisions involving light-duty vehicles. The study is based on utilizing ordinal regression modeling to analyze the severity of drivers' injuries in all police-reported lightduty single-vehicle collisions that occurred in North Carolina from January 1, 2007, to December 31, 2013. A separate regression model was estimated for each year so that statistical significance of each risk factor may be compared over the years. The study also estimated random-parameter(mixed) ordered logit models to explore the heterogeneity in data. The most significant factor that was found to increase the severity of drivers' injuries in light-duty single-vehicle collisions is driving under the influence of alcohol or illicit drugs. Other significant factors, in decreasing order in terms of their significance, include driving on a highway curve, exceeding speed limit, lighting conditions, the age of the driver, and the age of the vehicle. In contrast, there were six factors that were found to be significant in only some years and not in all years. These six temporally unstable factors include the use of seatbelt, driver's gender, rural highways, undivided highways, the type of the light-duty vehicle, and weather and road surface conditions. These same factors were found by other previous research studies to be significant and stable predictors of drivers' injury severity in single-vehicle collisions.

Basophile:Accurate Fragment Charge State Prediction Improves Peptide Identification Rates

In shotgun proteomics, database search algorithms rely on fragmentation models to pre- dict fragment ions that should be observed for a given peptide sequence. The most widely used strat- egy （Naive model） is oversimplified, cleaving all peptide bonds with equal probability to produce fragments of all charges below that of the precursor ion. More accurate models, based on fragmen- tation simulation, are too computationally intensive for on-the-fly use in database search algorithms. We have created an ordinal-regression-based model called Basophile that takes fragment size and basic residue distribution into account when determining the charge retention during CID/higher- energy collision induced dissociation （HCD） of charged peptides. This model improves the accuracy of predictions by reducing the number of unnecessary fragments that are routinely predicted for highly-charged precursors. Basophile increased the identification rates by 26% （on average） over the Naive model, when analyzing triply-charged precursors from ion trap data. Basophile achieves simplicity and speed by solving the prediction problem with an ordinal regression equation, which can be incorporated into any database search software for shotgun proteomic identification.