Towards effective machine learning in medical imaging analysis: A novel approach and expert evaluation of high-grade glioma 'ground truth' simulation on MRI.

PURPOSE/OBJECTIVE(S): Gliomas are uniformly fatal brain tumours with significant neurological and quality of life detriment to patients. Improvement in outcomes has remained largely unchanged in nearly 20 years. MRI (magnetic resonance imaging) is often used in diagnosis and management. Machine learning analyses of large-scale MRI data are pivotal in advancing the diagnosis, management and improve outcomes in neuro-oncology. A common challenge to robust machine learning approaches is the lack of large 'ground truth' datasets in supervised learning for building classification and prediction models. The creation of these datasets relies on human-expert input and is time-consuming and subjective error-prone, limiting effective machine learning applications. Simulation of mechanistic aspects such as geometry, location and physical properties of brain tumours can generate large-scale ground-truth datasets allowing for comparison of analysis techniques in clinical applications. We aimed to develop a transparent and convenient method for building 'ground truth' presentations of simulated glioma lesions on anatomical MRI. MATERIALS/METHODS: The simulation workflow was created using the Feature Manipulation Engine (FME®), a data integration platform specializing in the spatial data processing. By compiling and integrating FME's functions to read, integrate, transform, validate, save, and display MRI data, and experimenting with ways to manipulate the parameters concerning location, size, shape, and signal intensity with the presentations of glioma, we were able to generate simulated appearances of high-grade gliomas on gadolinium-based high-resolution 3D T1-weighted MRI (1 mm3). Data of patients with canonical high-grade tumours were used as real-world tumours for validating the accuracy of the simulation. Twenty raters who are experienced with brain tumour interpretation on MRI independently completed a survey, designed to distinguish simulated and real-world brain tumours. Sensitivity and specificity were calculated for assessing the performance of the approach with the binary classification of simulated vs real-world tumours. Correlation and regression were used in run time analysis, assessing the software toolset's efficiency in producing different numbers of simulated lesions. Differences in the group means were examined using the non-parametric Kruskal-Wallis test. RESULTS: The simulation method was developed as an interpretable and useful workflow for the easy creation of tumour simulations and incorporation into 3D MRI. A linear increase in the running time and memory usage was observed with an increasing number of generated lesions. The respondents' accuracy rate ranged between 33.3 and 83.3 %. The sensitivity and specificity were low for a human expert to differentiate simulated lesions from real gliomas (0.43 and 0.58) or vice versa (0.65 and 0.62). The mean scores ranking the real-world gliomas did not differ between the simulated and real tumours. CONCLUSION: The reliable and user-friendly software method can allow for robust simulation of high-grade glioma on MRI. Ongoing research efforts include optimizing the workflow for generating glioma datasets as well as adapting it to simulating additional MRI brain changes.

Morphological variation in the freshwater blenny Salaria fluviatilis from Corsican rivers: adaptive divergence, phenotypic plasticity or both?

The first goal of this study was to determine whether morphological variation in the freshwater blenny Salaria fluviatilis results in spatially structured populations distributed around Corsica, France, which would suggest genetically differentiated populations through reproductive isolation by distance. The second goal was to determine whether some morphological traits are related to water velocity, one of the most contrasting habitat characteristics in these rivers, which would suggest an adaptation to local conditions. The results showed that the morphology of S. fluviatilis differed among the three main geographic areas studied in Corsica and that geographically distant populations of S. fluviatilis were less similar morphologically and genetically than close ones. The results also indicated that the morphological differences among populations conformed to functional expectations. Overall, the results suggest that the morphological variation of S. fluviatilis from Corsican rivers is an adaptive response to water velocity and that these populations are in a process of reproductive isolation by distance.

A combination of poloxamers increases gene expression of plasmid DNA in skeletal muscle.

Intramuscular administration of plasmid DNA is a promising strategy to express therapeutic genes, however, it is limited by a relatively low level of gene expression. We report here that a non-ionic carrier, SP1017, composed of two amphiphilic block copolymers, pluronics L61 and F127, also known as poloxamers, significantly increases intramuscular expression of plasmid DNA. Two reporter genes, luciferase and beta-galactosidase, and one therapeutic gene, erythropoietin, were injected intramuscularly with and without SP1017 into C57Bl/6 and Balb/C mice and Sprague-Dawley rats. SP1017 increased gene expression by about 10-fold and maintained higher gene expression compared with naked DNA. Comparison of SP1017 with polyvinyl pyrrolidone (PVP) showed that SP1017 exhibited a significantly higher efficacy and its optimal dose was 500-fold lower. Experiments with beta-galactosidase using X-gal staining suggested that SP1017 considerably increased plasmid DNA diffusion through the tissue. SP1017 also improved expression of the erythropoietin gene leading to an increase in its systemic level and hematocrits. Previous toxicity studies have suggested that SP1017 has over a 1000-fold safety margin. Poloxamers used in SP1017 are listed in the US Pharmacopeia as inactive excipients and are widely used in a variety of clinical applications. We believe that the described system constitutes a simple and efficient gene transfer method to achieve local or systemic production of therapeutic proteins.

First lifetime back pain and psychiatry treatment: psychological factors and recovery in compensated workers.

The role of psychological factors in recovery from first lifetime low back pain (LBP) was explored in this study. Consecutive clients from one physiatry clinic in Montreal who had LBP of less than 3 months' duration, were on sick leave and receiving workers' compensation benefits, and reported the current event as first lifetime LBP were enrolled. Psychological factors that fluctuate with current events (Psychiatric Symptom Index) and remain stable over time (General Well Being Scale) were assessed. Outcomes were late return to work (> 31 days) and 1 year incidence of compensated recurrence. Results from two multivariate models indicated lower psychological distress predicted late return to work, and higher well being, higher aggressiveness, and lower anxiety predicted compensated recurrence. Researchers concluded psychological factors do not impact clients with all types of LBP in the same way. For individuals lacking prior LBP experience, better psychological functioning increased lengthy work absence. Thus, awareness of the clients' psychological profiles and previous LBP experiences may benefit recovery.

Homophobia in northeastern Brazilian university students.

The purpose of this research was to examine the presence of homophobia in northeastern Brazilian university students and the interaction between homophobia and various constructs, such as gender, family, and contact with homosexuals. This research was completed through the use of questionnaires, and responses were attained from a diverse group of 553 students. The Brazilian results demonstrate a complete inversion of the relationship between homophobia and gender roles from that which has been established in past research. Specifically, the results found that women are slightly more homophobic than men, female homophobia is more pronounced toward female homosexuals than male homosexuals, and male homophobia is equally directed toward male and female homosexuals. The differences are hypothesized to stem from the similarly rigid gender roles of northeastern Brazilian women and industrialized men.

A cross-sectional study comparing the Oswestry and Roland-Morris Functional Disability scales in two populations of patients with low back pain of different levels of severity.

STUDY DESIGN: This cross-sectional study compares the Oswestry and Roland-Morris disability scales in two groups of patients with low back pain of different clinical and electromyographic severity. OBJECTIVES: To evaluate the correlation between functional disability and diagnoses. SUMMARY OF BACKGROUND DATA: There is an increasing need for functional disability measurements to be applied to the evaluation of therapy and outcome in patients experiencing low back pain. METHODS: Two very different groups of patients with low back pain completed the Oswestry and Roland-Morris self-administrated functional disability questionnaires. One group included patients presenting with an episode of mechanical low back pain with no clinical radiculopathy. The other group consisted of patients with low back pain and clinical and electromyographic evidence of radiculopathy. RESULTS: Patients diagnosed with low back pain who exhibited signs of radiculopathy on electromyography had a mean score of 49.1 +/- 17.1 on the Oswestry disability questionnaire; a mean score of 33.0 +/- 14.7 was found for patients who experienced "simple" low back sprain (with no radiculopathy). This difference was statistically significant (P < 0.0001). On the Roland-Morris questionnaire, the mean score obtained by the group of patients with radiculopathy was 59.1 +/- 21.8 compared with 45.4 +/- 19.4 for those with no radiculopathy. This difference was also statistically significant (P < 0.0001). Moreover, there exists a moderate correlation between both functional scales within each group of patients: 0.72 (P < 0.0001) in the group with radiculopathy and 0.66 (P < 0.0001) among those without radiculopathy. CONCLUSIONS: The authors conclude that both functional disability scales accurately discriminated between these two groups of patients with low back pain of very different clinical and electromyographic severity.

Back school in a first episode of compensated acute low back pain: a clinical trial to assess efficacy and prevent relapse.

OBJECTIVE: To assess the efficacy of a back school program for patients with a first episode of acute work-related low back pain requiring compensation. DESIGN: A randomized single-blind controlled trial. SETTING: A private physiatrics outpatient clinic. PATIENTS: The mean duration of low back pain was 15 days. INTERVENTION: Eligible patients were randomized to a standard treatment program that included daily physiotherapy (n = 86) or the same program with the addition of back school (n = 82). The back school program consisted of three 90-minute sessions given by a single trained instructor at 0, 1, and 8 weeks. MAIN OUTCOME MEASURES: The primary outcomes were the time off work for the presenting episode of back pain and the number and duration of recurrences in the year following the study onset. Secondary outcomes included the level of pain, spinal mobility, active straight-leg raising, and functional disability assessed by the Oswestry and Roland-Morris scales. RESULTS: Those randomized to the back school group gained significantly more knowledge, based on the multiple choice examination (p = .0001) and performed the exercise program significantly better (p = .0001) than the standard care group. There were no differences between the two treatment groups for either of the primary outcomes. The median time to return to work from randomization was 33 days for both the back school and the standard care groups (p = .48). The number of compensated recurrences of low back pain over 1 year was similar (back school = 14, standard care = 10, p = .16), as was the median duration of these episodes (back school = 25 days, standard care = 70 days, p = .21). There were no significant differences favoring the back school group for any of the secondary outcomes at the posttreatment, 6-month, or 12-month assessments. CONCLUSION: A back school intervention in addition to standard care resulted in no reduction in the time to return to work or the number or duration of recurrences of low back pain requiring compensation over a period of one year.

Categorization in unsupervised neural networks: the Eidos model.

Proulx and Begin (1995) recently explained the power of a learning rule that combines Hebbian and anti-Hebbian learning in unsupervised auto-associative neural networks. Combined with the brain-state-in-a-box transmission rule, this learning rule defines a new model of categorization: the Eidos model. To test this model, a simulated neural network, composed of 35 interconnected units, is subjected to an alphabetical characters recognition task. The results indicate the necessity of adding two parameters to the model: a restraining parameter and a forgetting parameter. The study shows the outstanding capacity of the model to categorize highly altered stimuli after a suitable learning process. Thus, the Eidos model seems to be an interesting option to achieve categorization in unsupervised neural networks.

Automation of steroid radioimmunoassays using a robotics workstation.

OBJECTIVE: To automate the radioimmunoassay (RIA) of steroids in a diagnostic clinical laboratory. SETTING: The Laboratory of Pediatric Endocrinology, Cornell Medical Center-New York Hospital. PRACTICE DESCRIPTION: A tertiary-care center supporting the diagnosis and treatment of pediatric patients with endocrine disorders. PRODUCT COMPARISON: The Packard MultiPROBE Model 100 Automated Liquid Handling System (Packard Instrument Company, Meriden, CT 06450) was compared with the assays typically used to assist in the diagnosis of steroidogenic disorders in children: extraction of biologic fluids, celite partition chromatography, and RIA. MAIN OUTCOME MEASUREMENT: The comparative efficiency, cost-effectiveness, specificity, and sensitivity of the two methods. RESULT: The automated RIAs correlated (r = 0.963) with the established manual assays for steroids. The specificity and sensitivity of the assays were uniformly maintained after automation. CONCLUSION: The automation of steroid RIAs has made the method a highly efficient and cost-effective one for diagnostic clinical laboratories.

Processing of pragmatic and facial affective information by patients with closed-head injuries.

Although several affective impairments have been demonstrated to occur following closed-head injury (CHI), deficits of the communicative function of language, particularly sentenial and suprasentential pragmatic aspects, have been suggested, but not demonstrated, to occur. This study compared 31 normals and 31 severely closed-head injured patients matched for age, sex and education. The dependent measures consisted of a facial test of emotion (FTE) and a contextual test of emotion (CTE). The former task consisted of 36 slides representing facial expressions of the six emotions demonstrated by Ekman and colleagues to be transcultural, namely, job, sadness, fear, anger, surprise and disgust. The subject was required to name the appropriate emotion for each slide. The latter task consisted of correctly identifying the appropriate emotion for each of 36 brief verbal narratives representing contexts connotative of the same six transcultural emotions. The CHI patients were impaired overall on the FTE but not the CTE. However, the ability to identify anger was significantly impaired on both tasks when considered in isolation from the other emotions. It was concluded that a processing deficit of primary emotional material, particularly anger, does exist following CHI, but that this deficit is not necessarily independent of task and/or modality parameters. It was also concluded that evidence of a pragmatic deficit of the language function following CHI remains to be provided at this time.

Emotional facial expressive and discriminative performance and lateralization in normal young adults.

Studies of cerebral dominance for posed emotional facial expression using free-viewing of hemicomposites have produced inconclusive findings, and the concordance of facial emotion identification (discrimination) and the expression of the same facial emotion remains unknown. Expressive and discriminative (14 men, 14 women) facial emotion performances of undergraduates and the lateralization of full-face and lower-face hemicomposite photographic montages of the expressions of six transcultural emotions (joy, sadness, fear, surprise, disgust, anger) as ascertained by 15 male and 15 female undergraduate judges were analyzed. All groups were matched for age and education. The lower face was non-significantly left-face dominant, sadness was strongly significantly right-face dominant and fear was non-significantly left face dominant. Both sexes were equally lateralized overall and demonstrated the same pattern as described above, though slight (apparently trivial) differences appeared in multivariate analysis, and in univariate interactions. Results were interpreted as non-supportive of a simple right hemisphere dominance model of facial affect, nor of a left-hemisphere-negative/right-hemisphere-positive model. It was concluded that facial affect dominance results are coherent only within, and not between, methods such as free viewing hemicomposite and tachistoscopic methods, and tasks, such as expressive and discriminative tasks.