Prediction of Conversion from CIS to Clinically Definite Multiple Sclerosis Using Convolutional Neural Networks.

Multiple sclerosis (MS) is a chronic neurological disease of the central nervous system (CNS). Early diagnosis of MS is highly desirable as treatments are more effective in preventing MS-related disability when given in the early stages of the disease. The main aim of this research is to predict the occurrence of a second MS-related clinical event, which indicates the conversion of clinically isolated syndrome (CIS) to clinically definite MS (CDMS). In this study, we apply a branch of artificial intelligence known as deep learning and develop a fully automated algorithm primed with convolutional neural network (CNN) that has the ability to learn from MRI scan features. The basic architecture of our algorithm is that of the VGG16 CNN model, but amended such that it can handle MRI DICOM images. A dataset comprised of scans acquired using two different scanners was used for the purposes of verification of the algorithm. A group of 49 patients had volumetric MRI scans taken at onset of the disease and then again one year later using one of the two scanners. In total, this yielded 7360 images which were then used for training, validation, and testing of the algorithm. Initially, these raw images were taken through 4 steps of preprocessing. In order to boost the efficiency of the process, we pretrained our algorithm using the publicly available ADNI dataset used to classify Alzheimer's disease. Finally, we used our preprocessed dataset to train and test the algorithm. Clinical evaluation conducted a year after the first time point revealed that 26 of the 49 patients had converted to CDMS, while the remaining 23 had not. Results of testing showed that our algorithm was able to predict the clinical results with an accuracy of 88.8% and with an area under the curve (AUC) of 91%. A highly accurate algorithm was developed using CNN approach to reliably predict conversion of patients with CIS to CDMS using MRI data from two different scanners.

The emerging role of artificial intelligence in multiple sclerosis imaging.

BACKGROUND: Computer-aided diagnosis can facilitate the early detection and diagnosis of multiple sclerosis (MS) thus enabling earlier interventions and a reduction in long-term MS-related disability. Recent advancements in the field of artificial intelligence (AI) have led to the improvements in the classification, quantification and identification of diagnostic patterns in medical images for a range of diseases, in particular, for MS. Importantly, data generated using AI techniques are analyzed automatically, which compares favourably with labour-intensive and time-consuming manual methods. OBJECTIVE: The aim of this review is to assist MS researchers to understand current and future developments in the AI-based diagnosis and prognosis of MS. METHODS: We will investigate a variety of AI approaches and various classifiers and compare the current state-of-the-art techniques in relation to lesion segmentation/detection and prognosis of disease. After briefly describing the magnetic resonance imaging (MRI) techniques commonly used, we will describe AI techniques used for the detection of lesions and MS prognosis. RESULTS: We then evaluate the clinical maturity of these AI techniques in relation to MS. CONCLUSION: Finally, future research challenges are identified in a bid to encourage further improvements of the methods.

Control of Risk Factors for Cardiovascular Disease among Multinational Patient Population in the Arabian Gulf.

We evaluated the control of cardiovascular disease (CVD) risk factors among patients with atherosclerotic cardiovascular disease (ASCVD) in the Centralized Pan-Middle East Survey on the undertreatment of hypercholesterolaemia (CEPHEUS) in the Arabian Gulf. Of the 4398 enrolled patients, overall mean age was 57 ± 11 years, 60% were males, 13% were smokers, 76% had diabetes, 71% had metabolic syndrome and 78% had very high ASCVD risk status. The proportion of subjects with body mass index <25 kgm2, HbA1c <7% (in diabetics), low-density lipoprotein cholesterol (LDL-C) <2.6 mmol/L (100 mg/dL) and <1.8 mmol/L (70 mg/dL) for high and very high ASCVD risk cohorts, respectively and controlled blood pressure (<140/90 mmHg) was 14, 26, 31% and 60%, respectively. Only 1.4% of the participants had all of their CVD risk factors controlled with significant differences among the countries (P < .001). CVD risk goal attainment rates were significantly lower in those with very high ASCVD risk compared with those with high ASCVD risk status (P < .001). Females were also, generally, less likely to attain goals when compared with males (P < .001).

Isolation, characterization, and multiplexing of novel microsatellite markers for the tropical scalloped spiny lobster (Panulirus homarus).

Of the various spiny lobster species in the tropical and subtropical Indo-West Pacific region, the tropical scalloped spiny lobster (Panulirus homarus) supports one of the most commercially valuable fishery resources in many coastal African and Asian countries. The last decade has witnessed a serious decline in the wild populations of this species. Knowledge of the genetic basis of spiny lobster population structure is a prerequisite to achieve a sustainable fisheries management for this species. Here, we describe 13 novel polymorphic microsatellite markers developed for P. homarus, using a cross-species primer design strategy based on P. ornatus Roche 454 shot-gun generated sequencing. Microsatellite polymorphisms were assessed in 96 unrelated P. homarus individuals of a natural population, with the number of alleles per locus varying from 2 to 14, the observed and expected heterozygosity from 0.00 to 0.78 and from 0.03 to 0.79, respectively, and with only four loci (Pho-G27, Pho-G32, Pho-G36, and Pho-G58) deviating from Hardy- Weinberg equilibrium. Genetic linkage disequilibrium analysis between all pairs of the loci showed significant departure from the null hypothesis between loci Pho-G22 - Pho-G30, and Pho-G30 - Pho-G35. The successful cross amplification of these microsatellites highlights the potential of the developed microsatellites for future population genetic research within the different Panulirus species.

Validation and comparison of three formulae to estimate sodium and potassium excretion from a single morning fasting urine compared to 24-h measures in 11 countries.

BACKGROUND AND OBJECTIVES: Although 24-h urinary measure to estimate sodium and potassium excretion is the gold standard, it is not practical for large studies. We compared estimates of 24-h sodium and potassium excretion from a single morning fasting urine (MFU) using three different formulae in healthy individuals. METHODS: We studied 1083 individuals aged 35-70 years from the general population in 11 countries. A 24-h urine and MFU specimen were obtained from each individual. A subset of 448 individuals repeated the measures after 30-90 days. The Kawasaki, Tanaka, and INTERSALT formulae were used to estimate urinary excretion from a MFU specimen. RESULTS: The intraclass correlation coefficient (ICC) between estimated and measured sodium excretion was higher with Kawasaki (0.71; 95% confidence interval, CI: 0.65-0.76) compared with INTERSALT (0.49; 95% CI: 0.29-0.62) and Tanaka (0.54; 95% CI: 0.42-0.62) formulae (P <0.001). For potassium, the ICC was higher with the Kawasaki (0.55; 95% CI: 0.31-0.69) than the Tanaka (0.36; 95% CI: -0.07 to 0.60; P <0.05) formula (no INTERSALT formula exists for potassium). The degree of bias (vs. the 24-h urine) for sodium was smaller with Kawasaki (+313 mg/day; 95% CI: +182 to +444) compared with INTERSALT (-872 mg/day; 95% CI: -728 to -1016) and Tanaka (-548 mg/day; 95% CI: -408 to -688) formulae (P <0.001 and P = 0.02, respectively). Similarly for potassium, the Kawasaki formula provided the best agreement and least bias. Blood pressure correlated most closely and similarly with the 24-h and Kawasaki estimates for sodium compared with the other two formulae. CONCLUSION: In a diverse population, the Kawasaki formula is the most valid and least biased method of estimating 24-h sodium excretion from a single MFU and is suitable for population studies.

Validation and comparison of three formulae to estimate sodiumand potassiumexcretion froma singlemorning fasting urine comparedto 24-hmeasures in 11countries

Background and objectives: Although 24-h urinarymeasure to estimate sodium and potassium excretion isthe gold standard, it is not practical for large studies. Wecompared estimates of 24-h sodium and potassiumexcretion from a single morning fasting urine (MFU) usingthree different formulae in healthy individuals.Methods: We studied 1083 individuals aged 35–70 yearsfrom the general population in 11 countries. A 24-h urineand MFU specimen were obtained from each individual. Asubset of 448 individuals repeated the measures after 30–90 days. The Kawasaki, Tanaka, and INTERSALT formulaewere used to estimate urinary excretion from a MFU specimen.Results: The intraclass correlation coefficient (ICC)between estimated and measured sodium excretion washigher with Kawasaki (0.71; 95% confidence interval, CI:0.65–0.76) compared with INTERSALT (0.49; 95% CI:0.29–0.62) and Tanaka (0.54; 95% CI: 0.42–0.62)formulae (P<0.001). For potassium, the ICC was higherwith the Kawasaki (0.55; 95% CI: 0.31–0.69) than theTanaka (0.36; 95% CI: 0.07 to 0.60; P<0.05) formula(no INTERSALT formula exists for potassium). The degreeof bias (vs. the 24-h urine) for sodium was smaller withKawasaki (R313 mg/day; 95% CI: R182 to R444)compared with INTERSALT ( 872 mg/day; 95% CI: 728to 1016) and Tanaka ( 548 mg/day; 95% CI: 408 to 688) formulae (P<0.001 and P»0.02, respectively).Similarly for potassium, the Kawasaki formula provided thebest agreement and least bias. Blood pressure correlatedmost closely and similarly with the 24-h and Kawasakiestimates for sodium compared with the other twoformulae.Conclusion: In a diverse population, the Kawasaki formulais the most valid and least biased method of estimating24-h sodium excretion from a single MFU and is suitablefor population studies.

Intravascular ultrasound aids in the performance of endovascular repair of abdominal aortic aneurysm.

PURPOSE: The purpose of this retrospective review was to assess the accuracy of aortic measurements with intravascular ultrasound scan (IVUS) compared with computed tomographic (CT) scan and to assess the role of IVUS in the performance of endovascular repair of abdominal aortic aneurysms (AAAs). METHODS: Seventy-eight patients undergoing repair of AAA with the AneuRx stent graft (Medtronic AVE, Inc, Santa Rosa, Calif) underwent measurement with CT scan and IVUS. The initial selection of stent graft size was made on the basis of the CT scan measurements, but the final decision for size was made on the basis of the IVUS measurements. Standard measurements of a phantom tube obtained with IVUS, CT scan, and digital caliper were also compared. RESULTS: IVUS measurements of the phantom standard agreed closely with CT scan measurements. However, stent graft size initially selected with CT measurement was altered in 28% of cases on the basis of intraoperative IVUS measurements. No type I endoleaks were encountered in our series, and no aortic cuffs were necessary for endoleak repair. CONCLUSION: IVUS accurately measures the aorta for selection of stent grafts for endovascular repair of AAA and may prevent type I endoleaks and remedial procedures for their repair.

Breast carcinoma in Pakistani women.

In many developed and developing countries including Pakistan, breast cancer is the most frequently diagnosed cancer and the leading cause of cancer death in women. Among 4575 women presenting to the Cancer Research Foundation of Pakistan between 1987 and 1994 with breast lumps, 1201 (26%) were found to have breast cancer. Their ages ranged from 19 to 79 years. The peak incidence was in the 30 to 39 age group. Most patients were multiparous with an average of five children. The size of the tumor was greater than 5 cm in 66% of the cases. Invasive ductal carcinoma was the most common morphological type. According to the Bloom and Richardson grading system, 58% of cases were grade III. Lymph node metastases were present in 73% of the cases.

Breast cancer in pregnant and lactating women.

Between 1988 and 1991, we treated 595 women with breast cancer in the Breast Disease Section of the Cancer Research Foundation of Pakistan. We report here on 61 patients who were pregnant or lactating. Most patients presented at a late stage of disease because of ignorance, social taboos, or fear of hospitalization and operation. The largest diameter of the breast mass at presentation was 15 cm. Lymph nodes were involved in 70.5% of cases. Multiparity, young marriages, malnutrition, and unhygienic conditions are ripe in the rural environment of Pakistan. No oral contraceptives are used. Modern and conventional methods of treatment did not increase the survival rate of these cancer patients.

PIP: Among the 595 women with breast cancer diagnosed at the Breast Disease Section of the Cancer Research Foundation of Pakistan during 1988-91, 61 were pregnant or lactating. Foundation patients were primarily low-income, rural women who came to the clinic in response to a mass media educational campaign that offered free treatment to the poor. The 28 women who presented in the second and third trimesters of pregnancy were delivered at term, while the 4 women in their first trimester aborted. The 29 women who developed a breast mass during lactation had breast fed for 3-18 months before diagnosis. Most patients presented with large T3 and T4 tumor masses; over 70% were in stage III of the disease. Infiltrating ductal carcinoma was the predominant histologic type of tumor. Lymph node involvement was present in 75% of pregnant and 65.5% of lactating patients. The breast mass had been detected an average of 4 and 6 months before clinic attendance in pregnant women and lactating women, respectively. Women delayed seeking medical evaluation because of their fears of disease, disfigurement, and rejection by their husbands. Also implicated were a lack of training in breast self-examination and the belief breast enlargement resulted from engorgement. Despite modern treatment methods (mastectomy, radiation, and chemotherapy), the median survival time was under 36 months in both groups.

Evaluation of coliphages in sewage effluent of Faisalabad.

One hundred and ten samples of Sewage were collected from both underground sewage and open drain systems of Faisalabad for coliphage assay. It was observed that the samples from underground sewage system ranged from 8.43 X 10(3)--4.65 X 10(3) in mean plaque forming units (PFU) per ml, whereas the corresponding figures in open drain system varied from 8.66 X 10(3)--3.21 X 10(3) mean PFU per ml. In general, samples from congested areas of both the systems studied tended to be richest both in mean PFU per ml as well as plaque morphological variations. Overall 620 plaque morphological classes were isolated. It was also noted that the mean PFU per ml was higher in the summer than in the winter months and phage contents were increased after rain fall.