Traditional and deep learning-oriented medical and biological image analysis.

We investigated various methods for image segmentation and image processing for the segmentation of MRI of human medical data, as well as bioinformatics for the segmentation of brain cell details, in this work. The goal is to demonstrate and bring various mathematical analyses for medical and biological image analysis. We proposed new software and methods for improving the segmentation of biological and medical data. This way, we can find new ways to improve the diagnostic process in medical data and improve results in cell and iron diagnostics. We present the GrabCut algorithm as well as new, improved software for this part, a fuzzy approach and fuzzy processing of tissues, and finally machine­learning techniques with neural networks. We implemented the new software in the C++ programming language for the Grab cut algorithm. Consequently, we present a fuzzy approach to the diagnosis of image data in Matlab. Finally, a deep learning-based approach is used, with a U-Net-based segmentation architecture proposed to measure the various brain cell parameters. We will be able to proceed with data that we were unable to proceed when using other methods. As a result, we improved biological and medical data segmentation to obtain better boundaries and sharper edges on the objects. There is still space to extend these methods to other medical and biological applications (Tab. 1, Fig. 34, Ref. 46). Keywords: segmentation; image processing; fuzzy segmentation, GrabCut, deep learning.

LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery.

Automatic detection of lung diseases using AI-based tools became very much necessary to handle the huge number of cases occurring across the globe and support the doctors. This paper proposed a novel deep learning architecture named LWSNet (Light Weight Stacking Network) to separate Covid-19, cold pneumonia, and normal chest x-ray images. This framework is based on single, double, triple, and quadruple stack mechanisms to address the above-mentioned tri-class problem. In this framework, a truncated version of standard deep learning models and a lightweight CNN model was considered to conviniently deploy in resource-constraint devices. An evaluation was conducted on three publicly available datasets alongwith their combination. We received 97.28%, 96.50%, 97.41%, and 98.54% highest classification accuracies using quadruple stack. On further investigation, we found, using LWSNet, the average accuracy got improved from individual model to quadruple model by 2.31%, 2.55%, 2.88%, and 2.26% on four respective datasets.

Classification of Geometric Forms in Mosaics Using Deep Neural Network.

The paper addresses an image processing problem in the field of fine arts. In particular, a deep learning-based technique to classify geometric forms of artworks, such as paintings and mosaics, is presented. We proposed and tested a convolutional neural network (CNN)-based framework that autonomously quantifies the feature map and classifies it. Convolution, pooling and dense layers are three distinct categories of levels that generate attributes from the dataset images by introducing certain specified filters. As a case study, a Roman mosaic is considered, which is digitally reconstructed by close-range photogrammetry based on standard photos. During the digital transformation from a 2D perspective view of the mosaic into an orthophoto, each photo is rectified (i.e., it is an orthogonal projection of the real photo on the plane of the mosaic). Image samples of the geometric forms, e.g., triangles, squares, circles, octagons and leaves, even if they are partially deformed, were extracted from both the original and the rectified photos and originated the dataset for testing the CNN-based approach. The proposed method has proved to be robust enough to analyze the mosaic geometric forms, with an accuracy higher than 97%. Furthermore, the performance of the proposed method was compared with standard deep learning frameworks. Due to the promising results, this method can be applied to many other pattern identification problems related to artworks.

Preclinical Development of a Fusion Peptide Conjugate as an HIV Vaccine Immunogen.

The vaccine elicitation of broadly neutralizing antibodies against HIV-1 is a long-sought goal. We previously reported the amino-terminal eight residues of the HIV-1-fusion peptide (FP8) - when conjugated to the carrier protein, keyhole limpet hemocyanin (KLH) - to be capable of inducing broadly neutralizing responses against HIV-1 in animal models. However, KLH is a multi-subunit particle derived from a natural source, and its manufacture as a clinical product remains a challenge. Here we report the preclinical development of recombinant tetanus toxoid heavy chain fragment (rTTHC) linked to FP8 (FP8-rTTHC) as a suitable FP-conjugate vaccine immunogen. We assessed 16 conjugates, made by coupling the 4 most prevalent FP8 sequences with 4 carrier proteins: the aforementioned KLH and rTTHC; the H. influenzae protein D (HiD); and the cross-reactive material from diphtheria toxin (CRM197). While each of the 16 FP8-carrier conjugates could elicit HIV-1-neutralizing responses, rTTHC conjugates induced higher FP-directed responses overall. A Sulfo-SIAB linker yielded superior results over an SM(PEG)2 linker but combinations of carriers, conjugation ratio of peptide to carrier, or choice of adjuvant (Adjuplex or Alum) did not significantly impact elicited FP-directed neutralizing responses in mice. Overall, SIAB-linked FP8-rTTHC appears to be a promising vaccine candidate for advancing to clinical assessment.

Prevalence of Irritable Bowel Syndrome (IBS), Migraine and Co-Existing IBS-Migraine in Medical Students.

INTRODUCTION: Irritable Bowel Syndrome (IBS) and migraine frequently co-exist. Stress is a major contributing factor for both. Our medical students are subjected to stress related to the implicit responsibility of courses. But the prevalence of IBS, migraine and co-existing migraine in medical students is not known. AIM: To estimate the prevalence of migraine, IBS and co-existing IBS and migraine among medical students. A Cross-Sectional Survey. MATERIALS AND METHODS: Self-reported questionnaire based study, was conducted in which migraine was defined according to International Headache Society (IHS) criteria while IBS by both Asian criteria and Rome III criteria. Both preclinical (n=142) and clinical students (n=151) of four medical colleges (government and private) of Dhaka and Sylhet district participated in the study. Statistical Analysis: Student's t-test and chi-square test were used to compare the distributions of continuous data and categorical data respectively with significance level set at 0.05 or less. RESULTS: Among the 293 students (mean age 21.09 ± 2.24 years) volunteered in the study (Males= 177), 14 (4.8%, 11 males, 3 females, p = 0.175) met the criteria for IBS with comparable prevalence among preclinical and clinical (4.2% vs. 5.3%, p = 0.787) students from both private and government institutions (2.1% vs. 7.2%, p = 0.055). IBS-D was the most prevalent subtype (n = 8, M = 6) and abdominal pain relieved by defecation (n = 11), was the most prevalent symptom. Fifty percent (n = 7) of IBS patients considered their bowel habit as normal. Among the 221 (75.4%) students with headache, only 51 (17.4%, 20 males and 31 females, p = 0.001) were diagnosed of migraine, with comparable prevalence among preclinical and clinical students (16.2% vs. 18.5%, p = 0.645). Only 17 (33%) subjects with migraine had accompanying aura. Common triggers were stress (n = 43), lack of sleep (n = 42), and daily life events. Twelve (23.5%) subjects with migraine had migraine-associated frequent disability. Only two female students with IBS-D (14.3%) had concomitant IBS and migraine. CONCLUSION: IBS and concomitant migraine - IBS prevalence was found to be low in our medical students, but migraine prevalence corresponds to other countries as well as in medical students.