Prediction of Alzheimer's disease stages based on ResNet-Self-attention architecture with Bayesian optimization and best features selection.

Alzheimer's disease (AD) is a neurodegenerative illness that impairs cognition, function, and behavior by causing irreversible damage to multiple brain areas, including the hippocampus. The suffering of the patients and their family members will be lessened with an early diagnosis of AD. The automatic diagnosis technique is widely required due to the shortage of medical experts and eases the burden of medical staff. The automatic artificial intelligence (AI)-based computerized method can help experts achieve better diagnosis accuracy and precision rates. This study proposes a new automated framework for AD stage prediction based on the ResNet-Self architecture and Fuzzy Entropy-controlled Path-Finding Algorithm (FEcPFA). A data augmentation technique has been utilized to resolve the dataset imbalance issue. In the next step, we proposed a new deep-learning model based on the self-attention module. A ResNet-50 architecture is modified and connected with a self-attention block for important information extraction. The hyperparameters were optimized using Bayesian optimization (BO) and then utilized to train the model, which was subsequently employed for feature extraction. The self-attention extracted features were optimized using the proposed FEcPFA. The best features were selected using FEcPFA and passed to the machine learning classifiers for the final classification. The experimental process utilized a publicly available MRI dataset and achieved an improved accuracy of 99.9%. The results were compared with state-of-the-art (SOTA) techniques, demonstrating the improvement of the proposed framework in terms of accuracy and time efficiency.

High resistance of fluoroquinolone and macrolide reported in avian pathogenic Escherichia coli isolates from the humid subtropical regions of Pakistan.

OBJECTIVES: This study aimed to assess the antimicrobial resistance profile, virulence potential, and genetic characterization of avian pathogenic Escherichia coli (APEC) that cause colibacillosis in poultry. METHODS: Antibiotic susceptibility testing (AST) was measured via the Kirby-Bauer disc diffusion method against 27 commonly used antibiotics. Phylogrouping, virulence-associated gene detection, and hybrid strain detection via multiplex polymerase chain reaction (PCR) and genetic diversity were analysed via ERIC-PCR fingertyping method. RESULTS: AST analysis showed 100% of isolates were multidrug-resistant (MDR) and highest resistance was against penicillin, tetracycline, and macrolide classes of antibiotics. The mcr-1 gene was present in 40% of the isolates, though only 4% of isolates were showing phenotypic resistance. Despite the scarce use of fluoroquinolone, carbapenem, and cephalosporin in the poultry sector, resistance was evident because of the high prevalence of extended-spectrum ß-lactamase (ESBL) (53.7%) and other ß-lactamases in APEC isolates. ß-lactamase genotyping of APEC isolates revealed that 85.7% of isolates contained either blaCTX or blaTEM and around 38% of isolates were complement resistant. Growth in human urine was evident in 67.3% of isolates. Phylogroup B1 (51%) was the most prevalent group followed by phylogroups A (30.6%), D (13.61%), and B2 (4.76%). The most prevalent virulence-associated genes were fimH, iss, and tatT. Results showed that 26 isolates (17.69%) can be termed hybrid strains and APEC/EHEC (enterohemorrhagic E. coli) was the most prevalent hybrid E. coli pathotype. ERIC-PCR fingerprinting genotype analysis clustered APEC isolates in 40 groups (E1-E40). This study provides insights into the antibiotic resistance and virulence profiling of the APEC isolates in Pakistan. CONCLUSIONS: The findings of this study provide insights into that the antibiotic resistance and virulence profiling of the APEC isolates in Pakistan. This data can inform future studies designed to better estimate the severity of the colibacillosis in poultry farms.

Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning.

The choroid layer is a vascular layer in human retina and its main function is to provide oxygen and support to the retina. Various studies have shown that the thickness of the choroid layer is correlated with the diagnosis of several ophthalmic diseases. For example, diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. Despite contemporary advances, automatic segmentation of the choroid layer remains a challenging task due to low contrast, inhomogeneous intensity, inconsistent texture and ambiguous boundaries between the choroid and sclera in Optical Coherence Tomography (OCT) images. The majority of currently implemented methods manually or semi-automatically segment out the region of interest. While many fully automatic methods exist in the context of choroid layer segmentation, more effective and accurate automatic methods are required in order to employ these methods in the clinical sector. This paper proposed and implemented an automatic method for choroid layer segmentation in OCT images using deep learning and a series of morphological operations. The aim of this research was to segment out Bruch's Membrane (BM) and choroid layer to calculate the thickness map. BM was segmented using a series of morphological operations, whereas the choroid layer was segmented using a deep learning approach as more image statistics were required to segment accurately. Several evaluation metrics were used to test and compare the proposed method against other existing methodologies. Experimental results showed that the proposed method greatly reduced the error rate when compared with the other state-of-the-art methods.

Publisher Correction: Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Immunoexpression of Cyclin D1 and PTEN in Various Endometrial Pathologies.

OBJECTIVE: To determine the expression of cyclin D1 and PTEN (phosphatase and tensin homolog) in endometrial hyperplasias and neoplasias. STUDY DESIGN: Analytical study. PLACE AND DURATION OF STUDY: The study was conducted at BMSI, JPMC, Karachi, from January 2008 to December 2012. METHODOLOGY: Analysis of endometrial samples, comprising of hysterectomies and curettage, was carried out. Immunohistochemical staining was done for PTEN and cyclin D1 expression. RESULTS: Fifty-three endometrial samples including 23 endometrial carcinomas, 6 complex hyperplasias with atypia, 14 complex hyperplasias without atypia, 6 simple hyperplasias without atypia and 4 normal proliferative endometrium were analyzed. Fifty-two percent (12 out of 23) and 48% (11 out of 23) cases of endometrial carcinomas showed complete loss of PTEN expression and cyclin D1 over expression, respectively. Five (5 out of 6) cases of complex hyperplasias with atypia and 64.28% (9 out of 14) cases of complex hyperplasia without atypia showed complete loss of or diminished expression of PTEN whereas 66.66% (4 out of 6) cases of endometrial hyperplasia with atypia and 50% (7 out of 14) cases of endometrial hyperplasia without atypia showed cyclin D1 overexpression (p < 0.001). CONCLUSION: Loss of PTEN, expression and cyclin D1 overexpression was seen in a significant number of well differentiated endometrial adenocarcinomas and complex hyperplasias with atypia, suggesting both as an early event in endometrial carcinogenesis.

Differential expression of p63 in hydropic and molar gestations.

OBJECTIVE: To observe the differential expression of p63 in hydropic and molar gestation. STUDY DESIGN: Cross-sectional analytical study. PLACE AND DURATION OF STUDY: Department of Pathology, Basic Medical Sciences Institute, Jinnah Postgraduate and Medical Centre, Karachi, from January 2006 to June 2013. METHODOLOGY: Ninety placental biopsies including 30 cases each of hydropic abortions, partial hydatidiform mole and complete hydatidiform mole were analyzed for morphological features and results of immunohistochemical staining. Results were described as frequency. Significance was determined using test of proportions with significance at p < 0.05. RESULTS: Out of 30 cases of hydropic abortion, 6 were negative, 15 were weak, 4 were moderate and 5 showed strong degree of intensity for p63. Out of 30 cases of partial hydatidiform mole, 3 were negative, 2 showed weak, 4 showed moderate and 21 cases showed strong degree of intensity for p63. All 30 cases of complete hydatidiform mole strongly stained for p63. CONCLUSION: The intensity of staining of p63 was stronger in cases of molar pregnancy as compared to hydropic abortion. There was loss of p63 expression in cytotrophoblastic cells in all abortions. In limited resources settings, where facilities for PCR/FISH and DNA ploidy analysis is not available, the authors advocate p63 in routine clinical practice to provide the most refined diagnosis of hydatidiform moles.