Deep Learning Supplants Visual Analysis by Experienced Operators for the Diagnosis of Cardiac Amyloidosis by Cine-CMR

Background: Diagnosing cardiac amyloidosis (CA) from cine-CMR (cardiac magnetic resonance) alone is not reliable. In this study, we tested if a convolutional neural network (CNN) could outperform the visual diagnosis of experienced operators. Method: 119 patients with cardiac amyloidosis and 122 patients with left ventricular hypertrophy (LVH) of other origins were retrospectively selected. Diastolic and systolic cine-CMR images were preprocessed and labeled. A dual-input visual geometry group (VGG ) model was used for binary image classification. All images belonging to the same patient were distributed in the same set. Accuracy and area under the curve (AUC) were calculated per frame and per patient from a 40% held-out test set. Results were compared to a visual analysis assessed by three experienced operators. Results: frame-based comparisons between humans and a CNN provided an accuracy of 0.605 vs. 0.746 (p < 0.0008) and an AUC of 0.630 vs. 0.824 (p < 0.0001). Patient-based comparisons provided an accuracy of 0.660 vs. 0.825 (p < 0.008) and an AUC of 0.727 vs. 0.895 (p < 0.002). Conclusion: based on cine-CMR images alone, a CNN is able to discriminate cardiac amyloidosis from LVH of other origins better than experienced human operators (15 to 20 points more in absolute value for accuracy and AUC), demonstrating a unique capability to identify what the eyes cannot see through classical radiological analysis.

First Report of Potato Viruses Infecting Lamium purpureum in Ukraine

Weeds as reservoirs for destructive plant pathogens have a significant impact on the viral epidemiology, ecology and, as a result, on local economy, and are therefore being investigated in many parts of the world. Thus, the aim of this study was to investigate virus occurrence in red dead-nettle plants (Lamium purpureum L.) widespread in urban and field conditions throughout the in the Kyiv region of Ukraine. Methods. Field crop observations, visual diagnosis, biological testing of the virus, immunoassay (ELISA), polymerase chain reaction with reverse transcription (RT-PCR), sanger sequencing of partial genome sequences of PVX, PVY, PVS, PVM. Results. The results obtained in the study indicate that Lamium plants could be alternative weed hosts of number important viral diseases including potatoes and other vegetables. Serological and molecular test results evidence plants were infected by Potato virus X, Potato virus Y, Potato virus M, Potato virus S and therefore Lamium L. species can serve as a potential source of inoculum for wide range of vegetables and ornamentals. This study is the first report of Lamium plants being naturally infected with Potato virus M and Potato virus S in central Europe. Conclusions. These plants are alternative host of mixed infection with viruses belonging to different families: Alphaflexiviridae, Betaflexiviridae and Potyviridae.

Visual Diagnosis of Pleural Tuberculosis and its Association with Tissue Biopsy, Culture and Xpert Assay

Introduction The diagnosis of pleural tuberculosis remains a clinical challenge due to the paucibacillary nature of disease. Medical thoracoscopy remains the gold standard in diagnosing tuberculous pleuritis. Objective To establish the diagnostic yield of sago-seed thoracoscopic appearance of pleura in tuberculosis and its correlation with histopathology, tissue AFB culture and tissue Xpert MTB/Rif assay. Methods All consecutive patients with lymphocytic exudative pleural effusion, who fulfilled inclusion criteria of the study underwent medical thoracoscopy under local anesthesia and pleural tissue was sent for histopathology, AFB culture and Xpert MTB/Rif assay. Chronic granulomatous inflammation on histopathology and response to anti-tuberculous treatment was taken as reference standard for diagnosis of tuberculous pleurisy. Results A total of 249 patients were included in the study, out of which 168 had effusion secondary to tuberculosis. Sago-like nodules visualized on thoracoscopy had a sensitivity of 58.9 %, specificity of 92.6 % and diagnostic accuracy of 69.88 % for pleural tuberculosis. There is a strong association between the presence of sago-like nodules and detection of mycobacterium tuberculosis on Xpert MTB/Rif assay and AFB culture of pleura (p-value 0.007). Conclusion Sago seed nodules on pleura have a high positive predictive value for tuberculous pleurisy. In high endemic countries patients with this finding on thoracoscopy can be commenced on anti-tuberculous treatment before histopathology or culture results are available.

Probing Loop-Mediated Isothermal Amplification (LAMP) targeting two gene-fragments of rose rosette virus

This study explores the development of Loop-mediated isothermal amplification (LAMP) for detection of rose rosette virus (RRV), a technique with the potential to be translated to rose nurseries. RRV is a negative-sense, single-stranded RNA virus which is a member of the genus Emaravirus (Family Fimoviridae) and the causal agent of the rose rosette disease (RRD). Although RRV symptoms are characteristics, early visual diagnosis of RRD can be misleading and confusing since it may appear like herbicide damage. Moreover, it may take incubation time for symptoms to appear after virus infection. Two sets of RRV gene sequences RNA3 and RNA4 were analyzed and two sets of four LAMP primers were designed. The direct antigen-capture method for direct trapping of RRV in plastic was used for RNA extraction followed by cDNA synthesis. RT-LAMP reactions were for 1 hour at 64°C (RRV-P3) and 66.5°C (RRV-P4) using either a thermocycler or a portable dry bath. RT-qLAMP was also optimized using DNA polymerase GspSSD LD using the same RRV sets of primers. RRV was detected in symptomatic and non-symptomatic RRD tissue from Oklahoma. The limit of detection (LoD) was 1pg/μL and 1 fg/μL using Bst 2.0 LAMP and GspSSD LD quantitative LAMP, respectively. In visual colorimetric pre- and post-reactions, the LoD was 10 pg/μL and 0.1 pg/μL using hydroxy naphthol blue (HNB, 120 μM) and SYBR green I (1:10 dilution), respectively. No cross-reactivity was detected in the RT-LAMP reaction testing cDNAs of eight commonly co-infecting rose viruses and one virus taxonomically related to RRV. Four different dyes were tested, and visible colorimetric reactions were obtained with RT-LAMP Bst 2.0 combined with SYBR I or HNB. RT-qLAMP with GspSSD2.0 offers LoD equal to RT-PCR and it is faster since it works with RNA directly.

Incrementally accumulated holographic SDP characteristic fusion method in ship propulsion shafting bearing fault diagnosis

To improve the accuracy of fault diagnosis of ship propulsion shaft bearing in a harsh working environment, a visual diagnosis method based on incrementally accumulated holographic symmetrical dot pattern (SDP) characteristic fusion method is proposed in this research. The current study simultaneously extracts the time- and frequency-domain characteristic parameters of vibration signal based on the incremental accumulation method to avoid inconspicuous difference and small discrimination generated by a single parameter. Subsequently, the extracted characteristic signals are transformed into a 2D image based on the SDP method to enhance the differences between signals. Eventually, bearing fault is diagnosed based on the similarity recognition method. Simulation and engineering experiments were conducted to verify the effectiveness of the proposed method. Results demonstrate that the proposed method can effectively diagnose the ship propulsion shaft bearing fault diagnosis.

System for neural network recognition of malignant pigmented skin neoplasms with image pre-processing

The article presents a system for the recognition of malignant pigmented skin neoplasms with a preliminary processing stage. Image pre-processing consists of removing hair structures from images, as well as resizing images and their further augmentation. Augmentation made it possible to increase the variety of training data, balance the number of images in different categories, and avoid retraining the neural network. The modeling was carried out using the MatLab R2020b software package for solving technical calculations on clinical dermatoscopic images from the international open archive ISIC Melanoma Project. The proposed system for the recognition of malignant pigmented skin neoplasms made it possible to increase the accuracy of image classification up to 80.55%. The use of the proposed recognition system will make it possible to increase the efficiency and quality of diagnosis, in comparison with the methods of visual diagnosis.

A miniPCR-Duplex Lateral Flow Dipstick Platform for Rapid and Visual Diagnosis of Lymphatic Filariae Infection

Lymphatic filariasis (LF) is a neglected major tropical disease that is a leading cause of permanent and long-term disability worldwide. Significant progress made by the Global Programme to Eliminate Lymphatic Filariasis (GPELF) has led to a substantial decrease in the levels of infection. In this limitation, DNA detection of lymphatic filariae could be useful due to it capable of detecting low level of the parasites. In the present study, we developed a diagnostic assay that combines a miniPCR with a duplex lateral flow dipstick (DLFD). The PCR primers were designed based on the HhaI and SspI repetitive noncoding DNA sequences of Brugia malayi and Wuchereria bancrofti, respectively. The limits of detection and crossreactivity of the assay were evaluated. In addition, blood samples were provided by Thais living in a brugian filariasis endemic area. The miniPCR-DLFD assay exhibited a detection limit of 2 and 4 mf per milliliter (mL) of blood for B. malayi as well as W. bancrofti, respectively, and crossamplification was not observed with 11 other parasites. The result obtained from the present study was in accordance with the thick blood smear staining for the known cases. Thus, a miniPCR-DLFD is an alternative tool for the diagnosis of LF in point-of-collection settings with a modest cost (~USD 5) per sample.

Neural network classification system for pigmented skin neoplasms with preliminary hair removal in photographs

The article proposes a neural network classification system for pigmented skin neoplasms with a preliminary processing stage to remove hair from the images. The main difference of the proposed system is the use of the stage of preliminary image processing to identify the location of the hair and their further removal. This stage allows you to prepare dermatoscopic images for further analysis in order to carry out automated classification and diagnosis of pigmented skin lesions. Modeling was carried out using the MatLAB R2020b software package on clinical dermatoscopic images from the international open archive ISIC Melanoma Project. The proposed system made it possible to increase the recognition accuracy of pigmented skin lesion images in 10 diagnostically important categories up to 80.81%. The use of the proposed system for the recognition and classification of images of dermatoscopic pigmented lesions by specialists will make it possible to increase the diagnostic efficiency in comparison with methods of visual diagnosis, and will also allow starting treatment at an earlier stage of the disease, which directly affects the survival and recovery rates for patients.