Search

Whole genome sequencing of bacteria is important to enable strain classification. Using entire genomes as an input to machine learning (ML) models would allow rapid classification of strains while using information from multiple genetic elements. We developed a "bag-of-words" approach to encode, using SentencePiece or k-mer tokenization, entire bacterial genomes and analyze these with ML. Initial model selection identified SentencePiece with 8,000 and 32,000 words as the best approach for genome tokenization. We then classified in Neisseria meningitidis genomes the capsule B group genotype with 99.6% accuracy and the multifactor invasive phenotype with 90.2% accuracy, in an independent test set. Subsequently, in silico knockouts of 2,808 genes confirmed that the ML model predictions aligned with our current understanding of the underlying biology. To our knowledge, this is the first ML method using entire bacterial genomes to classify strains and identify genes considered relevant by the classifier., Competing Interests: M.P. and S.B. disclose that their postdoctoral grant at the University of Pisa, Italy, is funded by GSK. Outside of the submitted work, S.B. also discloses having received grants from the University of Siena, Italy and the University of Tuscia, Viterbo, Italy; payment or honoraria for lectures, presentations, speakers’ bureaus, manuscript writing or educational events from the University of Siena, Italy, University of Bari, Italy, and the Italica Academy srl. A.P., A.B., G.R., A.M., and M.B. are employed by GSK. M.S. was an intern at GSK during the time of the study. G.R. holds shares in GSK and in Novartis AG. A.M. holds shares in GSK. C.P. and A.S. disclose that GSK commissioned this research. The authors declare no other financial and non-financial relationships and activities and no other conflicts of interest., (© 2024 GSK.)

Background: Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists' experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM)., Objective: We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL)., Methods: A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated "iDCNN_aMSL" model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models., Results: In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %)., Conclusions: The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions., Competing Interests: Declaration of Competing Interest The authors report no declarations of interest., (Copyright © 2020 Japanese Society for Investigative Dermatology. Published by Elsevier B.V. All rights reserved.)

Background and Objectives: Deep learning models and specifically Convolutional Neural Networks (CNNs) are becoming the leading approach in many computer vision tasks, including medical image analysis. Nevertheless, the CNN training usually requires large sets of supervised data, which are often difficult and expensive to obtain in the medical field. To address the lack of annotated images, image generation is a promising method, which is becoming increasingly popular in the computer vision community. In this paper, we present a new approach to the semantic segmentation of bacterial colonies in agar plate images, based on deep learning and synthetic image generation, to increase the training set size. Indeed, semantic segmentation of bacterial colony is the basis for infection recognition and bacterial counting in Petri plate analysis., Methods: A convolutional neural network (CNN) is used to separate the bacterial colonies from the background. To face the lack of annotated images, a novel engine is designed - which exploits a generative adversarial network to capture the typical distribution of the bacterial colonies on agar plates - to generate synthetic data. Then, bacterial colony patches are superimposed on existing background images, taking into account both the local appearance of the background and the intrinsic opacity of the bacterial colonies, and a style transfer algorithm is used for further improve visual realism., Results: The proposed deep learning approach has been tested on the only public dataset available with pixel-level annotations for bacterial colony semantic segmentation in agar plates. The role of including synthetic data in the training of a segmentation CNN has been evaluated, showing how comparable performances can be obtained with respect to the use of real images. Qualitative results are also reported for a second public dataset in which the segmentation annotations are not provided., Conclusions: The use of a small set of real data, together with synthetic images, allows obtaining comparable results with respect to using a complete set of real images. Therefore, the proposed synthetic data generator is able to address the scarcity of biomedical data and provides a scalable and cheap alternative to human ground-truth supervision., Competing Interests: Declaration of Competing Interest None., (Copyright © 2019. Published by Elsevier B.V.)

In this paper, we present the analysis and results of a direct measurement of the cosmic-ray proton spectrum with the CALET instrument onboard the International Space Station, including the detailed assessment of systematic uncertainties. The observation period used in this analysis is from October 13, 2015 to August 31, 2018 (1054 days). We have achieved the very wide energy range necessary to carry out measurements of the spectrum from 50 GeV to 10 TeV covering, for the first time in space, with a single instrument the whole energy interval previously investigated in most cases in separate subranges by magnetic spectrometers (BESS-TeV, PAMELA, and AMS-02) and calorimetric instruments (ATIC, CREAM, and NUCLEON). The observed spectrum is consistent with AMS-02 but extends to nearly an order of magnitude higher energy, showing a very smooth transition of the power-law spectral index from -2.81±0.03 (50-500 GeV) neglecting solar modulation effects (or -2.87±0.06 including solar modulation effects in the lower energy region) to -2.56±0.04 (1-10 TeV), thereby confirming the existence of spectral hardening and providing evidence of a deviation from a single power law by more than 3σ.

Extended results on the cosmic-ray electron + positron spectrum from 11 GeV to 4.8 TeV are presented based on observations with the Calorimetric Electron Telescope (CALET) on the International Space Station utilizing the data up to November 2017. The analysis uses the full detector acceptance at high energies, approximately doubling the statistics compared to the previous result. CALET is an all-calorimetric instrument with a total thickness of 30 X_{0} at normal incidence and fine imaging capability, designed to achieve large proton rejection and excellent energy resolution well into the TeV energy region. The observed energy spectrum in the region below 1 TeV shows good agreement with Alpha Magnetic Spectrometer (AMS-02) data. In the energy region below ∼300  GeV, CALET's spectral index is found to be consistent with the AMS-02, Fermi Large Area Telescope (Fermi-LAT), and Dark Matter Particle Explorer (DAMPE), while from 300 to 600 GeV the spectrum is significantly softer than the spectra from the latter two experiments. The absolute flux of CALET is consistent with other experiments at around a few tens of GeV. However, it is lower than those of DAMPE and Fermi-LAT with the difference increasing up to several hundred GeV. The observed energy spectrum above ∼1  TeV suggests a flux suppression consistent within the errors with the results of DAMPE, while CALET does not observe any significant evidence for a narrow spectral feature in the energy region around 1.4 TeV. Our measured all-electron flux, including statistical errors and a detailed breakdown of the systematic errors, is tabulated in the Supplemental Material in order to allow more refined spectral analyses based on our data.

First results of a cosmic-ray electron and positron spectrum from 10 GeV to 3 TeV is presented based upon observations with the CALET instrument on the International Space Station starting in October, 2015. Nearly a half million electron and positron events are included in the analysis. CALET is an all-calorimetric instrument with total vertical thickness of 30 X_{0} and a fine imaging capability designed to achieve a large proton rejection and excellent energy resolution well into the TeV energy region. The observed energy spectrum over 30 GeV can be fit with a single power law with a spectral index of -3.152±0.016 (stat+syst). Possible structure observed above 100 GeV requires further investigation with increased statistics and refined data analysis.

Urinary tract infections (UTIs) are considered to be the most common bacterial infection and, actually, it is estimated that about 150 million UTIs occur world wide yearly, giving rise to roughly $6 billion in healthcare expenditures and resulting in 100,000 hospitalizations. Nevertheless, it is difficult to carefully assess the incidence of UTIs, since an accurate diagnosis depends both on the presence of symptoms and on a positive urinoculture, whereas in most outpatient settings this diagnosis is made without an ad hoc analysis protocol. On the other hand, in the traditional urinoculture test, a sample of midstream urine is put onto a Petri dish, where a growth medium favors the proliferation of germ colonies. Then, the infection severity is evaluated by a visual inspection of a human expert, an error prone and lengthy process. In this paper, we propose a fully automated system for the urinoculture screening that can provide quick and easily traceable results for UTIs. Based on advanced image processing and machine learning tools, the infection type recognition, together with the estimation of the bacterial load, can be automatically carried out, yielding accurate diagnoses. The proposed AID (Automatic Infection Detector) system provides support during the whole analysis process: first, digital color images of Petri dishes are automatically captured, then specific preprocessing and spatial clustering algorithms are applied to isolate the colonies from the culture ground and, finally, an accurate classification of the infections and their severity evaluation are performed. The AID system speeds up the analysis, contributes to the standardization of the process, allows result repeatability, and reduces the costs. Moreover, the continuous transition between sterile and external environments (typical of the standard analysis procedure) is completely avoided., (Copyright © 2016 Elsevier Ltd. All rights reserved.)