With recent advances in the field of deep learning, the use of convolutional neural networks (CNNs) in medical imaging has become very encouraging. The aim of our paper is to propose a patch-based CNN method for automated mass detection in full-field digital mammograms (FFDM). In addition to evaluating CNNs pretrained with the ImageNet dataset, we investigate the use of transfer learning for a particular domain adaptation. First, the CNN is trained using a large public database of digitized mammograms (CBIS-DDSM dataset), and then the model is transferred and tested onto the smaller database of digital mammograms (INbreast dataset). We evaluate three widely used CNNs (VGG16, ResNet50, InceptionV3) and show that the InceptionV3 obtains the best performance for classifying the mass and nonmass breast region for CBIS-DDSM. We further show the benefit of domain adaptation between the CBIS-DDSM (digitized) and INbreast (digital) datasets using the InceptionV3 CNN. Mass detection evaluation follows a fivefold cross-validation strategy using free-response operating characteristic curves. Results show that the transfer learning from CBIS-DDSM obtains a substantially higher performance with the best true positive rate (TPR) of 0.98 ± 0.02 at 1.67 false positives per image (FPI), compared with transfer learning from ImageNet with TPR of 0.91 ± 0.07 at 2.1 FPI. In addition, the proposed framework improves upon mass detection results described in the literature on the INbreast database, in terms of both TPR and FPI ; This work is partially supported by SMARTER project funded by Ministry of Economy and Competitiveness of Spain, under project reference DPI2015-68442-R.A. is funded by the support of the Secretariat of Universities and Research, Ministry of Economy and Knowledge, Government of Catalonia Ref. ECO/1794/2015 FIDGR-2016
The authors acknowledge the financial support of the funding agencies: Agence Nationale de la Recherche (contract ANR-15-CE31-0020), Centre National de la Recherche Scientifique (CNRS), Commission Europeenne (FEDER fund and Marie Curie Program), Institut Universitaire de France (IUF), LabEx UnivEarthS (ANR-10-LABX-0023 and ANR-18-IDEX-0001), Paris Ile-de-France Region, France; Shota Rustaveli National Science Foundation of Georgia (SRNSFG, FR-18-1268), Georgia; Deutsche Forschungsgemeinschaft (DFG), Germany; The General Secretariat of Research and Technology (GSRT), Greece; Istituto Nazionale di Fisica Nucleare (INFN), Ministero dell'Universita e della Ricerca (MUR), PRIN 2017 program (Grant NAT-NET 2017W4HA7S) Italy; Ministry of Higher Education, Scientific Research and Professional Training, Morocco; Nederlandse organisatie voor Wetenschappelijk Onderzoek (NWO), the Netherlands; The National Science Centre, Poland (2015/18/E/ST2/00758); National Authority for Scientific Research (ANCS), Romania; Ministerio de Ciencia, Innovacion, Investigacion y Universidades (MCIU): Programa Estatal de Generacion de Conocimiento (refs. PGC2018-096663-B-C41, -A-C42, -B-C43, -B-C44) (MCIU/FEDER), Severo Ochoa Centre of Excellence and MultiDark Consolider (MCIU), Junta de Andalucia (ref. SOMM17/6104/UGR), Generalitat Valenciana: Grisolia (ref. GRISOLIA/2018/119) and GenT (ref. CIDEGENT/2018/034) programs, La Caixa Foundation (ref. LCF/BQ/IN17/11620019), EU: MSC program (ref. 713673), Spain. ; The KM3NeT research infrastructure is currently under construction at two locations in the Mediterranean Sea. The KM3NeT/ORCA water-Cherenkov neutrino detector off the French coast will instrument several megatons of seawater with photosensors. Its main objective is the determination of the neutrino mass ordering. This work aims at demonstrating the general applicability of deep convolutional neural networks to neutrino telescopes, using simulated datasets for the KM3NeT/ORCA detector as an example. To this end, the networks are employed to achieve reconstruction and classification tasks that constitute an alternative to the analysis pipeline presented for KM3NeT/ORCA in the KM3NeT Letter of Intent. They are used to infer event reconstruction estimates for the energy, the direction, and the interaction point of incident neutrinos. The spatial distribution of Cherenkov light generated by charged particles induced in neutrino interactions is classified as shower- or track-like, and the main background processes associated with the detection of atmospheric neutrinos are recognized. Performance comparisons to machine-learning classification and maximum-likelihood reconstruction algorithms previously developed for KM3NeT/ORCA are provided. It is shown that this application of deep convolutional neural networks to simulated datasets for a large-volume neutrino telescope yields competitive reconstruction results and performance improvements with respect to classical approaches. ; French National Research Agency (ANR) ANR-15-CE31-0020 ; Centre National de la Recherche Scientifique (CNRS), Commission Europeenne (FEDER fund) ; European Union (EU) ; Institut Universitaire de France (IUF) ; LabEx UnivEarthS ANR-10-LABX-0023 ANR-18-IDEX-0001 ; Shota Rustaveli National Science Foundation of Georgia FR-18-1268 ; German Research Foundation (DFG) ; Greek Ministry of Development-GSRT ; Istituto Nazionale di Fisica Nucleare (INFN) ; Ministry of Education, Universities and Research (MIUR) Research Projects of National Relevance (PRIN) ; Ministry of Higher Education, Scientific Research and Professional Training, Morocco ; Netherlands Organization for Scientific Research (NWO) ; National Science Centre, Poland 2015/18/E/ST2/00758 ; National Authority for Scientific Research (ANCS), Romania ; Ministerio de Ciencia, Innovacion, Investigacion y Universidades PGC2018-096663-B-C41 A-C42 B-C43 B-C44 ; Severo Ochoa Centre of Excellence ; Junta de Andalucia SOMM17/6104/UGR ; Generalitat Valenciana: Grisolia GRISOLIA/2018/119 CIDEGENT/2018/034 ; La Caixa Foundation LCF/BQ/IN17/11620019 ; EU: MSC program 713673
In: International journal of sociotechnology and knowledge development: IJSKD ; an official publication of the Information Resources Management Association, Band 14, Heft 1, S. 1-18
Object identification has exploded alongside the remarkable progression of Convolutional Neural Network and its variations since 2012. Identification of objects in a field of computer vision has significantly increased especially to face and human subjects. Subsequently, computer vision has also addressed a global challenge on certain systems such as missing child detection in the last decade. However, there are certain challenges and limitations in the detection of children in the crowd only with face detection. Thus this paper proposes a Regional proposal based Convolutional Neural Network system that addresses the global challenges using three add-on features along with face. The real time dataset has been collected and the experimentations are conducted to validate the significance of the proposed system.
The article reviews the problems of eye bottom fundus analysis and semantic segmentation algorithms used to distinguish eye vessels, optical disk. Various diseases, such as glaucoma, hypertension, diabetic retinopathy, macular degeneration, etc., can be diagnosed by changes and anomalies of vesssels and optical disk. For semantic segmentation convolutional neural networks, especially U-Net architecture, are well suited. Recently a number of U-Net modifications have been developed that deliver excellent performance results.
Recognition of sleep patterns and posture has sparked interest in various clinical applications. Sleep postures can be monitored autonomously and constantly to provide useful information for decreasing health risks. Existing systems mostly use images to train the model to learn based on many sensors. For example, a camera, pressure sensor, and electrocardiogram. In this study, a model (named as SleepCon) was designed using deep learning, which will have the capability to train with any threshold image obtained from any sensor. This paper presented a system where data was obtained from a camera installed on the top of a mattress. The camera located the movement of the body posture on the mattress while the subject was lying down on the mattress. In doing so, CNN and other pre-processed steps took place to collect data and then analyze the data to recognize different sleep postures. This model was stored for use in real-time applications. The system can recognize the three major postures, i.e., left, right, and supine. A real-time application is also developed and operates the stored SleepCon model through an accompanying desktop application for detecting the posture live. The accuracy of classification was greater than 90%, while the actual application accuracy was 100% after carrying out the experiment on the SleepCon model. Doi: 10.28991/ESJ-2023-07-01-04 Full Text: PDF
The monitoring of threatened habitats is a key objective of European environmental policies. Due to the high cost of current field-based habitat mapping techniques, there is keen interest in proposing solutions that can reduce cost through increased levels of automation. Our study aims to propose a habitat mapping solution that benefits both from the merits of convolutional neural networks (CNNs) for image classification tasks, as well as from the high spatial, spectral, and multitemporal unmanned aerial vehicle image data, which shows great potential for accurate vegetation classification. The proposed CNN-based method uses multitemporal multispectral aerial imagery for the classification of threatened coastal habitats in the Maharees (Ireland) and shows a high level of classification accuracy. ; This project has received funding from the European Union's Horizon 2020 Research and Innovation program under the Marie Skłodowska-Curie Grant Agreement No. 847402. The authors would like to thank the EPA-funded iHabiMap project for providing the data used in this work. We thank the anonymous reviewers whose comments and suggestions helped improve and clarify this manuscript. The authors declare no conflicts of interest