Compressed Sensing MRI Reconstruction with Co-VeGAN: Complex-Valued Generative Adversarial Network

Activation functions play increasingly important roles in deep learning. The activation functions give the neural network the ability to learn complex patterns by introducing non-linearity. Complex-valued activation functions for complex-valued neural networks are extended from real-valued activation functions like sigmoid, tanh, rectified linear unit, and exponential linear unit. Recently, the most widely used complex-valued activation function is the real-imaginary-type activation function (RIAF), which applies separate real-valued activation functions on both the real and the imaginary parts of a neuron. This separate activation method ignores the internal relationship between the real and imaginary parts of the complex input and loses the integrity of activation. In this work, a complex-valued activation function called Gaussian-type activation function (GTAF) is proposed to activate the real and imaginary parts of a neuron jointly and enhance the learning ability and learning speed. GTAF consists of an ordinary real-valued activation function and a Gaussian function and is suitable for any given complex-valued neural network. Two polar-SAR image classification experiments on complex-valued convolutional neural networks show that GTAF converges faster than RIAF and has higher accuracy.

Conventional Convolutional Neural Networks (CNNs), which are realized in spatial domain, exhibit high computational complexity. This results in high resource utilization and memory usage and makes them unsuitable for implementation in resource and energy-constrained embedded systems. A promising approach for low-complexity and high-speed solution is to apply CNN modeled in the spectral domain. One of the main challenges in this approach is the design of activation functions. Some of the proposed solutions perform activation functions in spatial domain, necessitating multiple and computationally expensive spatial-spectral domain switching. On the other hand, recent work on spectral activation functions resulted in very computationally intensive solutions. This paper proposes a complex-valued activation function for spectral domain CNNs that only transmits input values that have positive-valued real or imaginary component. This activation function is computationally inexpensive in both forward and backward propagation and provides sufficient nonlinearity that ensures high classification accuracy. We apply this complex-valued activation function in a LeNet-5 architecture and achieve an accuracy gain of up to 7% for MNIST and 6% for Fashion MNIST dataset, while providing up to 79% and 85% faster inference times, respectively, over state-of-the-art activation functions for spectral domain.

HomeRadiologyVol. 231, No. 3 PreviousNext EditorialsMR Imaging: Its Development and the Recent Nobel PrizeStephen J. RiedererStephen J. RiedererAuthor Affiliations1From the MR Laboratory, Mayo Clinic, 200 First Street SW, Rochester, MN 55905. Received January 19, 2004; accepted January 21. Address correspondence to the author (e-mail: [email protected]).Stephen J. RiedererPublished Online:Jun 1 2004https://doi.org/10.1148/radiol.2313040114MoreSectionsFull textPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked In References 1 Lauterbur PC. Image formation by induced local interactions: examples employing nuclear magnetic resonance. Nature 1973; 242:190-191. Crossref, Google Scholar2 USA MRI market Mountain View, Calif: Frost and Sullivan Market Research, 2002. Google Scholar3 Mansfield P, Grannell PK. NMR “diffraction” in solids? J Phys C Solid State Phys 1973; 6:L422. Crossref, Google Scholar4 Mansfield P. Multi-planar image formation using NMR spin echoes. J Phys C 1977; 10:L55. Crossref, Google Scholar5 Haase A, Frahm J, Matthaei D, Hanicke W, Merboldt KD. FLASH imaging: rapid NMR imaging using low flip-angle pulses. J Magn Reson 1986; 67:258-266. Google Scholar6 Masaryk TJ, Modic MT, Ross JS, et al. Intracranial circulation: preliminary clinical results with three-dimensional (volume) MR angiography. Radiology 1989; 171:793-799. Link, Google Scholar7 Parker DL, Yuan C, Blatter DD. MR angiography by multiple thin slab 3D acquisition. Magn Reson Med 1991; 17:434-451. Crossref, Medline, Google Scholar8 Prince MR, Yucel EK, Kaufman JA, Harrison DC, Geller SC. Dynamic gadolinium-enhanced 3D abdominal MR arteriography. J Magn Reson Imaging 1993; 3:877-881. Crossref, Medline, Google Scholar9 Hennig J, Nauerth A, Friedburg H. RARE imaging: a fast imaging method for clinical MR. Magn Reson Med 1986; 3:823-833. Crossref, Medline, Google Scholar10 Mulkern RV, Wong STS, Winalski C, Jolesz FA. Contrast manipulation and artifact assessment of 2D and 3D RARE sequences. Magn Reson Imaging 1990; 8:557-566. Crossref, Medline, Google Scholar11 Hayes CE, Edelstein WA, Schenck JR, Mueller OM, Eash M. An efficient, highly homogeneous radiofrequency coil for whole-body NMR imaging at 1.5T. J Magn Reson 1985; 63:622-628. Google Scholar12 Roemer PB, Edelstein WA, Hayes CE, Souza SP, Mueller OM. The NMR phased array. Magn Reson Med 1990; 16:192-225. Crossref, Medline, Google Scholar13 Roemer PB, Edelstein WA. Self-shielded gradient coils (abstr) In: Book of abstracts: Society of Magnetic Resonance in Medicine 1986. Berkeley, Calif: Society of Magnetic Resonance in Medicine, 1986; 1067. Google Scholar14 Le Bihan D, Breton E, Lallemand D, Grenier P, Cabanis E, Laval-Jeantet M. MR imaging of intravoxel incoherent motions: application to diffusion and perfusion in neurologic disorders. Radiology 1986; 161:401-407. Link, Google Scholar15 Turner R, Le Bihan D, Maier J, Vavrek R, Hedges LK, Pekar J. Echo-planar imaging of intravoxel incoherent motion. Radiology 1990; 177:407-414. Link, Google Scholar16 Basser PJ, Mattiello J, Le Bihan D. MR diffusion tensor spectroscopy and imaging. Biophys J 1994; 66:259-267. Crossref, Medline, Google Scholar17 Wakana S, Jiang H, Nagae-Poetscher LM, van Zijl P, Mori S. Fiber tract-based atlas of human white matter anatomy. Radiology 2004; 230:77-87. Link, Google Scholar18 Belliveau JW, Kennedy DN, McKinstry RC, et al. Functional mapping of the human visual cortex by magnetic resonance imaging. Science 1991; 254:716-718. Crossref, Medline, Google Scholar19 Bandettini PA, Wong EC, Hinks RS, Tikofsky RS, Hyde JS. Time course EPI of human brain function during task activation. Magn Reson Med 1992; 25:390-397. Crossref, Medline, Google Scholar20 Kwong KK, Belliveau JW, Chesler DA, et al. Dynamic magnetic resonance imaging of human brain activity during primary sensory stimulation. Proc Natl Acad Sci U S A 1992; 89:5675-5679. Crossref, Medline, Google Scholar21 Ogawa S, Tank D, Menon R, et al. Intrinsic signal changes accompanying sensory stimulation: functional brain mapping using MRI. Proc Natl Acad Sci U S A 1992; 89:5951-5955. Crossref, Medline, Google Scholar22 Ogawa S, Lee TM, Kay AR, Tank DW. Brain magnetic resonance imaging with contrast dependent on blood oxygenation. Proc Natl Acad Sci U S A 1990; 87:9868-9872. Crossref, Medline, Google Scholar23 Johnson GA, Benveniste H, Black RD, Hedlund LW, Maronpot RR, Smith BR. Histology by magnetic-resonance microscopy. Magn Reson Q 1993; 9:1-30. Medline, Google Scholar24 Paulus MJ, Sari-Sarraff H, Gleason SS, et al. A new x-ray computed tomography system for laboratory mouse imaging. IEEE Trans Nucl Sci 1999; 46:558-564. Crossref, Google Scholar25 Kruger RA, Mistretta CA, Houk TL, et al. Computerized fluoroscopy in real time for noninvasive visualization of the cardiovascular system: preliminary studies. Radiology 1979; 130:49-57. Link, Google ScholarArticle HistoryPublished in print: June 2004 FiguresReferencesRelatedDetailsCited ByMedicine, Vol. 93, No. 28Skeletal Radiology, Vol. 40, No. 9Medicine - Programa de Formaci?n M?dica Continuada Acreditado, Vol. 9, No. 92Magnetic Resonance Imaging, Vol. 24, No. 4Applied Magnetic Resonance, Vol. 29, No. 1Pacing and Clinical Electrophysiology, Vol. 28, No. 10Magnetic Resonance Imaging, Vol. 22, No. 10Recommended Articles RSNA Education Exhibits RSNA Case Collection Vol. 231, No. 3 Metrics Altmetric Score PDF download

Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network

An understanding of data acquisition and processing in magnetic resonance imaging (MRI) facilitates subsequent manipulation and analysis of the resultant images. Unlike other medical imaging modalities, MRI is not well described in terms of the transmission and reception of a propagating wave since the wavelength of the radiofrequency signals involved is on the order of meters. Rather, MRI exploits the fact that the magnetization vectors associated with certain atoms (notably protons in water) will, when placed in a strong magnetic field, oscillate at a frequency proportional to that field. By spatially varying the magnetic field, position is mapped by the frequency and phase of the field effects caused by the oscillating magnetization vectors at each location. The data acquisition associated with this spatial mapping can be described as temporally scanning the Fourier or spatial frequency domain of the volume of interest. Image reconstruction is achieved by an inverse Fourier transform of the received signal. The Fourier representation of the imaging process is developed from an overview of the physics underlying MRI signal behaviour. Under this formalism, trade-offs in acquisition time, resolution, and field-of-view as well as image degradation associated with noise are addressed. Finally, the ability in MRI to manipulate soft tissue contrast over a wide range of independent parameters is outlined. >

Fast acquisition in magnetic resonance imaging (MRI) is considered in this paper. Often, fast acquisition is achieved using parallel imaging (pMRI) techniques. It has been shown recently that the combination of pMRI and compressed sensing (CS), which enables exact reconstruction of sparse or compressible signals from a small number of random measurements, can accelerate the speed of MRI acquisition because the number of measurements are much smaller than that by pMRI per se. Also recently in CS, chaos filters were designed to obtain chaotic measurements. This chaotic CS approach potentially offers simpler hardware implementation. In this paper, we combine chaotic CS and pMRI. However, instead of using chaos filters, the measurements are obtained by chaotically undersampling the k-space. MRI image reconstruction is then performed by using nonlinear conjugate gradient optimization. For pMRI, we use the well-known approach SENSE - sensitivity encoding -, which requires an estimation of the sensitivity maps. The performance of the proposed method is analyzed using the point spread function, the transform point spread function, and the reconstruction error measure.

ABSTRACTWe compared the qualitative and quantitative quality of prostate conventional T2-weighted imaging and T2-weighted imaging with deep-learning reconstruction. Patients with suspected prostate cancer undergoing magnetic resonance imaging between April 2022 and June 2023 were included. Quantitative analysis was performed to determine the signal-to-noise and contrast ratios of the perirectal fat tissue, internal obturator muscle, and pubic tubercle. Eight periprostatic anatomical structures, overall image quality, and motion artifacts were evaluated by two radiologists using 5- or 4-point scales. Qualitative analysis results were compared to determine the agreement between the two radiologists. In total, 106 patients (mean age: 71 ± 8.3 years; 106 men) were included in this study. The acquisition time for conventional T2-weighted imaging and T2-weighted imaging with deep-learning reconstruction was 4 min and 16 s and 2 min and 12 s, respectively. The signal-to-noise ratio of the perirectal fat tissue and internal obturator muscle and contrast ratio of fat/muscle and bone/muscle determined via T2-weighted imaging with deep-learning reconstruction were significantly superior to those determined via conventional T2-weighted imaging (both p < 0.01). Compared with conventional T2-weighted imaging, T2-weighted imaging with deep-learning reconstruction showed significant improvement in the visualization of the periprostatic anatomy, overall image quality, and motion artifacts (both p < 0.05). Compared with conventional methods, T2-weighted imaging with deep-learning reconstruction facilitated the acquisition of good-quality magnetic resonance images of the prostate within a shorter acquisition time. T2-weighted imaging with deep-learning reconstruction will aid clinicians in diagnosing prostate cancer with shortened acquisition time while maintaining quantitative and qualitative image properties.

BackgroundHigh-spatial resolution magnetic resonance imaging (MRI) is essential for imaging ankle joints. However, the clinical application of fast spin-echo sequences remains limited by their lengthy acquisition time. Artificial intelligence-assisted compressed sensing (ACS) technology has been recently introduced as an integrative acceleration solution. We compared ACS-accelerated 3-T ankle MRI to conventional methods of compressed sensing (CS) and parallel imaging (PI) .MethodsWe prospectively included 2 healthy volunteers and 105 patients with ankle pain. ACS acceleration factors for ankle protocol of T1-, T2-, and proton density (PD)-weighted sequences were optimized in a pilot study on healthy volunteers (acceleration factor 3.2–3.3×). Images of patients acquired using ACS and conventional acceleration methods were compared in terms of acquisition times, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), subjective image quality, and diagnostic agreement. Shapiro-Wilk test, Cohen κ, intraclass correlation coefficient, and one-way ANOVA with post hoc tests (Tukey or Dunn) were used.ResultsACS acceleration reduced the acquisition times of T1-, T2-, and PD-weighted sequences by 32−43%, compared with conventional CS and PI, while maintaining image quality (mostly higher SNR with p < 0.004 and higher CNR with p < 0.047). The diagnostic agreement between ACS and conventional sequences was rated excellent (κ = 1.00).ConclusionsThe optimum ACS acceleration factors for ankle MRI were found to be 3.2–3.3× protocol. The ACS allows faster imaging, yielding similar image quality and diagnostic performance.Relevance statementAI-assisted compressed sensing significantly accelerates ankle MRI times while preserving image quality and diagnostic precision, potentially expediting patient diagnoses and improving clinical workflows.Key points• AI-assisted compressed sensing (ACS) significantly reduced scan duration for ankle MRI.• Similar image quality achieved by ACS compared to conventional acceleration methods.• A high agreement by three acceleration methods in the diagnosis of ankle lesions was observed.Graphical

The recently introduced Compressed Sensing (CS) theory explains how sparse or compressible signals can be reconstructed from far fewer samples than what was previously believed possible. The CS theory has attracted significant attention for applications such as Magnetic Resonance Imaging (MRI) where long acquisition times have been problematic. This is especially true for dynamic MRI applications where high spatio-temporal resolution is needed. For example, in cardiac cine MRI, it is desirable to acquire the whole cardiac volume within a single breath-hold in order to avoid artifacts due to respiratory motion. Conventional MRI techniques do not allow reconstruction of high resolution image sequences from such limited amount of data. Vaswani et al. recently proposed an extension of the CS framework to problems with partially known support (i.e. sparsity pattern). In their work, the problem of recursive reconstruction of time sequences of sparse signals was considered. Under the assumption that the support of the signal changes slowly over time, they proposed using the support of the previous frame as the "known" part of the support for the current frame. While this approach works well for image sequences with little or no motion, motion causes significant change in support between adjacent frames. In this paper, we illustrate how motion estimation and compensation techniques can be used to reconstruct more accurate estimates of support for image sequences with substantial motion (such as cardiac MRI). Experimental results using phantoms as well as real MRI data sets illustrate the improved performance of the proposed technique.

Magnetic resonance imaging (MRI) is crucial for accurately diagnosing a wide spectrum of musculoskeletal conditions due to its superior soft tissue contrast resolution. However, the long acquisition times of traditional two-dimensional (2D) and three-dimensional (3D) fast and turbo spin-echo (TSE) pulse sequences can limit patient access and comfort. Recent technical advancements have introduced acceleration techniques that significantly reduce MRI times for musculoskeletal examinations. Key acceleration methods include parallel imaging (PI), simultaneous multi-slice acquisition (SMS), and compressed sensing (CS), enabling up to eightfold faster scans while maintaining image quality, resolution, and safety standards. These innovations now allow for 3- to 6-fold accelerated clinical musculoskeletal MRI exams, reducing scan times to 4 to 6min for joints and spine imaging. Evolving deep learning-based image reconstruction promises even faster scans without compromising quality. Current research indicates that combining acceleration techniques, deep learning image reconstruction, and superresolution algorithms will eventually facilitate tenfold accelerated musculoskeletal MRI in routine clinical practice. Such rapid MRI protocols can drastically reduce scan times by 80-90% compared to conventional methods. Implementing these rapid imaging protocols does impact workflow, indirect costs, and workload for MRI technologists and radiologists, which requires careful management. However, the shift from conventional to accelerated, deep learning-based MRI enhances the value of musculoskeletal MRI by improving patient access and comfort and promoting sustainable imaging practices. This article offers a comprehensive overview of the technical aspects, benefits, and challenges of modern accelerated musculoskeletal MRI, guiding radiologists and researchers in this evolving field.

Introduction: Patients at high risk for developing breast cancer are potential beneficiaries of personalized screening strategies. Breast magnetic resonance imaging (MRI) has shown high sensitivity, but its broader use remains constrained by issues such as high cost and long examination time. The abbreviated magnetic resonance protocol is presented as an alternative to overcome these challenges. Our primary outcome was to evaluate the concordance of the final report between full and abbreviated protocols. Secondary outcomes included the acquisition and reading time of images from the abbreviated protocol. Methods: A cross-sectional study was conducted on asymptomatic women at moderate and high risk for breast cancer who underwent the full MRI screening protocol in private health institutions in the city of Belo Horizonte, Brazil. The abbreviated protocol was derived from the full protocol by the computer through selection of specific sequences. Each image was independently blind read, and assigned a category from the Breast Imaging - Reporting and Data System (BI-RADS) by at least two examiners. The results were then compared using the Cohen's kappa and Intraclass Correlation Coefficients. Results: The study included 170 women, and a concordance rate of 96,9% was found for the reported BI-RADS category between protocols in this population. A 21-minute reduction was observed in examination time for the abbreviated protocol. Conclusion: The significant concordance between protocols indicates that despite the reduction in acquisition time, number of acquired images, and method's complexity, the abbreviated MRI protocol meets most screening demands. It is, therefore, a viable alternative for cost reduction and improving patients tolerability for the studied population. Table 1. Clinical characteristics of the study population Absolute and percentage data about age, personal risk for breast cancer, family history, and previous genetic testing in the study population. Table 2. Concordance analysis between abbreviated and complete MRI protocols based on the ACR-BIRADS classification - Coen Kappa and Intraclass Correlation Coefficient The Kappa value of 0.9687 (95% CI 0.9426 - 0.9949, p &amp;lt; 0.01) indicates almost perfect concordance between the two protocols. The intraclass correlation coefficient of 0.982 (95% CI 0.97 - 0.987, p &amp;lt; 0.01), also indicates excellent concordance using the two-way random effect models criteria. Citation Format: Mariana Mitraud Ottoni Guedes, Agnaldo Lopes da Silva Filho, Thais Paiva Moraes, Adriene Moraes Campos, Ivie Braga de Paula, Felipe Marcondes de Oliveira Coelho, Barbara Silveira Santana, Bertha Andrade Coelho, Maria Fernanda Sperotto Valadares Gontijo, Leticia Martins De Araujo Campos Linhares, Anna Dias Salvador, Waldeir José de Almeida Junior, José Tadeu Campos de Avelar. Concordance between abbreviated and complete magnetic resonance protocols for screening woman at moderate and high risk for breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-07-11.

Magnetic resonance imaging (MRI) is the keystone of modern musculoskeletal imaging; however, long pulse sequence acquisition times may restrict patient tolerability and access. Advances in MRI scanners, coil technology, and innovative pulse sequence acceleration methods enable 4-fold turbo spin echo pulse sequence acceleration in clinical practice; however, at this speed, conventional image reconstruction approaches the signal-to-noise limits of temporal, spatial, and contrast resolution. Novel deep learning image reconstruction methods can minimize signal-to-noise interdependencies to better advantage than conventional image reconstruction, leading to unparalleled gains in image speed and quality when combined with parallel imaging and simultaneous multislice acquisition. The enormous potential of deep learning-based image reconstruction promises to facilitate the 10-fold acceleration of the turbo spin echo pulse sequence, equating to a total acquisition time of 2-3 minutes for entire MRI examinations of joints without sacrificing spatial resolution or image quality. Current investigations aim for a better understanding of stability and failure modes of image reconstruction networks, validation of network reconstruction performance with external data sets, determination of diagnostic performances with independent reference standards, establishing generalizability to other centers, scanners, field strengths, coils, and anatomy, and building publicly available benchmark data sets to compare methods and foster innovation and collaboration between the clinical and image processing community. In this article, we review basic concepts of deep learning-based acquisition and image reconstruction techniques for accelerating and improving the quality of musculoskeletal MRI, commercially available and developing deep learning-based MRI solutions, superresolution, denoising, generative adversarial networks, and combined strategies for deep learning-driven ultra-fast superresolution musculoskeletal MRI. This article aims to equip radiologists and imaging scientists with the necessary practical knowledge and enthusiasm to meet this exciting new era of musculoskeletal MRI.

Functional magnetic resonance (MR) imaging is a complex, specialized examination that is able to noninvasively measure information critical to patient care such as hemispheric language lateralization ( 1 ). Diagnostic functional MR imaging requires extensive patient interaction as well as the coordinated efforts of the entire health care team. We observed in our practice at an academic center that the times to perform functional MR imaging examinations were excessively lengthy, making scheduling of the examination difficult. The purpose of our project was to reduce functional MR imaging acquisition times by increasing the efficiency of our workflow, using specific quality tools to drive improvement of functional MR imaging. We assembled a multidisciplinary team and retrospectively reviewed all functional MR imaging examinations performed at our institution from January 2013 to August 2015. We identified five key drivers: (a) streamlined protocols, (b) consistent patient monitoring, (c) clear visual slides and audio, (d) improved patient understanding, and (e) minimized patient motion. We then implemented four specific interventions over a period of 10 months: (a) eliminating intravenous contrast medium, (b) reducing repeated language paradigms, (c) updating technologist and physician checklists, and (d) updating visual slides and audio. Our mean functional MR imaging acquisition time was reduced from 76.3 to 53.2 minutes, while our functional MR imaging examinations remained of diagnostic quality. As a result, we reduced our routine scheduling time for functional MR imaging from 2 hours to 1 hour, improving patient comfort and satisfaction as well as saving time for additional potential MR imaging acquisitions. Our efforts to optimize functional MR imaging workflow constitute a practice quality improvement project that is beneficial for patient care and can be applied broadly to other functional MR imaging practices. ©RSNA, 2017.

Mild traumatic brain injury (mTBI) sustained in early childhood affects the brain at a peak developmental period and may disrupt sensitive stages of skill acquisition, thereby compromising child functioning. However, due to the challenges of collecting non-sedated neuroimaging data in young children, the consequences of mTBI on young children's brains have not been systematically studied. In typically developing preschool children (of age 3-5years), a brief behavioral-play familiarization provides an effective alternative to sedation for acquiring awake magnetic resonance imaging (MRI) in a time- and resource-efficient manner. To date, no study has applied such an approach for acquiring non-sedated MRI in preschool children with mTBI who may present with additional MRI acquisition challenges such as agitation or anxiety. The present study aimed to compare the effectiveness of a brief behavioral-play familiarization for acquiring non-sedated MRI for research purposes between young children with and without mTBI, and to identify factors associated with successful MRI acquisition. Preschool children with mTBI (n=13) and typically developing children (n=24) underwent a 15-minutes behavioral-play MRI familiarization followed by a 35-minutes non-sedated MRI protocol. Success rate was compared between groups, MRI quality was assessed quantitatively, and factors predicting success were documented. Among the 37 participants, 15 typically developing children (63%) and 10 mTBI (77%) reached the MRI acquisition success criteria (i.e., completing the two first sequences). The success rate was not significantly different between groups (p=.48; 95% CI [-0.36 14.08]; Cramer's V=.15). The images acquired were of high-quality in 100% (for both groups) of the structural images, and 60% (for both groups) of the diffusion images. Factors associated with success included older child age (Β=0.73, p=.007, exp(B)=3.11, 95% CI [1.36 7.08]) and fewer parental concerns (Β=-1.56, p=.02, exp(Β)=0.21, 95% CI [0.05 0.82]) about the MRI procedure. Using brief behavioral-play familiarization allows acquisition of high-quality non-sedated MRI in young children with mTBI with success rates comparable to those of non-injured peers.

Purpose: A powerful imaging method for evaluating brain patches is resting-state functional Magnetic Resonance (rs-fMRI) Imaging, in which the subject is at rest. Artificial Neural Networks (ANN) are one of the several Alzheimer's Disease (AD) analysis and diagnosis methods used in this study. We investigate ANNs' ability to diagnose AD using rs-fMRI data.&#x0D; Materials and Methods: The acquisition of functional and structural magnetic resonance imaging was applied for 15 AD, 17 mild cognitive impairment, and ten normal healthy participants. Time series of blood oxygen level-dependent were extracted from the multi-subject dictionary learning brain atlas after pre-processing. This study develops a one-dimensional Convolutional Neural Network (CNN) using extracted signals of the functional atlas for differential diagnosis of AD.&#x0D; Results: Applying the proposed method to rs-fMRI signals for classifying three classes of Alzheimer’s patients resulted in overall accuracy, F1-score, and precision of 0.685, 0.663, and 0.681, respectively. Using 39 regions in the brain and proposing a quite simple network than most of the available deep learning-based methods are the main advantages of this model.&#x0D; Conclusion: rs-fMRI signal recognition based on a functional atlas with the application of a deep neural network has a pattern recognition capability that can make a differential diagnosis with an acceptable level of accuracy and precision. Therefore, deep neural networks can be considered as a tool for the early diagnosis of AD.