From amri.wuye at gmail.com Fri Aug 6 16:23:50 2021 From: amri.wuye at gmail.com (Wu Ye) Date: Fri, 6 Aug 2021 16:23:50 -0400 Subject: [Neuroimaging] Postdoctoral Positions in Artificial Intelligence for Radiation Oncology Message-ID: <4F5897AF-274C-407D-8589-68FEDD6A71F4@gmail.com> Hi all, Multiple postdoctoral positions in artificial intelligence for radiation oncology are available in the Department of Radiation Oncology and Biomedical Research Imaging Center (BRIC) at the University of North Carolina at Chapel Hill (UNC-Chapel Hill). The successful candidate should have a strong background in Computer Science, Electrical Engineering, Biomedical Engineering, or Medical Physics, preferably with an emphasis on deep learning, image analysis, and big data. Experience in medical image segmentation, registration, and optimization for radiation therapy is highly desirable. Proficiency in programming (good command of LINUX, C and C++, and Python) is required. The research will focus on developing and validating learning-based segmentation methods for multimodal pelvic images for radiation treatment. Another research focus is on the automatic detection and prediction of brain tumors based on MR images. The successful candidates will be part of a multidisciplinary group including computer scientists, medical physicists, biostatisticians, and radiation oncologists. The new research will build upon the group?s previous work on medical image analysis using artificial intelligence. If interested, please email resume and list of references to project advisors Dr. Jun Lian (jun_lian at med.unc.edu) and Dr. Pew-Thian Yap (ptyap at med.unc.edu). UNC-Chapel Hill is one of the top public universities in the US. The cancer center and BRIC have a national reputation in cutting-edge research, clinical care, and training next-generation professionals. Chapel Hill, NC, routinely ranks as one of the best college towns and best places to live and raise a family in the United States. Further details can be found at attachment. Best regards Ye -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Postdoctoral Positions_Lian_Yap.pdf Type: application/pdf Size: 66611 bytes Desc: not available URL: -------------- next part -------------- An HTML attachment was scrubbed... URL: From eran_dayan at med.unc.edu Mon Aug 9 07:28:23 2021 From: eran_dayan at med.unc.edu (Dayan, Eran) Date: Mon, 9 Aug 2021 11:28:23 +0000 Subject: [Neuroimaging] Postdoctoral Research Associate position in deep learning at UNC Chapel Hill Message-ID: A Postdoctoral Research Associate position is immediately open in the Neuroinformatics lab (dayanlab.web.unc.edu) at the Biomedical Research Imaging Center, University of North Carolina at Chapel Hill. The position is open to accomplished and highly motivated candidates, with an interest in machine learning and clinical neuroscience. The lab focuses on fundamental questions relating to brain organization in neurodegenerative diseases, while aiming to develop methods and tools that could eventually be used in the clinic. The Postdoctoral Research Associate will develop diagnostic and prognostic deep learning models for Alzheimer?s disease using rich existing multimodal datasets. Ample training and career development opportunities will be provided, as well as opportunities to collaborate with other groups within and outside UNC. A recent (<2 years) doctoral degree in biomedical engineering, computer science, computational neuroscience, biomedical data science, physics or other related fields is required. Excellent quantitative background, experience in deep learning, relevant programming experience, and a track record of first-author publications in peer-reviewed journals are required. Interest and experience in clinical neuroscience, particularly in Alzheimer?s disease research, would be advantageous but is not required. To apply, please send your C.V, and the names and contact details of at least 2 referees to Dr. Eran Dayan at: eran_dayan at med.unc.edu The University of North Carolina at Chapel Hill is an equal opportunity and affirmative action employer. All qualified applicants will receive consideration for employment without regard to age, color, disability, gender, gender expression, gender identity, genetic information, race, national origin. -------------- next part -------------- An HTML attachment was scrubbed... URL: From markiewicz at stanford.edu Mon Aug 9 16:13:48 2021 From: markiewicz at stanford.edu (Christopher Markiewicz) Date: Mon, 9 Aug 2021 20:13:48 +0000 Subject: [Neuroimaging] [Nibabel] Discourse category for Surface API discussions Message-ID: Hi all, I'm starting to work on the Surface API portion of the Nibabel grant. I've created a category on the Discourse here: https://nipy.discourse.group/c/surface-api/10 And I've started some initial notes here mostly laying out the problem: https://nipy.discourse.group/t/preliminary-notes-on-surface-representations/57 The next steps are going to be to identify use cases for people working with surface data, which will also involve finding people who I may not know about, so please forward this on to people who might be interested in joining the discussion. -- Christopher J. Markiewicz, PhD Center for Reproducible Neuroscience Stanford University From frakkopesto at gmail.com Mon Aug 9 19:23:32 2021 From: frakkopesto at gmail.com (frakkopesto) Date: Mon, 9 Aug 2021 18:23:32 -0500 Subject: [Neuroimaging] Register for the 2021 Workshop of the Advanced Computational Neuroscience Message-ID: Dear Colleagues We would appreciate it greatly if you could share the attached announcement to the appropriate lists and individuals. Best regards, Franco *FRANCO PESTILLI*, *Ph.D.* | *Associate Professor* Department of Psychology | College of Liberal Arts | The University of Texas at Austin he/him | pestilli at utexas.edu | web | GitHub | brainlife.io ---------- Forwarded message --------- From: Sepideh Sadaghiani Date: Mon, Aug 2, 2021 at 4:52 PM Subject: Register for the 2021 Workshop of the Advanced Computational Neuroscience Network To: Sept. 2-3 virtual event with in-person opening event at Beckman Institute, Illinois Click here to see this online [image: University of Illinois Urbana-Champaign] Beckman Institute for Advanced Science and Technology [image: Beckman Institute at the University of Illinois] *Register for the 2021 Workshop of the Advanced Computational Neuroscience Network (ACNN)* *Thursday, Sept. 2 and Friday, Sept. 3* Virtual event with in-person opening The ACNN 2021 meeting examines the re-emergence of neuroimaging of brain networks as we exit the pandemic with larger machines, higher resolution data, and larger cohorts on the horizon to address societal challenges from aging, social equality, and infectious diseases. This virtual meeting seeks to foster a collaborative exchange of information, data, and techniques across the Midwest, and beyond, to enable us to improve our understanding of brain organization and function and prepare us to solve the challenges of the future. See the workshop's web page for a full schedule. REGISTER NOW *Nalbandov Public Lecture* *Kamil Ugurbil of the University of Minnesota*3 p.m. CDT Thursday, Sept. 2 Via Zoom and livestreamed in the Beckman Institute Auditorium 405 N. Mathews Ave., Urbana, Illinois [image: Kamil Ugurbil] Kamil Ugurbil *Keynote speakers* *Jean-Baptiste Poline of McGill University* *Shella Kleiholz of Georgia Tech* [image: Poline and Kleiholz] Poline, left, and Kleiholz, right *Zoom lectures from:* Monica Rosenburg of the University of Chicago Caterina Gratton of Northwestern University Archana Venkataraman of Johns Hopkins University Joaquin Go?i of Purdue University [image: Rosenburg, Gratton, Venkataraman, and Go?i] From left, Rosenburg, Gratton, Venkataraman, and Go?i Register and submit an abstract . Registration is free but required. Abstracts must be submitted by 11:59 p.m. CDT Monday, Aug. 23. All presentations will be livestreamed with audience interaction. *Program at a glance:* *Thursday, Sept. 2 ,2021* 3 p.m., *Nalbandov Public Lecture *featuring Kamil Ugurbil. Livestream on Zoom for remote attendees, livestream shown at the Beckman Institute Auditorium at the University of Illinois for in-person audience 4:30 p.m., Reception in the Beckman Institute Atrium and garden at the University of Illinois *Friday, Sept. 3, 2021* 8:45 a.m. to 5 p.m. *Lightning talks* from submitted abstracts *Keynotes *from Jean-Baptiste Poline*, *Shella Keilholz *Lectures* from Monica Rosenburg, Caterina Gratton, Archana Venkataraman, Joaquin Go?i *About ACNN* The *Advanced Computational Neuroscience Network* aims to build broad consensus on the core requirements, infrastructure, and components needed to develop a new generation of sustainable interdisciplinary Neuroscience Big Data research. As a Midwest-coordinated network, ACNN leverages community strengths and resources to drive innovation and collaboration for the understanding of the structure, physiology, and function of the human brain through partnerships and services in education, tools, and best practices. Previous ACNN annual meetings have been held at The University of Michigan, Indiana University, and Ohio State University. *Want to share information about the workshop?*Please download our printable flyer! REGISTER AND SUBMIT ABSTRACT [image: university logo] Beckman Institute for Advanced Science and Technology University of Illinois Urbana-Champaign 405 N. Mathews Ave. | Urbana, IL 61801 Contact us [image: Facebook] [image: Twitter] [image: Instagram] [image: LinkedIn] [image: YouTube] Unsubscribe -------------- next part -------------- An HTML attachment was scrubbed... URL: From redhatw at gmail.com Thu Aug 26 10:44:34 2021 From: redhatw at gmail.com (Ze Wang) Date: Thu, 26 Aug 2021 14:44:34 +0000 Subject: [Neuroimaging] one sample t-test in nilearn: is there an automatic z-transform involved? Message-ID: My images from each individual have non-negative values across the brain, I would assume that t-value (or the z-value) for the one-sample t-test will be all greater than 0. But I found negative values. Does anyone know is there a z-transform in nilearn before doing the one-sample t? my code is simple: design_matrix=pd.DataFrame(np.hstack( (np.ones( (cova.shape[0],1)), cova) ), columns=colname ) model = SecondLevelModel(smoothing_fwhm=8.0, mask_img=brainmask) print(design_matrix) #print(imgs) model.fit(imgs.tolist(), design_matrix=design_matrix) omaps = model.compute_contrast('intercept', output_type='all') The contrast for the intercept was taken as the one-sample t results. and the resulting z-map have negative values. Thanks Ze -------------- next part -------------- An HTML attachment was scrubbed... URL: From yf2018210598 at bupt.edu.cn Fri Aug 27 05:25:00 2021 From: yf2018210598 at bupt.edu.cn (=?utf-8?B?5p2o5biG?=) Date: Fri, 27 Aug 2021 17:25:00 +0800 Subject: [Neuroimaging] Consult Message-ID: Hello, I have some questions about seg a brain image to white matter,grey matter? and CSF, I use the code in test_segmentation. def _test_brain_seg(model, niters=3, beta=0, ngb_size=6, init_params=None, convert=True): S = BrainT1Segmentation(anat_img.get_data(), mask=anat_mask, model=model, niters=niters, beta=beta, ngb_size=ngb_size, init_params=init_params, convert=convert) shape = anat_img.shape if convert: nclasses = 3 else: nclasses = S.mixmat.shape[0] # Check that the class attributes have appropriate dimensions _check_dims(S.ppm, 4, list(shape) + [nclasses]) _check_dims(S.label, 3, shape) _check_dims(S.mu, 1, S.mixmat.shape[0]) _check_dims(S.sigma, 1, S.mixmat.shape[0]) # Check that probabilities are zero outside the mask and sum up to # one inside the mask assert_almost_equal(S.ppm[~S.mask].sum(-1).max(), 0) assert_almost_equal(S.ppm[S.mask].sum(-1).min(), 1) # Check that labels are zero outside the mask and > 1 inside the # mask assert_almost_equal(S.label[~S.mask].max(), 0) assert_almost_equal(S.label[S.mask].min(), 1) def test_brain_seg1(): _test_brain_seg('3k', niters=3, beta=0.0, ngb_size=6)S_CSF = S.ppm[:,:,:,0] S_GM = S.ppm[:,:,:,1] S_WM = S.ppm[:,:,:,2] # cmap = AffineTransform('kji','zxy',np.eye(4)) CSF = nib.Nifti1Image(S_CSF,np.eye(4)) GM = nib.Nifti1Image(S_GM,np.eye(4)) WM = nib.Nifti1Image(S_WM,np.eye(4))(the code above is only a part of the whole procedure)I? consider that S.ppm contains the segmented image including white matter, grey matter and CSF, is that right?I got the CSF_1, GM_1 and WM_1 by using the above codebut my senior schoolmate gave me the correct white matter image and grey image is GM_correct and WH_correct.I'm a newcomer in medical imaging, but I can see the huge difference between my image and the correct image.So, could you please tell me how to correctly segment a brain image into WM,GM and CSF using nipy.Many thanks!FAN YANG ?? ??????/???/????????? 15911034495 ??   ?????????????? WM_1.nii (83M, 2021?09?26? 17:16 ??)???????http://mail.qq.com/cgi-bin/ftnExs_download?t=exs_ftn_download&k=0f653861c6cbffc308625d4e4135070b1e570a590006080905480a5252541d0d55015c4c0457525c1c5d0f0552560900050759555335383966286750485b5950315b&code=1e8af509&fid=72/228f3804-234a-4ddd-bbbe-87d4c994ba45 GM_1.nii (83M, 2021?09?26? 17:16 ??)???????http://mail.qq.com/cgi-bin/ftnExs_download?t=exs_ftn_download&k=07363634919dadca0031531b16635502160f0e52535552000b1b505102504f040d0f0619505253521455060c035b50025d04535057636a307e7b69051f0d0b593908&code=96641cb0&fid=72/98fb6002-fe33-4490-a11b-c082822d2edf CSF_1.nii (83M, 2021?09?26? 17:15 ??)???????http://mail.qq.com/cgi-bin/ftnExs_download?t=exs_ftn_download&k=0661653195c6ae9b0066001e1238565316005600540859055c4c00090d094c555c52001c0c5c595814025702040f56500d030106003868617a32236e04160f0850615b&code=9ae158aa&fid=72/a31a08de-e881-4e3e-9d89-c2317714bd75 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: GM_correct.nii Type: application/octet-stream Size: 14218626 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: WH_correct.nii Type: application/octet-stream Size: 14218626 bytes Desc: not available URL: