30 research outputs found
MRG rekonstrüksiyonu için difüzyon köprüleri
No full textCataloged from PDF version of article.Includes bibliographical references (leaves 53-73).Magnetic Resonance Imaging (MRI) reconstruction typically involves a dealiasing process to transform undersampled data into fully-sampled data. However, conventional diffusion priors perform a denoising transformation, starting from a state of Gaussian noise and ending with fully-sampled data. Since the aliasing artifacts associated with many k-space sampling patterns have spatial structures that differ significantly from white Gaussian noise, this denoising process can lead to reconstruction errors due to suboptimal suppression of artifacts. To overcome this limitation, we introduce the first Fourier-constrained diffusion bridge (FDB) for MRI reconstruction. Unlike task-agnostic diffusion priors, the FDB is specifically designed to perform a dealiasing transformation, starting with undersampled data and ending with fully-sampled data. The starting point is created using a novel stochastic degradation operator that removes a randomly selected, progressively increasing set of spatial frequencies. Unlike diffusion priors that start from a heavily degraded state, the FDB uses a moderately undersampled starting point to enhance the reverse diffusion sampling process. Furthermore, unlike existing diffusion bridges that degrade data based on a weighted average of the start and end points, the FDB uses a binary removal of k-space points, aligning more closely with the nature of accelerated MRI acquisitions. To further enhance image quality, the FDB employs a novel sampling algorithm based on a learned correction term, enabling soft dealiasing by continuously refining estimates of the recovered k-space data during reverse diffusion steps. Tests on brain MRI show that the FDB outperforms competing non-diffusion priors by 4.8 dB PSNR and 11.8% SSIM, and diffusion priors by 4.7 dB PSNR and 6.6% SSIM.by Muhammad Usama Mirz
The Emirate of Damascus in the early Crusading period, 488-549/1095-1154
No full textThis study "The Emirate of Damascus During the Early
Crusading Period 488-549/1095-1154 deals with this
Emirate which was established in 488/1095, after the
defeat and the murder of Taj al-Dawla Tutush near Rayy
in 488/1095 by his nephew Sultan Berkiyaruq Ibn Sult-an
Malik-Sh5h. The dominions of Ti al-Dawla, mainly in
Syria and the Jazira divided between his elder sons King
Fakhr al-Mullik Ridwan in Aleppo and King Shams al-Muliik
Ducfaq in Damascus. The Kingdom of Damascus comprized
south Syria and some parts of the Jazira such as al-
Rahba and Mayyafäriqin.
Zahir al-Din Tughtekln, who was Atabek of King Duclaq, became the de facto ruler of Damascus during the
reign of King Duqaq 488-497/1095-1104. After the death
of Duqaq, Tughtekin was to be the real Amir of Damascus,
and his dynasty was to gain control of the Emirate until
its fall at the hands of Niir al-Din Mahmild of Aleppo in
549/1154.
In this thesis, the following matters are discussed:
1. The conditions which led to the foundation of this
Emirate.
2. The role of Tughtekin in establishing his authority
in the Emirate.
3. The foreign policy of the Emirate, and the factors
which shaped this policy.
4. The effects (on the Emirate) of the coming of the
Crusaders particularly those of Jerusalem.
S. Internal rivalries in the Emirate, and their
influence on the stability of the Emirate and its
external relations.
6. The policy of alliances adopted by the Emirate and
the factors which affected this.
7. The influence of the growing power of Zangi of
Aleppo and Mosul (521-541/1127-1146) on Damascus and
why he did not succeed in annexing Damascus to his
united front in Syria and the Jazira aimed at
challenging the power of the Crusaders.
8. The reasons which helped Mir al-Din Mahmüd Ibn Zangi
of Aleppo to annex Damascus to his state in
549/1154.
9. The importance of the military power of Damascus and
Its role in protecting the Emirate.
Finally a concluding section sums up the achievement
of the Emirate of Damascus in maintaining its
Independence during the period and the role of the
Emirate in the Counter-Crusade
Hızlandırılmış MRG geriçatımı için süper-çözünürlük difüzyon modeli
No full textDate of Conference: 05-08 July 2023Conference Name: 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023MRI reconstruction is a process to generate high-quality images from the raw data obtained during magnetic resonance imaging. Diffusion models, a class of generative models, have become a popular method for MRI Reconstruction due to their ability to generate high quality images. Diffusion models work by adding Gaussian noise to the original image and training a network to remove the noise. Diffusion models can continue to generate high quality images even with a different type of noise added to the original image. In this study we combine a resolution decreasing operator with noise scheduling used by regular diffusion models, ResDiff to perform MRI Reconstruction. One of the biggest drawbacks of Diffusion models is the amount of time taken to generate images. Down-sampling images to a lower resolution requires fewer steps allowing ResDiff to achieve competitive results in far less time.MRI rekonstrüksiyonu, manyetik rezonans görüntüleme sırasında elde edilen ham verilerden yüksek kaliteli görüntüler oluşturma işlemidir. Üretken modellerin bir sınıfı olan difüzyon modelleri, yüksek kaliteli görüntüler oluşturma yetenekleri nedeniyle MRI Rekonstrüksiyonu için popüler bir yöntem haline geldi. Difüzyon modelleri, orijinal görüntüye Gauss gürültüsü ekleyerek ve bir ağı gürültüyü gidermek için eğiterek çalışır. Difüzyon modelleri, orijinal görüntüye farklı türde bir gürültü eklendiğinde bile yüksek kaliteli görüntüler oluşturmaya devam edebilir. Bu çalışmada, MRI Rekonstrüksiyonunu gerçekleştirmek için normal difüzyon modelleri ResDiff tarafından kullanılan gürültü programlama ile çözünürlüğü azaltan bir operatörü birleştirdik. Difüzyon modellerinin en büyük dezavantajlarından biri, görüntü oluşturmak için harcanan sürenin miktarıdır. Çözünürlüğü azaltmak, modelin çok daha kısa sürede rekabetçi sonuçlar elde etmesini sağlar
Folio
No full textJonson, Robert-Article-What Interfaith Dialogue Should and Shouldn't be at FCC. pp. 1-3; Suhail Umar-Article-Between Secular Pluralism and Religious Exclusivism. pp. 4-11; Nisar Ahmed-Article-Interfaith Relationship. pp. 12; Abdul Ghani-Article-Religious Harmony. pp. 13-16; Bashir Ahmed Khan-Article-The Politics of Interfaith Dialogue. pp. 17-19; Abur Razzaq Black-Article-The Adobe of Peace. pp. 20-24; Anood Alta-Article-Technology has Replaced Faith. pp. 25; Riaz Akbar Somrai-Article-Peace Exclusive. pp. 26-27; Interview-An Interview with General Pervaiz Musharaf. pp. 29-32; Memoirs from Across the Border. pp. 33-35; Kuldip S. Bajwa-Zulfie, My Friend. pp. 36-37; Ch. Muhammad Aslam-My Memories, My Wealth. pp. 38; Kuldip S. Bajwa-One Upmanship. pp. 39-40; Shakila Noor Sindhu-Folio's Visit to India. pp. 41-42; Mirza Ather Baig-Article-Globalization and Global Claustrophobia. pp. 43-47; Thomson, Carol B.-Article-How People Engage in Global Conversations. pp. 48-49; Marryum Ishaque-Article-Global Economy and Trade Liberalization. pp. 50; Fawzia Afsal-Khan-Article-Edward Said: The Decolonizer as Humanist. pp. 51-56; Hall, Geof M.-Article-Under Western Eyes. pp. 57-62; Nasim Riaz Butt-Article-Of Culture. pp. 63-64; Farid Malik-Article-The Third World, Islamic Ummah and the Third World War. pp. 65-67; Bilkis Hussain-Article-Gender Empowerment for Socio-Economic Development. pp. 68; Omer Habib-Article-Saying Goodbye to Traditions. pp. 69; Aqsa Ijaz-Article-Puppets in the Hands of Society. pp. 70-72; Interview-An Interview with Dr Grace C. Clark. pp. 73-77; Struck, Craig-Article-Coping with Emotional Stress. pp. 78-81; Waseem Anwar-Article-Higher Education. pp. 82-85; Zamir Hussain-My Dear Undergrads and a Ghanaian Poet. pp. 86-87; Muhammad Usman-Educational Stereotypes. pp. 88-89; A. Riaz, S. Nathaniel, R. Javed-Article-A Fullbright Experience: A Dream Come True. pp. 90-94; Nausheen Ishaque-Article-Art versus Morality. pp. 95-97; Iffat Khatoon-Article-The Theatrics of Masking. pp. 98-100; Zoeya Naqvi-Article-On Humour. pp. 101; Azzam Siddique-All that Red Stuff. pp. 102-103; Riaz Akbar Somrai-Article-Paradise Hath Descended on Earth. pp. 104-105; Ashraf, C. M.-Article-Chemistry and Community. pp. 106-108; Bilkis Hussain-Article-Is Science a Bane or a Boon. pp. 109-110; Muhammad Usman-Article-The Technological Evils. pp. 111; Zoeya Naqvi-About Love Unattainable. pp. 112; Pannu, P. S.-Smiling to Glory. pp. 113-114; Inayatullah Khan-Article-Common Sense Ought Not to be so Uncommon. pp. 115-116; Kenneth Pervaiz-Today's Naked Man. pp. 117; Beenish Fatima-No One Wants to be Themselves These Days. pp. 118; Zeeshan Zaighum-Feelings. pp. 119; Usama-Dreams. pp. 120; Burke, Cheryl-What Does a Good Student Look Like. pp. 121; Haider F. Halim-The Golden Registration Day. pp. 122-123; Imran Bashir-Proud to be a Formanite. pp. 124-125; Sundus Maqbool-Do We Even Exist? pp. 126; Haider Farooq-Class Versus Cafeteria. pp. 127; Furqan Ali Akhtar-Conventional Consequences of Academic Achievements. pp. 128; Report-Campus Roundup. pp. 129-132; Kudos to FCC Faculty and Students. pp. 133; Imran Iqbal-International Negotiations. pp. 134; Formanites Alumni Association. pp. 135-136; Foreign Faculty at FCC: A Survey. pp. 137-138; Luqman Saeed-An Immoral Activity. pp. 139; Arooj Wahid-Story-Haji Sahib. pp. 140; Farhan Hashmi-Story-Untitled. pp. 141; Talha Mahboob-Story-If She Could Know. pp. 142-143; Maureen Miscus Crisick-Poetry-Arguing with Sand in Mali. pp. 144; Talha Mahboob-Poetry-Do They Care? pp. 144; Bilkis Hussain-Poetry-Less is More. pp. 145; Ramla Zaheer-Poetry-Dare Face the Challenge. pp. 145; Bilkis Hussain-Poetry-Memories. pp. 146; Umar Tahir-Poetry-Once.... pp. 146; Arif Qureshi-Poetry-Nostalgia. pp. 147; Shaharyar Khan-Poetry-To Dust. pp. 147; Easha Farooq-Poetry-Memories. pp. 148; Aakash Qasir Iqbal-Poetry-Hummingbirds. pp. 148; Jawad, M.-Poetry-Everlasting Attachments.... pp. 149; Arif Qureshi-Poetry-Reminiscences. pp. 149; Birinder Kaur Pannu-Poetry-A Requiem for Our Silky. pp. 150; Junaid Ali-Poetry-Here I am. pp. 150; Awan, M. Shaheer-Poetry-I Desire to Paint You. pp. 151; Uzma Azad-Poetry-Silent Wish. pp. 151; Uzma Azad-Poetry-Some Day. pp. 152; Amber M. Gill-Poetry-Patience. pp. 152; Ramla Zaheer-Poetry-Life Goes On. pp. 153; Awan, M. Shaheer-Poetry-Lost Angel. pp. 153; Jawad, M.-Poetry-The Foggy Trees. pp. 154; Sadia Riaz-Poetry-Tears and Laughter. pp. 154; Hafiz Ali Aziz Khokhar-Poetry-I Shine Now. pp. 155; Nauman Ahmad-Poetry-Life is Ephemeral. pp. 155; Ramla Zaheer-Poetry-To Time and Fate. pp. 156; Muhammad Adeel Ahmad-Poetry-Death of Beauty. pp. 156; Hafiz Ali Aziz-Poetry-What Should I do? pp. 157; Shaheryar Khan-Poetry-What May I Think? pp. 157; Azzam Saddique-Poetry-The Smith. pp. 158; Rao Ayyaz Ahmad-Poetry-Assignment Girls College. pp. 159; Zeeshan Zaighum-Poetry-Divorce. pp. 159; Folio [Urdu]. 146 p.Editorial Board (English). before the Editorial page; Kennedy Hall, Forman Christian College (1959-60). after page 30; Folio team with the President of Pakistan. after page 30; Offices. page 160; Visitors. after page 160; Convocation. after page 160; Sports. after page 160; Societies. after page 160; Drama. after page 160; Music. after page 160; College Life. after page 160; Alumni. after page 160; Sundaisay. after page 16
Multi-Class Skin Lesions Classification Using Deep Features
No full textSkin cancer classification is a complex and time-consuming task. Existing approaches use segmentation to improve accuracy and efficiency, but due to different sizes and shapes of lesions, segmentation is not a suitable approach. In this research study, we proposed an improved automated system based on hybrid and optimal feature selections. Firstly, we balanced our dataset by applying three different transformation techniques, which include brightness, sharpening, and contrast enhancement. Secondly, we retrained two CNNs, Darknet53 and Inception V3, using transfer learning. Thirdly, the retrained models were used to extract deep features from the dataset. Lastly, optimal features were selected using moth flame optimization (MFO) to overcome the curse of dimensionality. This helped us in improving accuracy and efficiency of our model. We achieved 95.9%, 95.0%, and 95.8% on cubic SVM, quadratic SVM, and ensemble subspace discriminants, respectively. We compared our technique with state-of-the-art approach
Üretken çekişmeli ağlar ile medikal görüntü sentezi için atlamalı bağlantılar
No full textConference Name: 2022 30th Signal Processing and Communications Applications Conference (SIU)Date of Conference: 15-18 May 2022Magnetic Resonance Imaging (MRI) is an imaging technique used to produce detailed anatomical images. Acquiring multiple contrast MRI images requires long scan times forcing the patient to remain still. Scan times can be reduced by synthesising unacquired contrasts from acquired contrasts. In recent years, deep generative adversarial networks have been used to synthesise contrasts using one-to-one mapping. Deeper networks can solve more complex functions, however, their performance can decline due to problems such as overfitting and vanishing gradients. In this study, we propose adding skip connections to generative models to overcome the decline in performance with increasing complexity. This will allow the network to bypass unnecessary parameters in the model. Our results show an increase in performance in one-to-one image synthesis by integrating skip connections
Super resolution mri via upscaling diffusion bridges
No full textConference Name: 32nd IEEE Signal processing and communications applications conference (SIU)Date of Conference:MAY 15-18, 2024Magnetic Resonance Imaging (MRI) is a powerful medical imaging modality that provides high-resolution anatomical information about tissues. However, the intrinsic trade-off between acquisition time and image quality poses challenges in obtaining high-resolution images within a clinically feasible timeframe. This study introduces a novel approach to acquire high-resolution images in short scan times based on Super-Resolution Diffusion Bridges (SRDB). The proposed method leverages advanced machine learning techniques based on diffusion models to upscale MR images. The While standard diffusion models learn a mapping from Gausssian distributed noise images to target images, SRDB instead learns a mapping from low-resolution MR images to high-resolution images. Unlike the task-independent learning in standard diffusion model, SRDB thus performs task-based learning to improve structural consistency and better preservation of anatomical features. In this way, the trained models help capture fine details that may be missed in standard low-resolution MRI acquisitions
Koşulsuz tıbbi görüntü oluşturma için gürültü giderme difüzyon çekişmeli modeller
No full textDate of Conference: 05-08 July 2023Conference Name: 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023Unconditional medical image synthesis is the task of generating realistic and diverse medical images from random noise without any prior information or constraints. Synthesizing realistic medical images can enrich the quality and diversity of medical imaging datasets, which in turn, enhance the performance and generalization of deep learning models for medical imaging. Prevalent approach for synthesizing medical images involves generative adversarial networks (GAN) or denoising diffusion probabilistic models (DDPM). However, GAN models that implicitly learn the image distribution are prone to limited sample fidelity and diversity. On the other hand, diffusion models suffer from slow sampling speed due to small diffusion steps. In this paper, we propose a novel diffusion-based method for unconditional medical image synthesis, Diff-Med-Synth, that generates realistic and diverse medical images from random noise. Diff-Med-Synth combines the advantages of denoising diffusion probabilistic models and GANs to achieve fast and efficient image sampling. We evaluate our method on two multi-contrast MRI datasets and show that it outperforms state-of-the-art methods in terms of quality, diversity, and fidelity of the synthesized images.Koşulsuz tıbbi görüntü sentezi, önceden bilgi veya kısıt olmaksızın rastgele gürültüden gerçekçi ve çeşitli tıbbi görüntüler üretme görevidir. Gerçekçi tıbbi görüntüler sentezlemek, tıbbi görüntüleme veri kümelerinin kalitesini ve çeşitliliğini zenginleştirebilir, bu da sırayla tıbbi görüntüleme için derin öğrenme modellerinin performansını ve genelleştirilmesini artırabilir. Tıbbi görüntüler sentezlemek için yaygın yaklaşım, üretici çekişmeli ağlar (GAN) veya gürültüyü giderme difüzyon olasılık modelleri (DDPM) içerir. Ancak, GAN modelleri görüntü dağılımını dolaylı olarak öğrenir ve sınırlı örnek sadakati ve çeşitliliğe eğilimlidir. Öte yandan, difüzyon modelleri küçük difüzyon adımları nedeniyle yavaş örnekleme hızından muzdariptir. Bu çalışmada, rastgele gürültüden gerçekçi ve hızlı şekilde tıbbi görüntüler üreten yeni bir difüzyon tabanlı yöntem olan Diff-Med-Synth’i öneriyoruz. Diff-Med-Synth, hızlı ve verimli görüntü örnekleme elde etmek için gürültüyü giderme difüzyon olasılık modellerinin ve GAN’ların avantajlarını birleştirir. Yöntemimizi iki çok kontrastlı MRG veri kümesinde değerlendiriyoruz ve sentezlenen görüntülerin kalitesi, çeşitliliği ve sadakati açısından son teknik yöntemleri geride bıraktığını gösteriyoruz
Bound States of Atomic Josephson Vortices
No full textWe study the existence and stability of the bound state Josephson vortices solution in two parallel quasi one-dimensional coupled Bose-Einstein condensates. The system can be elucidated by linearly coupled Gross-Pitaevskii equations. The purpose of this study is to investigate the effects of altering the strength of coupling between the two condensates over the stability of the bound state Josephson vortices. It is found that the stability of bound state Josephson vortices depends on the value of coupling strength. However, at a critical value of coupling parameter, the Josephson vortices solution transforms into a coupled dark soliton.The presentation of the authors' names and (or) special characters in the title of the pdf file of the accepted manuscript may differ slightly from what is displayed on the item page. The information in the pdf file of the accepted manuscript reflects the original submission by the author
Fake visual content detection using two-stream convolutional neural networks
No full textRapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection techniques have been proposed. The performance of most of these techniques however drops off significantly if the test and the training data are sampled from different distributions. This motivates efforts towards improving the generalization of fake detectors. Since current fake content generation techniques do not accurately model the frequency spectrum of the natural images, we observe that the frequency spectrum of the fake visual data contains discriminative characteristics that can be used to detect fake content. We also observe that the information captured in the frequency spectrum is different from that of the spatial domain. Using these insights, we propose to complement frequency and spatial domain features using a two-stream convolutional neural network architecture called TwoStreamNet. We demonstrate the improved generalization of the proposed two-stream network to several unseen generation architectures, datasets, and techniques. The proposed detector has demonstrated significant performance improvement compared to the current state-of-the-art fake content detectors with the fusing of frequency and spatial domain streams also improving the generalization of the detector. 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.Scopu
