Search

Your search keyword '"Siddiqui, Nasir"' showing total 501 results
Start Over Author "Siddiqui, Nasir"
501 results on '"Siddiqui, Nasir"'

4. Author Correction: Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Author

Pyrros, Ayis, Borstelmann, Stephen M., Mantravadi, Ramana, Zaiman, Zachary, Thomas, Kaesha, Price, Brandon, Greenstein, Eugene, Siddiqui, Nasir, Willis, Melinda, Shulhan, Ihar, Hines-Shah, John, Horowitz, Jeanne M., Nikolaidis, Paul, Lungren, Matthew P., Rodríguez-Fernández, Jorge Mario, Gichoya, Judy Wawira, Koyejo, Sanmi, Flanders, Adam E, Khandwala, Nishith, Gupta, Amit, Garrett, John W., Cohen, Joseph Paul, Layden, Brian T., Pickhardt, Perry J., and Galanter, William

Published
2024
Full Text
View/download PDF

10. Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Author

Pyrros, Ayis, Borstelmann, Stephen M., Mantravadi, Ramana, Zaiman, Zachary, Thomas, Kaesha, Price, Brandon, Greenstein, Eugene, Siddiqui, Nasir, Willis, Melinda, Shulhan, Ihar, Hines-Shah, John, Horowitz, Jeanne M., Nikolaidis, Paul, Lungren, Matthew P., Rodríguez-Fernández, Jorge Mario, Gichoya, Judy Wawira, Koyejo, Sanmi, Flanders, Adam E, Khandwala, Nishith, Gupta, Amit, Garrett, John W., Cohen, Joseph Paul, Layden, Brian T., Pickhardt, Perry J., and Galanter, William

Published
2023
Full Text
View/download PDF

13. EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision

Author

Biswal, Siddharth, Zhuang, Peiye, Pyrros, Ayis, Siddiqui, Nasir, Koyejo, Sanmi, and Sun, Jimeng

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Deep generative models have enabled the automated synthesis of high-quality data for diverse applications. However, the most effective generative models are specialized to data from a single domain (e.g., images or text). Real-world applications such as healthcare require multi-modal data from multiple domains (e.g., both images and corresponding text), which are difficult to acquire due to limited availability and privacy concerns and are much harder to synthesize. To tackle this joint synthesis challenge, we propose an End-to-end MultImodal X-ray genERative model (EMIXER) for jointly synthesizing x-ray images and corresponding free-text reports, all conditional on diagnosis labels. EMIXER is an conditional generative adversarial model by 1) generating an image based on a label, 2) encoding the image to a hidden embedding, 3) producing the corresponding text via a hierarchical decoder from the image embedding, and 4) a joint discriminator for assessing both the image and the corresponding text. EMIXER also enables self-supervision to leverage vast amount of unlabeled data. Extensive experiments with real X-ray reports data illustrate how data augmentation using synthesized multimodal samples can improve the performance of a variety of supervised tasks including COVID-19 X-ray classification with very limited samples. The quality of generated images and reports are also confirmed by radiologists. We quantitatively show that EMIXER generated synthetic datasets can augment X-ray image classification, report generation models to achieve 5.94% and 6.9% improvement on models trained only on real data samples. Taken together, our results highlight the promise of state of generative models to advance clinical machine learning.

Published
2020

16. Max-Sliced Wasserstein Distance and its use for GANs

Author

Deshpande, Ishan, Hu, Yuan-Ting, Sun, Ruoyu, Pyrros, Ayis, Siddiqui, Nasir, Koyejo, Sanmi, Zhao, Zhizhen, Forsyth, David, and Schwing, Alexander

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning
Abstract

Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to model high-dimensional distributions, sequential training and stacked architectures are common, increasing the number of tunable hyper-parameters as well as the training time. Nonetheless, the sample complexity of the distance metrics remains one of the factors affecting GAN training. We first show that the recently proposed sliced Wasserstein distance has compelling sample complexity properties when compared to the Wasserstein distance. To further improve the sliced Wasserstein distance we then analyze its `projection complexity' and develop the max-sliced Wasserstein distance which enjoys compelling sample complexity while reducing projection complexity, albeit necessitating a max estimation. We finally illustrate that the proposed distance trains GANs on high-dimensional images up to a resolution of 256x256 easily., Comment: Accepted to CVPR 2019

Published
2019

18. Quantification of biomarkers and evaluation of antioxidant, anti-inflammatory, and cytotoxicity properties of Dodonaea viscosa grown in Saudi Arabia using HPTLC technique

Author

Almarfadi Omer M., Siddiqui Nasir A., Shahat Abdelaaty A., Alqahtani Ali S., Alam Perwez, Nasr Fahd A., Alshahrani Saad S., and Noman Omar M.

Subjects
dodonaea viscosa, hptlc, antioxidant, anti-inflammatory and cytotoxicity, Chemistry, QD1-999
Abstract

Dodonaea viscosa (Sapindaceae) was collected from Riyadh, Saudi Arabia. For the simultaneous measurement of quercetin and kaempferol, a validated high-performance thin-layer chromatography (HPTLC) approach was devised in D. viscosa leaf extract. The antioxidant activity was evaluated using diphenyl 1-picrylhydrazyl (DPPH) and 2,2′-azino-bis-3-ethylbenzothiazoline-6-sulfonic acid (ABTS) assays. Moreover, the cytotoxic effect was tested against three cancer cell lines A549, HepG2, and MDA-MB-231. The potential anti-inflammatory properties of different fractions of D. viscosa were also evaluated using lipopolysaccharide (LPS)-induced THP-1 macrophages cells. The test samples include a crude extract of leaves and its solvent-soluble fractions of D. viscosa. The results showed that the crude extract and its fractions exhibited various significant biological activities, the fraction of chloroform demonstrated the highest free radical scavenging activity with IC50 values: 172.2 and 257.7 µg/mL for both DPPH and ABTS tests. Additionally, the chloroform fraction had the greatest cytotoxic activity against MDA-MB-231 (IC50 values: 24.6 ± 0.4 µg/mL). Moreover, the chloroform fraction exhibited the highest downregulation of the LPS-induced expression of TNF-α and IL-6. Quercetin and kaempferol were estimated concurrently in leaves crude extract using a validated technique on an HPTLC plate (10 cm2 × 10 cm2) with a combination of toluene–ethyl acetate–formic acid (5:4:0.2; v/v/v) as the mobile phase and a λ max of 254 nm. The amount of quercetin and kaempferol was found to be 31.8 and 15.01 mg/g of dried leaf extract, respectively. The presence of high levels of quercetin and kaempferol in D. viscosa leaves extract could explain its remarkable antioxidant, cytotoxic, and anti-inflammatory effects. The devolved HPTLC method can be used for routine analysis and standardization of D. viscosa crude plant material, extracts, and/or finished products using quercetin and kaempferol as appropriate markers.

Published
2022
Full Text
View/download PDF

23. Cytotoxic activity of guaiane-type sesquiterpene lactone (deoxycynaropicrin) isolated from the leaves of Centaurothamnus maximus

Author

Nasr Fahd A., Siddiqui Nasir Ali, ElGamal Ali A., Al-Massarani Shaza M., Basudan Omer A., Abdel-Mageed Wael M., Alhuzani Mohammed R., and Alqahtani Ali S.

Subjects
centaurothamnus maximus, guaianolide, leukemia, thp-1 cells, Chemistry, QD1-999
Abstract

Guaianolide is a type of naturally occurring sesquiterpene lactone compounds that have attracted attention due to their diverse biological properties. In this work, a guaiane-type sesquiterpene lactone identified as deoxycynaropicrin (compound 1) was isolated and reported for the first time from the leaves of Centaurothamnus maximus with two known flavonoid derivatives namely luteolin 6-O-methyl ether (compound 2) and quercetin 3-methyl ether 5-O-glucopyranoside (compound 3). The cytotoxic activity of all the three compounds was evaluated against the THP-1 human leukemia cell lines. Moreover, flow cytometry was employed to explore the cell cycle arrest and apoptosis induction for the active compound. We found that compound 1 (deoxycynaropicrin) exerted the highest cytotoxicity while compounds 2 and 3 showed no activity. Cell cycle analysis showed that compound 1 arrested the cells’ population at the G2/M phase. Furthermore, THP-1 cells treated with compound 1 exhibited a marked increase in the apoptotic cells compared to the control. Overall, this study showed that deoxycynaropicrin induces cytotoxicity against human leukemia cell lines and provided an important insight into its potential therapeutic effects against leukemia cells.

Published
2022
Full Text
View/download PDF

28. Utility of silver nanoparticles embedded on a covalent organic framework as a highly active catalyst for carboxylative cyclization with CO2: a sustainable route for production of tetronic acids and oxazolidinones.

Author

Nandi, Dip Kumar, Haque, Najirul, Biswas, Surajit, Siddiqui, Nasir A., Khan, Aslam, and Islam, Sk Manirul

Subjects
SUSTAINABILITY, TETRONIC acid, SILVER nanoparticles, ATMOSPHERIC carbon dioxide, OXAZOLIDINONES, HETEROGENEOUS catalysts, PROPARGYL alcohol
Abstract

The rising amount of carbon dioxide in our atmosphere is a concern regarding our environment. This large amount of CO2 can be utilized as a C1 source for chemical fixation. Heterogeneous catalysts like covalent organic frameworks (COFs) have been reported to show excellent CO2 capture ability, which can be used to convert CO2 to various fine chemicals. Here, we synthesized a silver nanoparticle-incorporated TFPNDA COF. This Ag@TFPNDA-COF was characterized by FTIR, PXRD, SEM, TEM, N2-adsorption desorption, TGA, and XPS analyses. Then we tested the catalytic activity of the Ag@TFPNDA-COF. This COF shows excellent CO2 fixation capability in the synthesis of tetronic acids via carboxylative cyclization of propargyl alcohols as well as the formation of oxazolidinones from propargyl alcohols and amines under mild conditions. In addition, the Ag@TFPNDA-COF acted as a heterogeneous catalyst that can be easily separated from the reaction mixture for reuse. Moreover, it showed promising recyclability up to five times in a sustainable route for the production of tetronic acids and oxazolidinones. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

29. Development of SnO2-SnSe composites for the efficient photocatalytic degradation of methylene blue.

Author

Ayyaz, Muhammad, Rahman, Shams ur, Shah, A., Ahmad, Furqan, Siddiqui, Nasir Ali, Maryam, Rabia, Hussain, Afzal, and Hussain, Rafaqat

Subjects
CHEMICAL processes, INDUSTRIAL wastes, CHEMICAL kinetics, ABSORPTION spectra, RAMAN spectroscopy, METHYLENE blue
Abstract

The discharge of toxic industrial effluents into freshwater has a significant impact on both humans and aquatic lives, which needs to be addressed on an urgent basis. SnO2, a wide bandgap material possesses good photocatalytic properties, which can be exploited to degrade organic pollutants. However, there is a need to develop an appropriate strategy to decrease its bandgap and minimize the recombination of charge carriers. For this purpose, we are reporting the synthesis of SnO2/SnSe composites by wet chemical process in various ratios. The as-synthesized samples were analyzed through various characterization techniques. The X-ray diffraction (XRD) patterns confirmed the successful synthesis of tetragonal rutile SnO2 and orthorhombic structure of SnSe. The average crystallite size varied between 25 and 35 nm. UV–visible spectroscopy (UV–vis) confirmed that the bandgap of SnO2 and SnSe was 3.63 eV and 1.21 eV, respectively, whereas the bandgap of composites ranged from 3.47 to 3.03 eV. The FTIR spectrum exhibited absorption peaks at 745 cm−1, 1113 cm−1, and 1381 cm−1 due to the Sn–O–Sn bond and Sn–OH bond vibrations. Whereas the absorption observed at 665 cm−1 is associated with Se–O bond vibration. Raman spectroscopy revealed the bands at 629 cm−1 and 767 cm−1 for the rutile structure of SnO2 and bands at 75 cm−1, and 152 cm−1 are characteristic of SnSe. Scanning electron microscopy (SEM) illustrated the formation of irregular-shaped agglomerated nanoparticles of the prepared materials. Photodegradation of methylene blue (MB) revealed that the composite containing 78% SnO2 and 32% SnSe (denoted as SS-4) was highly an highly effective catalyst and degraded 97.1% of MB in 120 min. The reaction kinetics of the prepared photocatalysts satisfied the Langmuir–Hinshelwood model. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

32. Predicting Prolonged Hospitalization and Supplemental Oxygenation in Patients with COVID-19 Infection from Ambulatory Chest Radiographs using Deep Learning

Author

Pyrros, Ayis, Flanders, Adam Eugene, Rodríguez-Fernández, Jorge Mario, Chen, Andrew, Cole, Patrick, Wenzke, Daniel, Hart, Eric, Harford, Samuel, Horowitz, Jeanne, Nikolaidis, Paul, Muzaffar, Nadir, Boddipalli, Viveka, Nebhrajani, Jai, Siddiqui, Nasir, Willis, Melinda, Darabi, Houshang, Koyejo, Oluwasanmi, and Galanter, William

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results