Tootfinder

Oh great, now I can’t trust the emails from #Google not to change between readings.
One of the reasons I value email is for the ability to store what’s been said at a point in time and refer back to it knowing it will not change, kind of like, books or letters.

Papanicolaou Stain Unmixing for RGB Image Using Weighted Nucleus Sparsity and Total Variation Regularization
Nanxin Gong, Saori Takeyama, Masahiro Yamaguchi, Takumi Urata, Fumikazu Kimura, Keiko Ishii
https://arxiv.org/abs/2506.20450

Papanicolaou Stain Unmixing for RGB Image Using Weighted Nucleus Sparsity and Total Variation Regularization
The Papanicolaou stain, consisting of eosin Y, hematoxylin, light Green SF yellowish, orange G, and Bismarck brown Y, provides extensive color information essential for cervical cancer screening in cytopathology. However, the visual observation of these colors is subjective and difficult to characterize. In digital image analysis, the RGB intensities are affected by staining and imaging variations, hindering direct quantification of color in Papanicolaou-stained samples. Stain unmixing is a pro…

WhatsApp führt KI-Zusammenfassungen von Chats ein – zuerst in den USA
WhatsApp erweitert die KI-Funktionen: Fortan können Nutzer Zusammenfassungen verpasster Nachrichten mittels Meta AI erstellen lassen – zunächst in den USA.

Netanyahu says „Free Palestine is just today's version of Heil Hitler” — on the same day it has just become illegal in Germany to ask “Have we learned nothing from the Holocaust?” in regards to Palestine, as German courts deemed it trivialization of the holocaust.

Just bought a ticket for @… in Freiburg!
Someone else coming? Can't wait to see y'all again.
#webdev

Never been this early, 07:46! 🌞

Happy P2P Friday (Push-to-Prod)⁠‼️

ハッシュタグ # じゃなくて 丼 に変わるかも説 ｳｹﾙ

WhatsApp launches optional Meta AI-generated summaries of unread messages in the US; Meta can't read the messages and summaries are hidden from other chat users (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/06/25/meta-is-adding-ai-power…

Meta is adding AI-powered summaries to WhatsApp | TechCrunch
Meta announced on Wednesday that it's adding an AI-powered summaries feature to WhatsApp. The optional new feature uses Meta AI to summarize unread

On Supersymmetric D-brane probes in 4d $\mathcal{N}=2$ $\text{AdS}_2\times\mathbf{S}^2$ Attractors
Alberto Castellano, Carmine Montella, Matteo Zatti
https://arxiv.org/abs/2507.17857

On Supersymmetric D-brane probes in 4d $\mathcal{N}=2$ $\text{AdS}_2\times\mathbf{S}^2$ Attractors
We extend the $κ$-symmetry analysis of supersymmetric D-brane probes in the $\mathrm{AdS}_2 \times \mathbf{S}^2$ attractor geometry, originally performed by Simons, Strominger, Thompson, and Yin, to also include stationary -- but non-static -- worldlines carrying angular momentum along the 2-sphere. We demonstrate that certain special trajectories, with fixed radius and orbital velocity, solve the equations of motion and moreover satisfy a supersymmetry preserving condition, thus defining new …

Loving Vampire lore and being a big fan of #BtVS Buffy The Vampire Slayer I went in to #Netflix The Discovery Of Witches as yeah, seen that, done that. But now into the 2nd season I'm really getting the vibe and story line. Both Theresa Palmer and Matthew Goode excel in their roles and bring …

CHERI-based memory safety for WebAssembly https://dl.acm.org/doi/pdf/10.1145/3571208

"grad deutscher härte" klingt einfach super sus

I’ve generally disliked South Park — not because it is rude and raunchy, but because it made it seem like being a cynical asshole is somehow brave and countercultural. It made the case that it’s OK to be carelessly hurtful as long as you hurt •everyone•. It tried to make a virtue out of disaffection. Its compulsion never to be caught actually •caring• about anything or anyone robbed it of its capacity to have insights or a moral center. It flirted with satire, but always ended up just being trolling.
But who knows? It feels like trolling the fascists might be what we need right now. Maybe the show finally has its moment.

Bei der Logitech MX Master 3 ist die Daumentaste "Maustaste 6" unter macOS und kann als solche in den Systemeinstellungen bei Schreibtisch & Dock als Mauskurzbefehl für Mission Control hinterlegt werden.
Ich hatte kurz Sorge, ich müsse Logitech Software installieren, um das zu konfigurieren.

Thought experiment: Most programming languages were designed in an era where mostly one programmer coded in isolation. If you were designing a language for modern collaborative programming/commenting/etc., what would you change? How would you *modify* existing languages?

Life hack: if you write a check for negative dollars, anyone who accidentally deposits it will owe YOU money #aiTrainingData

I'm going to say it... Wordpress (as self-hosted, multi-site website creating software) is a really awesome bit of free/open source software. I've tried a _lot_ of alternatives in the past but always come back to it, and it keeps getting better.

7/25/75 cleveland: similar but different sets over 2 nights. both 1st sets open with covers, tonight FIRE ENGINE (last night PSYCHOTIC REACTION) & close with cracklin’ BREAKIN’ IN MY HEART (breakin’ 10 minutes, too). both 2nd sets end with same 5 & lotta fiery richard lloyd solos, capped by LITTLE JOHNNY JEWEL, FOXHOLE, & new show closer KINGDOM COME, one of my single favorite television performances. sparkling, tight. most/all later versions have drum solo.

Sei laut, sei sichtbar – gerade jetzt
https://taz.de/Sichtbarkeit-beim-Disability-Pride-Month/!6093268/

Die Schlange vor der guten Eisdiele (Jones im Akazienkiez) ist absurd lang. Danke, Foodinfluencer auf Insta. Im Grunde enthält mir Zuckerberg die gute Eiskrem vor, grrr 😡

Air conditioning in my office is done for I think. Being a home owner is a pain in the ass some times.

Anfang Februar bin ich Mitglied bei der @… geworden, damit ich den 3D Drucker verwenden kann. Seitdem habe ich 40 Bücher, einige Hörspiele, Filme und Serien ausgeliehen und heute nutze ich den Drucker zum ersten mal 🙃
Bibliotheksausweis lohnt sich!

I swear it's not what it looks like!

Important thread on BlueSky from Elliot Higgins on misinformation.
#misinformation…

Typisch €DU: Kein Geld für Kultur und Soziales wegen angespannter Haushaltslage, aber von 3 Mio. € für zusätzliche Überwachung und sinnlose Law-and-Order Symbolpolitik träumen.
https://www.saechsische.de/lokales/dresden

Wie Dresden den „Kampf gegen Graffiti gewinnen“ will
Gesprühte Kunst wird in Dresden nun mit Laserstrahlen entfernt. Damit will die Stadt Sprayer abschrecken. Aber das kostet viel Geld.

Ken Pomeroy was the opening act!
#LiveMusic

Do the Las Vegas Raiders need another DT? https://raiderramble.com/2025/06/27/do-the-las-vegas-raiders-need-another-dt/

ChatGPT (cat, I farted, to the French) can't beat the world's best chess player, and it sucks at old video games, mainly because ChatGPT is NOT INTELLIGENCE of ANY kind. It's a parrot machine.

Antsietatea eukiteaz kantsauta nago.

Gesund zu essen kann auch schön sein. Besonders, wenn man das auf handbemalter Keramik von @… macht. 💝
Tag für Tag habe ich meine Freude an meinen Schätzen.

The Johns Hopkins University Press will license its authors' books to train AI models, citing concerns that "the window may be closing" for making AI deals (Ellie Wolfe/The Baltimore Banner)
https://www.thebaltimoreb…

Johns Hopkins University Press will license its authors’ books to train AI models
Authors at the Johns Hopkins University Press will be able to opt out of the AI licensing agreement until the end of August; if they do not, their work will be used to train AI models.

@… @… @… Not on my continent!

Fusing Radiomic Features with Deep Representations for Gestational Age Estimation in Fetal Ultrasound Images
Fangyijie Wang, Yuan Liang, Sourav Bhattacharjee, Abey Campbell, Kathleen M. Curran, Gu\'enol\'e Silvestre
https://arxiv.org/abs/2506.20407

Fusing Radiomic Features with Deep Representations for Gestational Age Estimation in Fetal Ultrasound Images
Accurate gestational age (GA) estimation, ideally through fetal ultrasound measurement, is a crucial aspect of providing excellent antenatal care. However, deriving GA from manual fetal biometric measurements depends on the operator and is time-consuming. Hence, automatic computer-assisted methods are demanded in clinical practice. In this paper, we present a novel feature fusion framework to estimate GA using fetal ultrasound images without any measurement information. We adopt a deep learning…

Die Aussage "die Bundeswehr müsse wieder in die MItte der Gesellschaft gerückt werden" verabscheue ich zu tiefst. Auch der Veteranentag ist nur der Versuch am Image der Bundeswehr zu feilen. Gerne wird das mit "Verteidigung im Ernstfall" erklärt, dass nun aufrüstungsgeile Alte mit den Säbeln rasseln und Waffen bestellen. Wir als Deutsches Volk können das nicht wollen. Bei einem Angriff sollten wir umgehend kapitulieren und uns ergeben. Aber Kriege zu führen hat noch keinem Menschen geholfen.…

#FrancescaAlbanese, the , #UN ’s special rapporteur for the occupied Palestinian territories, said the attack represented a “distinguishable sadistic pattern of the new phase of the genocide”.

a virtuoso of the house renovation is doing some works in the building and has been whistling since early this morning non-stop

EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Jiayan Chen, Kai Li, Yulu Zhao, Jianqiang Huang, Zhan Wang
https://arxiv.org/abs/2506.20333

EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model lon…

Asana names LaunchDarkly CEO Dan Rogers as its new CEO starting on July 21, replacing co-founder Dustin Moskovitz, who is retiring and will remain board chair (Jordan Novet/CNBC)
https://www.cnbc.com/2025/06/25/asana-ceo-dan-rogers-replace-dustin…

Asana picks Dan Rogers, formerly of ServiceNow, to replace CEO Dustin Moskovitz
Dustin Moskovitz, the largest individual owner of Asana stock, will stick around as the software company's board chair.

@… 乗るしかないこのビッグウェーブに……

I realize that one element of this is cop PR: “See! Those other guys are worse! We’re not so bad!!” This in no way lessens the wonder and the horror of the situation.

Ich arbeite erst ein Monat bei pretix, aber habe mich als neurodivergente Person noch nie so wohl und willkommen bei der Arbeit gefühlt. Falls ihr für Android entwickelt, bewerbt euch: https://pretix.eu/about/de/job/appdev

On the train to Barcelona for @… ! Having already spent a couple of days surrounded by live coders in a Peak District retreat I've got this weird thing where I keep seeing live coders just walking around everywhere who turn out to be lookalikes
I'll be involved with a paper about choreographic notation for robots with @…

Als de VVD meegaat in de afdelingsmanoeuvre van Wilders en alle tijd aan het bespreken van zijn "voorstellen" gaat besteden in plaats van de echte problemen oplossen mbt woningen, arbeidsmigratie, onderwijs, defensie, economie, gezondheidszorg, dan zijn ze echt geen knip voor de neus waard.
#VVD #politiek

Parks Associates: 33% of US internet households subscribe to a DTC sports-specific streamer and 40% of sports viewers exclusively watch sports via streamers (George Winslow/TV Tech)
https://www.tvtechnology.com/news/study-33

Study: 33% of US Internet Households Subscribe to a Direct-to-Consumer Sports Streaming Service
D2C sports service viewers are the heaviest spenders on streaming video services shelling out an average of $111 per month on all streaming subscriptions according to Parks Associates

@… The question is, how long can I run with it before people start to get nervous?

Transformer Based Multi-Target Bernoulli Tracking for Maritime Radar
Caden Sweeney, Du Yong Kim, Branko Ristic, Brian Cheung
https://arxiv.org/abs/2506.20319

Transformer Based Multi-Target Bernoulli Tracking for Maritime Radar
Multi-target tracking in the maritime domain is a challenging problem due to the non-Gaussian and fluctuating characteristics of sea clutter. This article investigates the use of machine learning (ML) to the detection and tracking of low SIR targets in the maritime domain. The proposed method uses a transformer to extract point measurements from range-azimuth maps, before clustering and tracking using the Labelled mulit- Bernoulli (LMB) filter. A measurement driven birth density design based on…

[2025-07-25 Fri (UTC), 22 new articles found for hep-th High Energy Physics - Theory]
toXiv_bot_toot

Recent grads and PhDs are being recruited by AI companies like Handshake to provide specialized training data in fields like music and law for $30-$160 per hour (Emma Haidar/Bloomberg)
https://www.bloomberg.com/news/articles/2025-07-24/col…

College Grads Are Finding Jobs Training AI Models
Ever since he picked up a trombone in middle school, Jackson Spellman has wanted to pursue a career in music.“It's 100% going to be a part of my life for the rest of my life,” said the 22-year-old from Wellington, Florida, who graduated in June from Northwestern University with a double major in music and cognitive science.Along with his degree, Spellman finished school with a new gig to add to his resume: artificial intelligence trainer. In the weeks leading up to graduation, Spellman said…

FundaQ-8: A Clinically-Inspired Scoring Framework for Automated Fundus Image Quality Assessment
Lee Qi Zun, Oscar Wong Jin Hao, Nor Anita Binti Che Omar, Zalifa Zakiah Binti Asnir, Mohamad Sabri bin Sinal Zainal, Goh Man Fye
https://arxiv.org/abs/2506.20303

FundaQ-8: A Clinically-Inspired Scoring Framework for Automated Fundus Image Quality Assessment
Automated fundus image quality assessment (FIQA) remains a challenge due to variations in image acquisition and subjective expert evaluations. We introduce FundaQ-8, a novel expert-validated framework for systematically assessing fundus image quality using eight critical parameters, including field coverage, anatomical visibility, illumination, and image artifacts. Using FundaQ-8 as a structured scoring reference, we develop a ResNet18-based regression model to predict continuous quality scores…

TouchPoints survey: the time people in Great Britain aged 15 or older spend using their phones has overtaken the time spent watching TV for the first time (Mark Sweney/The Guardian)
https://www.theguardian.com/media/2025/jun

@… @… OMG, that was it! Thank you for figuring it out, and sorry for taking up your time.
I am using nushell, and calling `path expand` on everything in my $PATH to expand `~`:

Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration
Jiaxing Huang, Heng Guo, Le Lu, Fan Yang, Minfeng Xu, Ge Yang, Wei Luo
https://arxiv.org/abs/2506.20282

Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration
Osteoporosis, characterized by reduced bone mineral density (BMD) and compromised bone microstructure, increases fracture risk in aging populations. While dual-energy X-ray absorptiometry (DXA) is the clinical standard for BMD assessment, its limited accessibility hinders diagnosis in resource-limited regions. Opportunistic computed tomography (CT) analysis has emerged as a promising alternative for osteoporosis diagnosis using existing imaging data. Current approaches, however, face three limi…

Replaced article(s) found for hep-th. https://arxiv.org/list/hep-th/new
[1/1]:
- New constrained generalized Killing spinor field classes in warped flux compactifications
D. Fabri Gon\c{c}alves, R. da Rocha

Google has defended Search against the first wave of disruption from generative AI, but AI agents and apps that can reduce clicks now threaten its ad business (Richard Waters/Financial Times)

Volumetric segmentation of muscle compartments using in vivo imaging and architectural validation in human finger flexors
Yang Li
https://arxiv.org/abs/2506.20206

Volumetric segmentation of muscle compartments using in vivo imaging and architectural validation in human finger flexors
Segmenting muscle compartments and measuring their architecture can facilitate movement function assessment, accurate musculoskeletal modeling, and synergy-based electromyogram simulation. Here, we presented a novel method for volumetric segmentation of muscle compartments using in vivo imaging, focusing on the independent compartments for finger control of flexor digitorum superficialis (FDS). Besides, we measured the architectural properties of FDS compartments and validated the segmentation.…

Anthropic releases preliminary results showing users who discuss emotional issues with Claude tend to grow more positive as conversations progress (Megan Morrone/Axios)
https://www.axios.com/2025/06/26/anthropic-claude-companion-therapist-coach…

Exclusive: How Claude became an emotional support bot
The research shows users grow more positive while chatting with Claude.

MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment
Siqiao Li, Chen Hui, Wei Zhang, Rui Liang, Chenyue Song, Feng Jiang, Haiqi Zhu, Zhixuan Li, Hong Huang, Xiang Li
https://arxiv.org/abs/2506.20200

MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment
Positron Emission Tomography / Computed Tomography (PET/CT) plays a critical role in medical imaging, combining functional and anatomical information to aid in accurate diagnosis. However, image quality degradation due to noise, compression and other factors could potentially lead to diagnostic uncertainty and increase the risk of misdiagnosis. When evaluating the quality of a PET/CT image, both low-level features like distortions and high-level features like organ anatomical structures affect …

Integrable spin chains in twisted maximally supersymmetric Yang-Mills theory
Tim Meier, Stijn J. van Tongeren
https://arxiv.org/abs/2507.18626 https://arxi…

Integrable spin chains in twisted maximally supersymmetric Yang-Mills theory
We study an angular dipole deformation of maximally supersymmetric Yang-Mills theory (SYM) that preserves its classical scale invariance. We show that two-point functions of suitable single trace operators, restricted to an invariant plane, are determined by scaling dimensions computable from an integrable spin chain. This spin chain is a diagonally twisted version of the famous integrable spin chain of SYM. It matches expectations from the dual string theory perfectly, presenting a precision t…

VoxelOpt: Voxel-Adaptive Message Passing for Discrete Optimization in Deformable Abdominal CT Registration
Hang Zhang, Yuxi Zhang, Jiazheng Wang, Xiang Chen, Renjiu Hu, Xin Tian, Gaolei Li, Min Liu
https://arxiv.org/abs/2506.19975

VoxelOpt: Voxel-Adaptive Message Passing for Discrete Optimization in Deformable Abdominal CT Registration
Recent developments in neural networks have improved deformable image registration (DIR) by amortizing iterative optimization, enabling fast and accurate DIR results. However, learning-based methods often face challenges with limited training data, large deformations, and tend to underperform compared to iterative approaches when label supervision is unavailable. While iterative methods can achieve higher accuracy in such scenarios, they are considerably slower than learning-based methods. To a…

Workers at Google, TikTok, Adobe, Dropbox, CrowdStrike, and other tech firms recount how managers used AI to justify firing them, speed up their work, and more (Brian Merchant/Blood in the Machine)
https://www.bloodinthemachine.com/p/how-ai-is-killing-jo…

AI Killed My Job: Tech workers
Tech workers at TikTok, Google, and across the industry share stories about how AI is changing, ruining, or replacing their jobs.

[2025-06-26 Thu (UTC), 10 new articles found for eess.IV Image and Video Processing]
toXiv_bot_toot

Graviton scattering on self-dual black holes
Tim Adamo, Giuseppe Bogna, Lionel Mason, Atul Sharma
https://arxiv.org/abs/2507.18605 https://arxiv.org/pdf/25…

Graviton scattering on self-dual black holes
The computation of gravitational wave scattering on black hole spacetimes is an extremely hard problem, typically requiring approximation schemes which either treat the black hole perturbatively or are only amenable to numerical techniques. In this paper, we consider linearised gravitational waves (or gravitons) scattering on the self-dual analogue of a black hole: namely, the self-dual Taub-NUT metric. Using the hidden integrability of the self-dual sector, we can solve the linearised Einstein…

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Mathematical Foundation of Sparsity-based Multi-snapshot Spectral Estimation
Ping Liu, Sanghyeon Yu, Ola Sabet, Lucas Pelkmans, Habib Ammari

Exploring the Design Space of 3D MLLMs for CT Report Generation
Mohammed Baharoon, Jun Ma, Congyu Fang, Augustin Toma, Bo Wang
https://arxiv.org/abs/2506.21535

Exploring the Design Space of 3D MLLMs for CT Report Generation
Multimodal Large Language Models (MLLMs) have emerged as a promising way to automate Radiology Report Generation (RRG). In this work, we systematically investigate the design space of 3D MLLMs, including visual input representation, projectors, Large Language Models (LLMs), and fine-tuning techniques for 3D CT report generation. We also introduce two knowledge-based report augmentation methods that improve performance on the GREEN score by up to 10\%, achieving the 2nd place on the MICCAI 2024 …

Supersymmetry and integrability of the elliptic $\mathrm{AdS}_3 \times \mathrm{S}^3 \times \mathrm{T}^4$ superstring
Ben Hoare, Fiona K. Seibold
https://arxiv.org/abs/2507.18548

Supersymmetry and integrability of the elliptic $\mathrm{AdS}_3 \times \mathrm{S}^3 \times \mathrm{T}^4$ superstring
We construct a 1-parameter family of Ramond-Ramond fluxes supporting the elliptic $\mathrm{AdS}_3 \times \mathrm{S}^3 \times \mathrm{T}^4$ metric with constant dilaton and preserving 8 of the 16 supercharges of the undeformed background. On the supersymmetric locus, we compute the tree-level worldsheet S-matrix in uniform light-cone gauge up to quadratic order in fermions and find that it non-trivially satisfies the classical Yang-Baxter equation. Moreover, imposing classical integrability and …

Lightweight Physics-Informed Zero-Shot Ultrasound Plane Wave Denoising
Hojat Asgariandehkordi, Mostafa Sharifzadeh, Hassan Rivaz
https://arxiv.org/abs/2506.21499

Lightweight Physics-Informed Zero-Shot Ultrasound Plane Wave Denoising
Ultrasound Coherent Plane Wave Compounding (CPWC) enhances image contrast by combining echoes from multiple steered transmissions. While increasing the number of angles generally improves image quality, it drastically reduces the frame rate and can introduce blurring artifacts in fast-moving targets. Moreover, compounded images remain susceptible to noise, particularly when acquired with a limited number of transmissions. We propose a zero-shot denoising framework tailored for low-angle CPWC ac…

GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models
Qifei Cui, Xinyu Lu
https://arxiv.org/abs/2506.21245 https://

GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models
This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures. By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions and iteratively enhances segmentation precision using adversarial loss constraints. Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated dataset…

Open strings in type IIB AdS$_3$ flux vacua
\'Alvaro Arboleya, Adolfo Guarino, Matteo Morittu, Giuseppe Sudano
https://arxiv.org/abs/2507.18529 https://

Open strings in type IIB AdS$_3$ flux vacua
The role of open strings is investigated in the context of AdS$_{3}$ flux vacua arising from type IIB orientifold reductions. On the one hand, contrary to expectations, the perturbative stability of certain recently found non-supersymmetric AdS$_{3}$ flux vacua is shown to be robust under fluctuations of the open-string moduli. On the other hand, a wealth of new perturbatively stable AdS$_{3}$ flux vacua appears as a consequence of the non-trivial dynamics of open-string moduli. We also comment…

Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
Jing Yang, Qunliang Xing, Mai Xu, Minglang Qiao
https://arxiv.org/abs/2506.21171

Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
Joint Photographic Experts Group (JPEG) achieves data compression by quantizing Discrete Cosine Transform (DCT) coefficients, which inevitably introduces compression artifacts. Most existing JPEG quality enhancement methods operate in the pixel domain, suffering from the high computational costs of decoding. Consequently, direct enhancement of JPEG images in the DCT domain has gained increasing attention. However, current DCT-domain methods often exhibit limited performance. To address this cha…

A Novel Framework for Integrating 3D Ultrasound into Percutaneous Liver Tumour Ablation
Shuwei Xing, Derek W. Cool, David Tessier, Elvis C. S. Chen, Terry M. Peters, Aaron Fenster
https://arxiv.org/abs/2506.21162

A Novel Framework for Integrating 3D Ultrasound into Percutaneous Liver Tumour Ablation
3D ultrasound (US) imaging has shown significant benefits in enhancing the outcomes of percutaneous liver tumour ablation. Its clinical integration is crucial for transitioning 3D US into the therapeutic domain. However, challenges of tumour identification in US images continue to hinder its broader adoption. In this work, we propose a novel framework for integrating 3D US into the standard ablation workflow. We present a key component, a clinically viable 2D US-CT/MRI registration approach, le…

Continuous spin superparticle in $4D$, ${\cal N}=1$ curved superspace
I. L. Buchbinder, S. A. Fedoruk
https://arxiv.org/abs/2507.18524 https://arxiv.org/pd…

Continuous spin superparticle in $4D$, ${\cal N}=1$ curved superspace
We present a new particle model that describes the dynamics of a $4D,$ $\mathcal{N}{=}\,1$ continuous spin particle in $AdS_4$ superspace and is a generalization of the continuous-spin superparticle model in flat $4D$, $\mathcal{N}{=}\,1$ superspace proposed in 2506.19709 [hep-th]. The model is described by $4D$, $\mathcal{N}{=}\,1$ superspace coordinates together with commuting spinor additional variables, which are inherent ingredients of continuous spin models. The Lagrangian and the system …

Development of MR spectral analysis method robust against static magnetic field inhomogeneity
Shuki Maruyama, Hidenori Takeshima
https://arxiv.org/abs/2506.20897

Development of MR spectral analysis method robust against static magnetic field inhomogeneity
Purpose:To develop a method that enhances the accuracy of spectral analysis in the presence of static magnetic field B0 inhomogeneity. Methods:The authors proposed a new spectral analysis method utilizing a deep learning model trained on modeled spectra that consistently represent the spectral variations induced by B0 inhomogeneity. These modeled spectra were generated from the B0 map and metabolite ratios of the healthy human brain. The B0 map was divided into a patch size of subregions, and t…

U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs
Racheal Mukisa, Arvind K. Bansal
https://arxiv.org/abs/2506.20689

U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs
Artificial intelligence, including deep learning models, will play a transformative role in automated medical image analysis for the diagnosis of cardiac disorders and their management. Automated accurate delineation of cardiac images is the first necessary initial step for the quantification and automated diagnosis of cardiac disorders. In this paper, we propose a deep learning based enhanced UNet model, U-R-Veda, which integrates convolution transformations, vision transformer, residual links…

Monte Carlo studies of the emergent spacetime in the polarized IKKT model
Chien-Yu Chou, Jun Nishimura, Cheng-Tsung Wang
https://arxiv.org/abs/2507.18472 https://

Monte Carlo studies of the emergent spacetime in the polarized IKKT model
The IKKT matrix model has been investigated as a promising nonperturbative formulation of superstring theory. One of the recent developments concerning this model is the discovery of the dual supergravity solution corresponding to the model obtained after supersymmetry-preserving mass deformation, which is dubbed the polarized IKKT model. Here we perform Monte Carlo simulations of this model in the case of matrix size N = 2 for a wide range of the deformation parameter Omega. While we reproduce…

Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation
Minglong Li, Lianlei Shan, Weiqiang Wang, Ke Lv, Bin Luo, Si-Bao Chen
https://arxiv.org/abs/2506.20688

Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation
Recently, there have been significant improvements in the accuracy of CNN models for semantic segmentation. However, these models are often heavy and suffer from low inference speed, which limits their practical application. To address this issue, knowledge distillation has emerged as a promising approach to achieve a good trade-off between segmentation accuracy and efficiency. In this paper, we propose a novel dual relation distillation (DRD) technique that transfers both spatial and channel r…

Global and Local Contrastive Learning for Joint Representations from Cardiac MRI and ECG
Alexander Selivanov, Philip M\"uller, \"Ozg\"un Turgut, Nil Stolt-Ans\'o, Daniel R\"uckert
https://arxiv.org/abs/2506.20683

Global and Local Contrastive Learning for Joint Representations from Cardiac MRI and ECG
An electrocardiogram (ECG) is a widely used, cost-effective tool for detecting electrical abnormalities in the heart. However, it cannot directly measure functional parameters, such as ventricular volumes and ejection fraction, which are crucial for assessing cardiac function. Cardiac magnetic resonance (CMR) is the gold standard for these measurements, providing detailed structural and functional insights, but is expensive and less accessible. To bridge this gap, we propose PTACL (Patient and …

[2025-06-27 Fri (UTC), 9 new articles found for eess.IV Image and Video Processing]
toXiv_bot_toot

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robus...
Zhang, Zhang, Cheng, Wang, Wang, Zhang, Yang, Wu, Huang, Aviles-Rivero, Gao, Yang, Lally
…

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new
[1/1]:
- Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases
Starck, Sideri-Lampretsa, Kainz, Menten, Mueller, Rueckert

Systematic Review of Pituitary Gland and Pituitary Adenoma Automatic Segmentation Techniques in Magnetic Resonance Imaging
Mubaraq Yakubu, Navodini Wijethilake, Jonathan Shapey, Andrew King, Alexander Hammers
https://arxiv.org/abs/2506.19797

Systematic Review of Pituitary Gland and Pituitary Adenoma Automatic Segmentation Techniques in Magnetic Resonance Imaging
Purpose: Accurate segmentation of both the pituitary gland and adenomas from magnetic resonance imaging (MRI) is essential for diagnosis and treatment of pituitary adenomas. This systematic review evaluates automatic segmentation methods for improving the accuracy and efficiency of MRI-based segmentation of pituitary adenomas and the gland itself. Methods: We reviewed 34 studies that employed automatic and semi-automatic segmentation methods. We extracted and synthesized data on segmentation te…

NeRF-based CBCT Reconstruction needs Normalization and Initialization
Zhuowei Xu, Han Li, Dai Sun, Zhicheng Li, Yujia Li, Qingpeng Kong, Zhiwei Cheng, Nassir Navab, S. Kevin Zhou
https://arxiv.org/abs/2506.19742

NeRF-based CBCT Reconstruction needs Normalization and Initialization
Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder's parameters is used (local sparse…

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Ahmad Mustafa, Reza Rastegar, Ghassan AlRegib
https://arxiv.org/abs/2506.19687 …

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Prostate gland segmentation from T2-weighted MRI is a critical yet challenging task in clinical prostate cancer assessment. While deep learning-based methods have significantly advanced automated segmentation, most conventional approaches-particularly 2D convolutional neural networks (CNNs)-fail to leverage inter-slice anatomical continuity, limiting their accuracy and robustness. Fully 3D models offer improved spatial coherence but require large amounts of annotated data, which is often imprac…

Filling of incomplete sinograms from sparse PET detector configurations using a residual U-Net
Klara Leffler, Luigi Tommaso Luppino, Samuel Kuttner, Karin S\"oderkvist, Jan Axelsson
https://arxiv.org/abs/2506.19600

Filling of incomplete sinograms from sparse PET detector configurations using a residual U-Net
Long axial field-of-view PET scanners offer increased field-of-view and sensitivity compared to traditional PET scanners. However, a significant cost is associated with the densely packed photodetectors required for the extended-coverage systems, limiting clinical utilisation. To mitigate the cost limitations, alternative sparse system configurations have been proposed, allowing an extended field-of-view PET design with detector costs similar to a standard PET system, albeit at the expense of i…

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
Joris Wuts, Jakub Ceranka, Nicolas Michoux, Fr\'ed\'eric Lecouvet, Jef Vandemeulebroucke
https://arxiv.org/abs/2506.19590

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
The segmentation of metastatic bone disease (MBD) in whole-body MRI (WB-MRI) is a challenging problem. Due to varying appearances and anatomical locations of lesions, ambiguous boundaries, and severe class imbalance, obtaining reliable segmentations requires large, well-annotated datasets capturing lesion variability. Generating such datasets requires substantial time and expertise, and is prone to error. While self-supervised learning (SSL) can leverage large unlabeled datasets, learned generi…

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Zhifeng Wang, Renjiao Yi, Xin Wen, Chenyang Zhu, Kai Xu, Kunlun He
https://arxiv.org/abs/2506.19455

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography …

NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
Khuram Naveed, Bruna Neves de Freitas, Ruben Pauwels
https://arxiv.org/abs/2506.19387

NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more effectively than high-frequency details. This leads to the loss of fine details, which is particularly problematic in dental radiographs where preserving subtle anatomical structures is crucial. While self-attention mechanisms can help mitigate this issue by …

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction
Solveig Thrun, Stine Hansen, Zijun Sun, Nele Blum, Suaiba A. Salahuddin, Kristoffer Wickstr{\o}m, Elisabeth Wetzer, Robert Jenssen, Maik Stille, Michael Kampffmeyer
https://arxiv.org/abs/2506.19363

Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction
Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focused only on current mammograms, recent approaches leverage the temporal aspect of screenings to track breast tissue changes over time, requiring spatial alignment across different time points. Two main strategies for this have emerged: explicit feature alignment through deformab…

Explicit Residual-Based Scalable Image Coding for Humans and Machines
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
https://arxiv.org/abs/2506.19297 https://…

Explicit Residual-Based Scalable Image Coding for Humans and Machines
Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition models. This shift has drawn growing attention to scalable image compression methods that serve both machine and human vision (ICMH). Many existing models employ neural network-based codecs, known as learned image compression, and have made significant strides i…

Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology
Can Cui, Xindong Zheng, Ruining Deng, Quan Liu, Tianyuan Yao, Keith T Wilson, Lori A Coburn, Bennett A Landman, Haichun Yang, Yaohong Wang, Yuankai Huo
https://arxiv.org/abs/2506.19234

Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology
Anomaly detection has been widely studied in the context of industrial defect inspection, with numerous methods developed to tackle a range of challenges. In digital pathology, anomaly detection holds significant potential for applications such as rare disease identification, artifact detection, and biomarker discovery. However, the unique characteristics of pathology images, such as their large size, multi-scale structures, stain variability, and repetitive patterns, introduce new challenges t…

Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
Xinke Ma, Yongsheng Pan, Qingjie Zeng, Mengkang Lu, Bolysbek Murat Yerzhanuly, Bazargul Matkerim, Yong Xia
https://arxiv.org/abs/2506.19222

Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
Effective representation of Regions of Interest (ROI) and independent alignment of these ROIs can significantly enhance the performance of deformable medical image registration (DMIR). However, current learning-based DMIR methods have limitations. Unsupervised techniques disregard ROI representation and proceed directly with aligning pairs of images, while weakly-supervised methods heavily depend on label constraints to facilitate registration. To address these issues, we introduce a novel ROI-…

VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction
Xin Zhu
https://arxiv.org/abs/2506.19181 https://arxiv.org/pdf…

VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction
Bias field artifacts in magnetic resonance imaging (MRI) scans introduce spatially smooth intensity inhomogeneities that degrade image quality and hinder downstream analysis. To address this challenge, we propose a novel variational Hadamard U-Net (VHU-Net) for effective body MRI bias field correction. The encoder comprises multiple convolutional Hadamard transform blocks (ConvHTBlocks), each integrating convolutional layers with a Hadamard transform (HT) layer. Specifically, the HT layer perfo…

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Benjamin Graham
https://arxiv.org/abs/2506.19167 https://

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Image registration is used in many medical image analysis applications, such as tracking the motion of tissue in cardiac images, where cardiac kinematics can be an indicator of tissue health. Registration is a challenging problem for deep learning algorithms because ground truth transformations are not feasible to create, and because there are potentially multiple transformations that can produce images that appear correlated with the goal. Unsupervised methods have been proposed to learn to pr…

Staining normalization in histopathology: Method benchmarking using multicenter dataset
Umair Khan, Jouni H\"ark\"onen, Marjukka Friman, Leena Latonen, Teijo Kuopio, Pekka Ruusuvuori
https://arxiv.org/abs/2506.19106

Staining normalization in histopathology: Method benchmarking using multicenter dataset
Hematoxylin and Eosin (H&E) has been the gold standard in tissue analysis for decades, however, tissue specimens stained in different laboratories vary, often significantly, in appearance. This variation poses a challenge for both pathologists' and AI-based downstream analysis. Minimizing stain variation computationally is an active area of research. To further investigate this problem, we collected a unique multi-center tissue image dataset, wherein tissue samples from colon, kidney, and skin …

Xray2Xray: World Model from Chest X-rays with Volumetric Context
Zefan Yang, Xinrui Song, Xuanang Xu, Yongyi Shi, Ge Wang, Mannudeep K. Kalra, Pingkun Yan
https://arxiv.org/abs/2506.19055

Xray2Xray: World Model from Chest X-rays with Volumetric Context
Chest X-rays (CXRs) are the most widely used medical imaging modality and play a pivotal role in diagnosing diseases. However, as 2D projection images, CXRs are limited by structural superposition, which constrains their effectiveness in precise disease diagnosis and risk prediction. To address the limitations of 2D CXRs, this study introduces Xray2Xray, a novel World Model that learns latent representations encoding 3D structural information from chest X-rays. Xray2Xray captures the latent rep…

NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
Georgii Bychkov, Khaled Abud, Egor Kovalev, Alexander Gushchin, Dmitriy Vatolin, Anastasia Antsiferova
https://arxiv.org/abs/2506.19051

NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI -- the first standard for end-to-end neural image compression (NIC) methods -- the question of evaluating NIC robustness has become critically significant. However, previous research has been limited to a narrow range of codecs and attacks. To address this, we present \textbf{NIC-RobustBench}, …

[2025-06-25 Wed (UTC), 16 new articles found for eess.IV Image and Video Processing]
toXiv_bot_toot