Enlarged perivascular spaces (ePVS) are fluid-filled spaces around small blood vessels in the brain that can become more visible with aging and small vessel disease and may reflect reduced clearance of waste from the brain. Measuring ePVS manually on MRI scans is time-consuming and impractical for large studies. To address this, researchers developed DORES, a deep learning tool that automatically identifies and measures ePVS using two types of brain MRI images. The model was developed using data from the 91³Ô¹ÏÍø Memory and Aging Project and evaluated against expert manual measurements and three other automated tools. DORES showed good performance in identifying ePVS in both white matter and the basal ganglia, a group of structures deep within the brain, and its estimates of ePVS number and volume agreed well with expert measurements. Testing on an independent Alzheimer’s disease imaging dataset showed somewhat lower performance, as was also observed with the other automated methods. Results also varied depending on the type of MRI scanner used, suggesting that scanner differences can affect measurement consistency. Overall, DORES provides a promising automated approach for measuring ePVS in older adults, although scanner-related differences should be considered when applying the method across multiple research sites.

Fig. 1.ÌýRepresentative White Matter ePVS Segmentations of DORES Performance in VMAP.

T₁-weighted axial scans were selected to illustrate DORES performance at the 25th (top row; DiceÌý=Ìý0.55), 50th (middle row; DiceÌý=Ìý0.63), and 75th (bottom row; DiceÌý=Ìý0.73) percentiles of white matter regional Dice scores. The first column displays the raw, skull-stripped images in the white matter. The second column displays the corresponding segmentation overlays. Manual segmentations are shown in blue, whereas DORES predictions are shown in red. Voxels where manual and DORES segmentations overlap appear purple. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

]]> /valiant/2026/08/24/correction-aware-interactive-3d-tumor-segmentation-with-sparse-and-revisable-prompts/ Mon, 24 Aug 2026 16:27:08 +0000 /valiant/?p=7339 Li, Hao; Li, Haoxuan. (2026). . Visual Computer, 42(9), 370.

Interactive 3D tumor segmentation allows users to correct computer-generated tumor outlines using visual prompts such as clicks, boxes, and scribbles. However, many existing methods are developed under simplified prompting conditions that do not reflect real-world use, where users may provide different types of prompts, correct only selected image slices, and revise earlier instructions over multiple rounds. We developed a correction-aware framework that treats prompts as ongoing revisions to an evolving tumor outline. The method combines clicks, a 3D bounding box, and scribbles with feedback from the current segmentation, focuses new prompts on remaining errors, supports scribbles on only selected informative slices to reduce user effort, and keeps track of revised instructions. We evaluated the method on the MSD-Colon and KiTS21 kidney tumor datasets and compared it with automatic and other interactive segmentation approaches. The proposed method achieved higher segmentation accuracy across different prompting conditions, with greater improvements when scribbles were limited to a small number of informative slices. It also produced more consistent results when earlier instructions were changed. These findings suggest that treating interactive 3D tumor segmentation as an iterative and revisable correction process can improve accuracy while reducing the amount of user input required.

Fig. 1

High-level overview of the proposed interactive 3D tumor segmentation framework. Starting from an initial mask that may contain under- or over-segmentation, the user inspects the current prediction and adds heterogeneous prompts, including clicks, scribbles, and a bounding box. The model refines the mask by combining the current prompts, the previous prediction, and a revision-aware prompt memory. The framework is designed to improve accuracy across prompt protocols, support sparse interaction on informative slices, and provide a defined prompt-history representation when prompts are revised across rounds

This study addresses the challenge ofÌýautomatic polyp segmentation, the process of identifying and outlining polyps in colonoscopy images. While many artificial intelligence (AI) models perform well on the data they were trained on, they often struggle when tested on images from different hospitals or datasets because polyps can vary widely in size, shape, color, and appearance. Differences in image quality, such as glare from reflected light, blur, fluid, and changes in lighting during colonoscopy, add to this challenge. To improve performance across different datasets, the researchers developedÌýHAT-SAM3, an adaptation of theÌýSegment Anything Model 3 (SAM 3), a large pre-trained AI model originally designed for image segmentation. HAT-SAM3 uses a training technique calledÌýhighlight-aware training (HAT), which helps the model better handle bright reflections commonly seen in endoscopy images without changing how the model operates during testing. When evaluated on five publicly available datasets, HAT-SAM3 achieved an averageÌýDice score(a measure of how closely the model’s predicted outlines match the true polyp boundaries) of 0.884 and produced the best reported results on four of the five datasets. In additional testing, where the model was trained on one dataset and evaluated on three completely separate datasets without further training, HAT-SAM3 consistently outperformed the strongest previously reported method. These results suggest that adapting a pre-trained foundation model with endoscopy-specific training techniques can improve the accuracy and reliability of automated polyp segmentation across a wide range of clinical datasets. The researchers have also made their code publicly available to support future research.

Fig 1: Motivation of HAT-SAM3. A task-specific polyp segmenter can perform well when training and test images come from the same visual distribution, but degrade under cross-domain changes in illumination, blur, specular reflection, and polyp appearance. HAT-SAM3 uses a broad segmentation prior with endoscopy-aware adaptation to improve cross-domain polyp segmentation

Wearable cameras can record daily life in a simple and convenient way, making it possible to analyze real-world activities as they happen. A major challenge is turning long, unorganized video into meaningful events, a process called temporal segmentation, which helps both people and computers understand what is happening in the footage. This is especially difficult for wearable camera video because the viewpoint changes constantly, activities vary a lot from place to place, and videos can be any length. To address this, the researchers developed SmartSeg, an unsupervised method that does not require labeled training data. SmartSeg uses a Temporal Self-Similarity Metric encoder, a model that looks for patterns of similarity across the video, and then groups sequences of frames into events using clustering, a technique that collects similar items together. The method was tested on three different datasets and outperformed current best methods, including a 50% improvement in Mean-over-Frames on one first-person video dataset. The researchers also applied it to nursing simulation videos, where it successfully separated complex and noisy interactions into meaningful activity changes. Overall, SmartSeg appears to be a strong tool for breaking long, messy wearable camera videos into understandable events in real-world settings.

Fig. 1.ÌýChallenges in temporal segmentation of wearable camera videos, illustrated with an example from a real-world nursing simulation.Ìý(1)Instability of camera views: Frequent head movements introduce changes in viewpoint, motion blur, and lighting variations.Ìý(2)ÌýDiverse activities and environments: The video contains over 10 distinct clinical activities performed across multiple environments (e.g., hallway, patient room, medication station), making segmentation more complex.Ìý(3)ÌýFlexible Duration: The total video length exceeds 21 min, which poses challenges for long-range temporal modeling and efficient segmentation.

Multiple sclerosis (MS) causes lesions, or areas of damage, in the brain that can be seen on multicontrast magnetic resonance (MR) images. Automatically segmenting, or outlining, these lesions using deep learning (DL) can improve speed and consistency compared to manual tracing by experts. Although many DL methods perform well on data similar to what they were trained on, they often struggle when tested on new datasets from different hospitals or scanners, a problem known as poor out-of-domain generalization.

To address this issue, the researchers developed a new method called UNISELF. The goal of UNISELF is to achieve high segmentation accuracy within the original training domain while also performing well on data from different sources. UNISELF introduces a test-time self-ensembled lesion fusion strategy, which combines multiple predictions at test time to improve accuracy. It also uses test-time instance normalization (TTIN) of latent features, meaning it adjusts internal feature representations during testing to better handle domain shifts and missing input contrasts, such as when certain MR image types are unavailable.

The model was trained using data from the ISBI 2015 longitudinal MS segmentation challenge. On the official test dataset, UNISELF ranked among the top-performing methods. Importantly, when evaluated on out-of-domain datasets with different scanners, imaging protocols, and missing contrasts—including the MICCAI 2016 dataset, the UMCL dataset, and a private multisite dataset—UNISELF outperformed other benchmark models trained on the same ISBI data. These results suggest that UNISELF is both accurate and robust to real-world variations in MR imaging, making it a promising tool for automated MS lesion segmentation across diverse clinical settings.

Fig. 1.ÌýAn illustration of the spatial augmentation, network input, and network output during training in UNISELF.

Segmenting structures and lesions inside kidney glomeruli usually requires expert nephropathologists to carefully examine tissue morphology, a process that is time-consuming and can vary between observers. Building on their earlier Glo In One toolkit for detecting and segmenting glomeruli, the authors developed Glo In One version 2, which adds more detailed segmentation capabilities. They created a large annotated dataset containing 14 labels that cover tissue regions, cell types, and glomerular lesions across 23,529 glomeruli from both human and mouse kidney histopathology images, making it one of the largest datasets of its kind. Using this dataset, they trained a single deep learning model with a dynamic head architecture to segment all 14 classes from partially labeled whole slide images. The model was trained on 368 annotated kidney slides and learned to identify five intraglomerular tissue types and nine lesion types. The model achieved solid performance, with an average Dice similarity coefficient of 76.5 percent for glomerulus segmentation. In addition, using transfer learning, where knowledge learned from mouse data is applied to human data, improved lesion segmentation accuracy by more than 3 percent across lesion types. Overall, this work introduces a publicly available convolutional neural network that enables detailed, multiclass segmentation of glomerular tissue and lesions, helping reduce manual workload and variability in kidney pathology analysis.

Fig.Ìý1

This figure presents fine-grained classes of intraglomerular tissue, including Bowman’s capsule (Cap), tuft (Tuft), mesangium (Mes), mesangial cells (Mec), and podocytes (Pod). It also highlights the glomerular lesions observed in rodents and humans: AH, adhesion; CD, capsular drop; GS, global sclerosis; HS, hyalinosis; ML, mesangial lysis; MA, microaneurysm; NS, nodular sclerosis; ME, mesangial expansion; SS segmental sclerosis.

]]> /valiant/2025/07/28/towards-fair-decentralized-benchmarking-of-healthcare-ai-algorithms-with-the-federated-tumor-segmentation-fets-challenge/ Mon, 28 Jul 2025 13:58:31 +0000 /valiant/?p=4769 Zenk, Maximilian, Baid, Ujjwal, Pati, Sarthak, Linardos, Akis, Edwards, Brandon, Sheller, Micah, Foley, Patrick, Aristizabal, Alejandro, Zimmerer, David, Gruzdev, Alexey, Martin, Jason, Shinohara, Russell T., Reinke, Annika, Isensee, Fabian, Parampottupadam, Santhosh, Parekh, Kaushal, Floca, Ralf, Kassem, Hasan, Baheti, Bhakti, Thakur, Siddhesh, Chung, Verena, Kushibar, Kaisar, Lekadir, Karim, Jiang, Meirui, Yin, Youtan, Yang, Hongzheng, Liu, Quande, Chen, Cheng, Dou, Qi, Heng, Pheng-Ann, Zhang, Xiaofan, Zhang, Shaoting, Khan, Muhammad Irfan, Azeem, Mohammad Ayyaz, Jafaritadi, Mojtaba, Alhoniemi, Esa, Kontio, Elina, Khan, Suleiman A., Mächler, Leon, Ezhov, Ivan, Kofler, Florian, Shit, Suprosanna, Paetzold, Johannes C., Loehr, Timo, Wiestler, Benedikt, Peiris, Himashi, Pawar, Kamlesh, Zhong, Shenjun, Chen, Zhaolin, Hayat, Munawar, Egan, Gary, Harandi, Mehrtash, Isik Polat, Ece, Polat, Gorkem, Kocyigit, Altan, Temizel, Alptekin, Tuladhar, Anup, Tyagi, Lakshay, Souza, Raissa, Forkert, Nils D., Mouches, Pauline, Wilms, Matthias, Shambhat, Vishruth, Maurya, Akansh, Danannavar, Shubham Subhas, Kalla, Rohit, Anand, Vikas Kumar, Krishnamurthi, Ganapathy, Nalawade, Sahil, Ganesh, Chandan, Wagner, Ben, Reddy, Divya, Das, Yudhajit, Yu, Fang F., Fei, Baowei, Madhuranthakam, Ananth J., Maldjian, Joseph, Singh, Gaurav, Ren, Jianxun, Zhang, Wei, An, Ning, Hu, Qingyu, Zhang, Youjia, Zhou, Ying, Siomos, Vasilis, Tarroni, Giacomo, Passerrat-Palmbach, Jonathan, Rawat, Ambrish, Zizzo, Giulio, Kadhe, Swanand Ravindra, Epperlein, Jonathan P., Braghin, Stefano, Wang, Yuan, Kanagavelu, Renuga, Wei, Qingsong, Yang, Yechao, Liu, Yong, Kotowski, Krzysztof, Adamski, Szymon, Machura, Bartosz, Malara, Wojciech, Zarudzki, Lukasz, Nalepa, Jakub, Shi, Yaying, Gao, Hongjian, Avestimehr, Salman, Yan, Yonghong, Akbar, Agus S., Kondrateva, Ekaterina, Yang, Hua, Li, Zhaopei, Wu, Hung-Yu, Roth, Johannes, Saueressig, Camillo, Milesi, Alexandre, Nguyen, Quoc D., Gruenhagen, Nathan J., Huang, Tsung-Ming, Ma, Jun, Singh, Har Shwinder H., Pan, Nai-Yu, Zhang, Dingwen, Zeineldin, Ramy A., Futrega, Michal, Yuan, Yading, Conte, Gian Marco, Feng, Xue, Pham, Quan D., Xia, Yong, Jiang, Zhifan, Luu, Huan Minh, Dobko, Mariia, Carré, Alexandre, Tuchinov, Bair, Mohy-ud-Din, Hassan, Alam, Saruar, Singh, Anup, Shah, Nameeta, Wang, Weichung, Sako, Chiharu, Bilello, Michel, Ghodasara, Satyam, Mohan, Suyash, Davatzikos, Christos, Calabrese, Evan, Rudie, Jeffrey, Villanueva-Meyer, Javier, Cha, Soonmee, Hess, Christopher, Mongan, John, Ingalhalikar, Madhura, Jadhav, Manali, Pandey, Umang, Saini, Jitender, Huang, Raymond Y., Chang, Ken, To, Minh-Son, Bhardwaj, Sargam, Chong, Chee, Agzarian, Marc, Kozubek, Michal, Lux, Filip, Michálek, Jan, Matula, Petr, Kerškovský, Miloš, Kopřivová, Tereza, Dostál, Marek, Vybíhal, Václav, Pinho, Marco C., Holcomb, James, Metz, Marie, Jain, Rajan, Lee, Matthew D., Lui, Yvonne W., Tiwari, Pallavi, Verma, Ruchika, Bareja, Rohan, Yadav, Ipsa, Chen, Jonathan, Kumar, Neeraj, Gusev, Yuriy, Bhuvaneshwar, Krithika, Sayah, Anousheh, Bencheqroun, Camelia, Belouali, Anas, Madhavan, Subha, Colen, Rivka R., Kotrotsou, Aikaterini, Vollmuth, Philipp, Brugnara, Gianluca, Preetha, Chandrakanth J., Sahm, Felix, Bendszus, Martin, Wick, Wolfgang, Mahajan, Abhishek, Balaña, Carmen, Capellades, Jaume, Puig, Josep, Choi, Yoon Seong, Lee, Seung-Koo, Chang, Jong Hee, Ahn, Sung Soo, Shaykh, Hassan F., Herrera-Trujillo, Alejandro, Trujillo, Maria, Escobar, William, Abello, Ana, Bernal, Jose, Gómez, Jhon, LaMontagne, Pamela, Marcus, Daniel S., Milchenko, Mikhail, Nazeri, Arash, Landman, Bennett, Ramadass, Karthik, Xu, Kaiwen, Chotai, Silky, Chambless, Lola B., Mistry, Akshitkumar, Thompson, Reid C., Srinivasan, Ashok, Bapuraj, J. Rajiv, Rao, Arvind, Wang, Nicholas, Yoshiaki, Ota, Moritani, Toshio, Turk, Sevcan, Lee, Joonsang, Prabhudesai, Snehal, Garrett, John, Larson, Matthew, Jeraj, Robert, Li, Hongwei, Weiss, Tobias, Weller, Michael, Bink, Andrea, Pouymayou, Bertrand, Sharma, Sonam, Tseng, Tzu-Chi, Adabi, Saba, Xavier Falcão, Alexandre, Martins, Samuel B., Teixeira, Bernardo C. A., Sprenger, Flávia, Menotti, David, Lucio, Diego R., Niclou, Simone P., Keunen, Olivier, Hau, Ann-Christin, Pelaez, Enrique, Franco-Maldonado, Heydy, Loayza, Francis, Quevedo, Sebastian, McKinley, Richard, Slotboom, Johannes, Radojewski, Piotr, Meier, Raphael, Wiest, Roland, Trenkler, Johannes, Pichler, Josef, Necker, Georg, Haunschmidt, Andreas, Meckel, Stephan, Guevara, Pamela, Torche, Esteban, Mendoza, Cristobal, Vera, Franco, Ríos, Elvis, López, Eduardo, Velastin, Sergio A., Choi, Joseph, Baek, Stephen, Kim, Yusung, Ismael, Heba, Allen, Bryan, Buatti, John M., Zampakis, Peter, Panagiotopoulos, Vasileios, Tsiganos, Panagiotis, Alexiou, Sotiris, Haliassos, Ilias, Zacharaki, Evangelia I., Moustakas, Konstantinos, Kalogeropoulou, Christina, Kardamakis, Dimitrios M., Luo, Bing, Poisson, Laila M., Wen, Ning, Vallières, Martin, Loutfi, Mahdi Ait Lhaj, Fortin, David, Lepage, Martin, Morón, Fanny, Mandel, Jacob, Shukla, Gaurav, Liem, Spencer, Alexandre, Gregory S., Lombardo, Joseph, Palmer, Joshua D., Flanders, Adam E., Dicker, Adam P., Ogbole, Godwin, Oyekunle, Dotun, Odafe-Oyibotha, Olubunmi, Osobu, Babatunde, Shu’aibu Hikima, Mustapha, Soneye, Mayowa, Dako, Farouk, Dorcas, Adeleye, Murcia, Derrick, Fu, Eric, Haas, Rourke, Thompson, John A., Ormond, David Ryan, Currie, Stuart, Fatania, Kavi, Frood, Russell, Simpson, Amber L., Peoples, Jacob J., Hu, Ricky, Cutler, Danielle, Moraes, Fabio Y., Tran, Anh, Hamghalam, Mohammad, Boss, Michael A., Gimpel, James, Kattil Veettil, Deepak, Schmidt, Kendall, Cimino, Lisa, Price, Cynthia, Bialecki, Brian, Marella, Sailaja, Apgar, Charles, Jakab, Andras, Weber, Marc-André, Colak, Errol, Kleesiek, Jens, Freymann, John B., Kirby, Justin S., Maier-Hein, Lena, Albrecht, Jake, Mattson, Peter, Karargyris, Alexandros, Shah, Prashant, Menze, Bjoern, Maier-Hein, Klaus, & Bakas, Spyridon. (2025). *Nature Communications, 16*(1), 6274.

Competitions are commonly used to test and compare computer algorithms for analyzing medical images. However, these competitions usually rely on small, carefully chosen datasets collected from only a few hospitals. This doesn’t reflect the reality of working with patient data from many different medical centers, which can vary a lot. TheÌýFederated Tumor Segmentation (FeTS) ChallengeÌýwas designed to better reflect real-world conditions. It tests two things: (i) how wellÌýfederated learningÌýmethods (where data stays at each hospital and only the model updates are shared) can combine information from different locations, and (ii) how well the latestÌýtumor segmentationÌýalgorithms perform across a wide range of data sources.

The challenge used brain tumor data from many hospitals to simulate how federated learning would work in real life. The results showed that algorithms that couldÌýadaptively combine informationÌýfrom different sites did better, and selecting which hospitals (clients) to involve at each step helped save time and resources. When the best segmentation algorithms were tested using brain scan data from 32 institutions around the world, they generally performed well, but in some cases, they struggled due to differences in the data. This shows that using data from many sites is important for making sure healthcare AI tools actually work in the real world.

Fig. 1: Concept and main findings of the Federated Tumor Segmentation (FeTS) Challenge.

The FeTS challenge is an international competition to benchmark brain tumor segmentation algorithms, involving data contributors, participants, and organizers across the globe. Test data hubs are geographically distributed while training data is centralized. Participants include those from the 2021 and 2022 challenges. Task 1 focused on simulated federated learning and we consistently saw an increase in performance by teams utilizing variants of selective sampling in their federated aggregation. In Task 2, submissions are distributed among the test data hubs for evaluation. As a representative example, the top-ranked model shows good average segmentation performance (measured by the Dice Similarity coefficient, DSC) but also failures for individual cases. Cases with empty tumor regions and data sites with less than 40 cases are not shown in the strip plot. Source data are provided as a Source Data file.

2024, .Ìý

Ìý

Attention-based models are becoming increasingly popular for tasks like image analysis and segmentation, but working with high-resolution images, like those used in pathology, presents challenges. The typical method involves breaking the images into small patches and processing them in sequence, but this becomes very resource-intensive for high-resolution images, making it difficult to use these models efficiently. One solution has been to either use complex multi-resolution models or simplified attention methods, but these come with their own challenges.Ìý

In this study, we drew inspiration from a technique used in high-performance computing called Adaptive Mesh Refinement (AMR). Instead of dividing the entire image into patches upfront, we dynamically adjust the patches based on the details in the image, allowing us to significantly reduce the number of patches needed for processing. This approach adds minimal extra work and can be easily used with any attention-based model. Our method not only improved the quality of image segmentation compared to existing models, but it also increased processing speed by an average of 6.9 times, even for images with very high resolutions (up to 64K²), while running on up to 2,048 GPUs.Ìý

Ìý

Magnetic resonance (MR) imaging is widely used to monitor the body non-invasively, but the results can vary due to differences in scanner hardware, software, and imaging protocols. This variability can create challenges for processing algorithms, which may struggle to handle these differences consistently. To address this, image harmonization is used to reduce these variations and improve the accuracy of tasks like segmentation. However, most harmonization models focus on imaging parameters like inversion or repetition time and overlook the impact of image resolution.Ìý

This study evaluates how image resolution affects harmonization by using a pretrained harmonization algorithm. We simulated different 2D image resolutions by altering slice thickness and gaps in high-resolution 3D MR images and analyzed how the harmonization algorithm performs with these changes. Our findings show that low-resolution images cause issues for harmonization, as it doesn’t fully account for resolution and orientation differences. While super-resolution techniques can help address this, they are not always used in practice. This approach highlights the importance of understanding the limits of harmonization algorithms and how resolution affects their reliability, offering guidance for preprocessing steps and ensuring trust in imaging results.Ìý

Fig. 1.Ìý

Slice thickness occurrences for each MRI image contrast: T1w, T2w, and T2w-FLAIRÌý

This study focuses on improving the automatic detection and segmentation of multiple sclerosis (MS) lesions in MRI scans, a process that is crucial for efficient and consistent diagnosis but traditionally performed manually. Current automated methods often rely on complex modifications to U-Net-based architectures to improve performance. However, these modifications can limit how well the models generalize across different MRI datasets with varying contrasts or image quality.

The researchers aimed to address this by developing a segmentation model based on the standard U-Net architecture, without any additional modifications, to create a more accurate and generalizable tool for detecting MS lesions. They introduced a novel self-ensembling technique that enhances model performance during testing by combining multiple predictions into a final, refined segmentation. This approach not only achieved the highest performance in the widely recognized ISBI 2015 MS lesion segmentation challenge but also showed that it is robust across different settings of the self-ensemble parameters.

Additionally, the study found that using instance normalization, rather than the more common batch normalization, improved the model’s ability to generalize across clinical MRI data from various scanners, making it more versatile in real-world applications. This work demonstrates that sophisticated modifications to architectures are not always necessary to achieve high accuracy and that simple techniques, when applied thoughtfully, can result in highly generalizable and efficient models for MS lesion segmentation.