Search

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often struggle with flexibility for partially annotated datasets and extensibility for new classes due to limitations in the one-hot encoding, architectural design, and learning scheme. To overcome these limitations, we propose a universal, extensible framework enabling a single model, termed Universal Model, to deal with multiple public datasets and adapt to new classes (e.g., organs/tumors). Firstly, we introduce a novel language-driven parameter generator that leverages language embeddings from large language models, enriching semantic encoding compared with one-hot encoding. Secondly, the conventional output layers are replaced with lightweight, class-specific heads, allowing Universal Model to simultaneously segment 25 organs and six types of tumors and ease the addition of new classes. We train our Universal Model on 3,410 CT volumes assembled from 14 publicly available datasets and then test it on 6,173 CT volumes from four external datasets. Universal Model achieves first place on six CT tasks in the Medical Segmentation Decathlon (MSD) public leaderboard and leading performance on the Beyond The Cranial Vault (BTCV) dataset. In summary, Universal Model exhibits remarkable computational efficiency (6x faster than other dataset-specific models), demonstrates strong generalization across different hospitals, transfers well to numerous downstream tasks, and more importantly, facilitates the extensibility to new classes while alleviating the catastrophic forgetting of previously learned classes. Codes, models, and datasets are available at https://github.com/ljwztc/CLIP-Driven-Universal-Model, Comment: Accepted to Medical Image Analysis

Deep learning classifiers face significant challenges when dealing with heterogeneous multi-modal and multi-organ biomedical datasets. The low-level feature distinguishability limited to imaging-modality hinders the classifiers' ability to learn high-level semantic relationships, resulting in sub-optimal performance. To address this issue, image augmentation strategies are employed as regularization techniques. While additive noise input during network training is a well-established augmentation as regularization method, modern pipelines often favor more robust techniques such as dropout and weight decay. This preference stems from the observation that combining these established techniques with noise input can adversely affect model performance. In this study, we propose a novel pretraining pipeline that learns to generate conditional noise mask specifically tailored to improve performance on multi-modal and multi-organ datasets. As a reinforcement learning algorithm, our approach employs a dual-component system comprising a very light-weight policy network that learns to sample conditional noise using a differentiable beta distribution as well as a classifier network. The policy network is trained using the reinforce algorithm to generate image-specific noise masks that regularize the classifier during pretraining. A key aspect is that the policy network's role is limited to obtaining an intermediate (or heated) model before fine-tuning. During inference, the policy network is omitted, allowing direct comparison between the baseline and noise-regularized models. We conducted experiments and related analyses on RadImageNet datasets. Results demonstrate that fine-tuning the intermediate models consistently outperforms conventional training algorithms on both classification and generalization to unseen concept tasks., Comment: 13 pages; 8 figures; 5 tables

Private network deployment is gaining momentum in warehouses, retail, automation, health care, and many such use cases to guarantee mission-critical services with less latency. Guaranteeing the delay-sensitive application in Wi-Fi is always challenging due to the nature of unlicensed spectrum. As the device ecosystem keeps growing and expanding, all the current and future devices can support both Wi-Fi and Private Cellular Network (CBRS is the primary spectrum in the US for private network deployment). However, due to the existing infrastructure and huge investment in the dense Wi-Fi network, consumers prefer two deployment models. The first scenario is deploying the private network outdoors and using the existing Wi-Fi indoors. The second scenario is to use the existing Wi-Fi network as a backup for offloading the traffic indoors and parallely utilizes the private network deployment for less latency applications. Hence, we expect, in both scenarios, a roaming between two technologies \emph{i.e.,} Wi-Fi and Private Cellular Network. In this work, we would like to quantify the roaming performance or service interruption time when the device moves from Wi-Fi to Private Network (CBRS) and vice-versa., Comment: Accepted in IEEE ICNC 2024

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational methods. The method (VCL) utilizes variational contrastive learning with beta-divergence to learn robustly from unlabelled datasets, including uncurated and noisy datasets. We demonstrate the effectiveness of the proposed method through rigorous experiments including linear evaluation and fine-tuning scenarios with multi-label datasets in the face understanding domain. In almost all tested scenarios, VCL surpasses the performance of state-of-the-art self-supervised methods, achieving a noteworthy increase in accuracy.

The 3.7 - 3.98 GHz frequency band (also known as C-band) was recently allocated in the US for the deployment of 5G cellular services. Prior to this, the lower adjacent band, 3.55 - 3.7 GHz, had been allocated to Citizens Broadband Radio Service (CBRS), where the entire 150 MHz can be used for free by Tier 3 General Authorized Access (GAA) users, but access to the spectrum needs to be authorized by the Spectrum Access System (SAS). GAA users are allowed on a channel only when there are no Tier 1 Incumbents (Navy radars) or Tier 2 Priority Access License (PAL) users in the area. However, since there are no guard bands between GAA and C-band, and both systems employ Time Division Duplexing (TDD) where the uplink/downlink configurations are not synchronized, adjacent channel interference can potentially reduce the performance of both systems. In this paper, we quantify the effect of this mutual interference by performing experiments with a real-world deployment. We observe significant downlink throughput reductions on both systems when two devices are in close proximity to each other, and one is transmitting uplink while the other is transmitting downlink: 60% for 4G CBRS and 43% for 5G C-band. We believe that this is the first paper to demonstrate this in a real deployment. This throughput degradation was reduced when the CBSD changed its channel and operated 20 MHz away from C-band, essentially creating a guard band between the channels. We also demonstrate the improvement in latency under adjacent channel interference by implementing MicroSlicing at the CBSD. Our results indicate that addressing adjacent channel interference due to the lack of guard bands and TDD configuration mismatch is crucial to improving the performance of both CBRS and C-band systems.

Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detecting COVID-19 infection, combining slice-based (2D) and volume-based (3D) approaches. The 2D system detects the infection on each CT slice independently, combining them to obtain the patient-level decision via different methods (averaging and long-short term memory networks). The 3D system takes the whole CT volume to arrive to the patient-level decision in one step. A new high resolution chest CT scan dataset, called the IST-C dataset, is also collected in this work. The proposed ensemble, called IST-CovNet, obtains 90.80% accuracy and 0.95 AUC score overall on the IST-C dataset in detecting COVID-19 among normal controls and other types of lung pathologies; and 93.69% accuracy and 0.99 AUC score on the publicly available MosMed dataset that consists of COVID-19 scans and normal controls only. The system is deployed at Istanbul University Cerrahpasa School of Medicine.

Leibniz's Monadology mentions perceptional and sentimental variations of the individual in the city. It is the interaction of people with people and events. Film festivals are highly sentimental events of multicultural cities. Each movie has a different sentimental effect and the interactions with the movies have reflections that can be observed on social media. This analysis aims to apply distant reading on Berlinale tweets collected during the festival. On contrary to close reading, distant reading let authors to observe patterns in large collection of data. The analysis is temporal and sentimental in multilingual domain and strongly positive and negative time intervals are analysed. For this purpose, we trained a deep sentiment network with multilingual embeddings. These multilingual embeddings are aligned in latent space. We trained the network with a multilingual dataset in three languages English, German and Spanish. The trained algorithm has a 0.78 test score and applied on Tweets with Berlinale hashtag during the festival. Although the sentimental analysis does not reflect the award-winning films, we observe weekly routine on the relationship between sentimentality, which can mislead a close reading analysis. We have also remarks on popularity of the director or actors., Comment: 5 pages, 3 figures

In this study, the effectiveness of the video prompting method and its maintenance and social validity were investigated in cloth folding skill teaching for individuals with autism spectrum disorder. Three male individuals with autism spectrum disorder were included in the study. In the research, inter-observer multiple-probe with a single-subject research model was used. As a result of the research, 3 participants achieved the target behavior successfully. It was observed that the maintenance of the behaviors acquired in both participants continued as 10, 20, 30. In a participant, the data of maintenance was collected for 10, 20 days and it was observed that the behavior was preserved, yet on the 30th day, the maintenance data could not be collected. For social validation, families reported positive opinions.