Fiducial marker positions in projection image of cone-beam computed tomography (CBCT) scans have been studied to evaluate daily residual motion during breath-hold radiation therapy. Fiducial marker migration posed challenges in accurately locating markers, prompting the development of a novel algorithm that reconstructs volumetric probability maps of marker locations from filtered gradient maps of projections. This guides the development of a Python-based algorithm to detect fiducial markers in projection images using Meta AI's Segment Anything Model 2 (SAM 2). Retrospective data from a pancreatic cancer patient with two fiducial markers were analyzed. The three-dimensional (3D) marker positions from simulation computed tomography (CT) were compared to those reconstructed from CBCT images, revealing a decrease in relative distances between markers over time. Fiducial markers were successfully detected in 2777 out of 2786 projection frames. The average standard deviation of superior-inferior (SI) marker positions was 0.56 mm per breath-hold, with differences in average SI positions between two breath-holds in the same scan reaching up to 5.2 mm, and a gap of up to 7.3 mm between the end of the first and beginning of the second breath-hold. 3D marker positions were calculated using projection positions and confirmed marker migration. This method effectively calculates marker probability volume and enables accurate fiducial marker tracking during treatment without requiring any specialized equipment, additional radiation doses, or manual initialization and labeling. It has significant potential for automatically assessing daily residual motion to adjust planning margins, functioning as an adaptive radiation therapy tool.

Partial differential equations (PDEs) are integral in modeling and describing the dynamics of many complex systems in science and engineering. Numerical solvers such as finite element methods (FEMs) and finite difference methods (FDMs) often obtain the solution of PDEs by discretizing the domain and solving a finite-dimensional problem. However, obtaining high-resolution solutions to PDEs using numerical simulations for complex large-scale problems can be computationally expensive and prohibitive. There has been a growing interest in more efficient data-driven alternatives that can directly learn the underlying solutions from the available data without requiring explicit knowledge about the governing PDEs [3, 11]. More recently, operator learning has emerged as a promising paradigm, aiming to learn an unknown mathematical operator governing a system of PDEs [4]. They capture mappings between infinite-dimensional function spaces and have demonstrated potential in capturing complex solution behaviors [18, 15]. Furthermore, due to their inherent differentiability, they can be seamlessly applied to inverse problems, such as design optimization tasks [1]. Various architectures have been developed, including the Deep Neural Operator (DeepONet) [18], Fourier Neural Operator (FNO) [15], Graph Neural Operator [16], General Neural Operator Transformer (GNOT) [9] and Operator Transformer (OFormer) [14]. These models differ in their discretization methods and the approximation techniques they use to enhance efficiency and scalability.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers. Shallow convolution neural networks(CNN's) are still an active research, where some phenomena are still unexplained. Activation functions used in the network are of utmost importance, as they provide non linearity to the networks. Relu's are the most commonly used activation function.We show a complex piece-wise linear(PWL) activation in the hidden layer. We show that these PWL activations work much better than relu activations in our networks for convolution neural networks and multilayer perceptrons. Result comparison in PyTorch for shallow and deep CNNs are given to further strengthen our case.

This work reveals undiscovered challenges in the performance and generalizability of deep learning models. We (1) identify spurious shortcuts and evaluation issues that can inflate performance and (2) propose training and analysis methods to address them. We trained an AI model to classify cancer on a retrospective dataset of 120,112 US exams (3,467 cancers) acquired from 2008 to 2017 and 16,693 UK exams (5,655 cancers) acquired from 2011 to 2015. We evaluated on a screening mammography test set of 11,593 US exams (102 cancers; 7,594 women; age 57.1 \pm 11.0) and 1,880 UK exams (590 cancers; 1,745 women; age 63.3 \pm 7.2). A model trained on images of only view markers (no breast) achieved a 0.691 AUC. The original model trained on both datasets achieved a 0.945 AUC on the combined US+UK dataset but paradoxically only 0.838 and 0.892 on the US and UK datasets, respectively. Sampling cancers equally from both datasets during training mitigated this shortcut. A similar AUC paradox (0.903) occurred when evaluating diagnostic exams vs screening exams (0.862 vs 0.861, respectively). Removing diagnostic exams during training alleviated this bias. Finally, the model did not exhibit the AUC paradox over scanner models but still exhibited a bias toward Selenia Dimension (SD) over Hologic Selenia (HS) exams. Analysis showed that this AUC paradox occurred when a dataset attribute had values with a higher cancer prevalence (dataset bias) and the model consequently assigned a higher probability to these attribute values (model bias). Stratification and balancing cancer prevalence can mitigate shortcuts during evaluation. Dataset and model bias can introduce shortcuts and the AUC paradox, potentially pervasive issues within the healthcare AI space. Our methods can verify and mitigate shortcuts while providing a clear understanding of performance.

The rapid spread of COVID-19 disease has had a significant impact on the world. In this paper, we study COVID-19 data interpretation and visualization using open-data sources for 351 cities and towns in Massachusetts from December 6, 2020 to September 25, 2021. Because cities are embedded in rather complex transportation networks, we construct the spatio-temporal dynamic graph model, in which the graph attention neural network is utilized as a deep learning method to learn the pandemic transition probability among major cities in Massachusetts. Using the spectral graph wavelet transform (SGWT), we process the COVID-19 data on the dynamic graph, which enables us to design effective tools to analyze and detect spatio-temporal patterns in the pandemic spreading. We design a new node classification method, which effectively identifies the anomaly cities based on spectral graph wavelet coefficients. It can assist administrations or public health organizations in monitoring the spread of the pandemic and developing preventive measures. Unlike most work focusing on the evolution of confirmed cases over time, we focus on the spatio-temporal patterns of pandemic evolution among cities. Through the data analysis and visualization, a better understanding of the epidemiological development at the city level is obtained and can be helpful with city-specific surveillance.

To evaluate the use of artificial intelligence (AI) to shorten digital breast tomosynthesis (DBT) reading time while maintaining or improving accuracy. A deep learning AI system was developed to identify suspicious soft-tissue and calcified lesions in DBT images. A reader study compared the performance of 24 radiologists (13 of whom were breast subspecialists) reading 260 DBT examinations (including 65 cancer cases) both with and without AI. Readings occurred in two sessions separated by at least 4 weeks. Area under the receiver operating characteristic curve (AUC), reading time, sensitivity, specificity, and recall rate were evaluated with statistical methods for multireader, multicase studies. Radiologist performance for the detection of malignant lesions, measured by mean AUC, increased 0.057 with the use of AI (95% confidence interval [CI]: 0.028, 0.087; P .01), Reading time decreased 52.7% (95% CI: 41.8%, 61.5%; P .01), Sensitivity increased from 77.0% without AI to 85.0% with AI (8.0%; 95% CI: 2.6%, 13.4%; P .01), The concurrent use of an accurate DBT AI system was found to improve cancer detection efficacy in a reader study that demonstrated increases in AUC, sensitivity, and specificity and a reduction in recall rate and reading time. See also the commentary by Hsu and Hoyt in this issue. Reading times were significantly reduced, and sensitivity, specificity, and recall rate improved in a nonclinical reader study when an artificial intelligence system was utilized concurrently with image interpretation for digital breast tomosynthesis.

Digital health products played a prominent role in addressing the COVID-19 pandemic and in helping caregivers and patients navigate their care in the past year. Going into 2022, remote monitoring, wearables, sensors, and other mobile health (mHealth) products are taking center stage in defining the future of medicine. "One of the clearest areas of excitement now and into the future is the sector of healthcare products referred to as wearables. These are devices like fitness trackers, heart monitors, and other devices that record in real time and communicate biometric data either directly to the user or to a connected platform for a variety of purposes, including coaching, intervention, analysis and even within clinical trials administration," notes a recent report from contract manufacturer Jabil, St. Petersburg, FL. The report, "Digital Health Technology Trends," finds that "the top three solution categories providers are developing or plan to develop are in patient monitoring, diagnostic equipment, and on-body or wearable devices (see Figure 1). As digital and mHealth capabilities have become an integral part of many medical devices and diagnostics, they have enabled a more agile and flexible healthcare system to emerge in the face of COVID-19. These products will continue to improve access to patient care. Digital transformation of healthcare is not just about adopting new digital technology, notes a recent position paper from medtech giant Philips. It's about reimagining healthcare for the digital age -- using the power of data, artificial intelligence (AI), cloud-based platforms, and new business models to improve health outcomes, lower the cost of care, and improve the human care experience for patients and staff alike."

General Electric Company is an American multinational conglomerate incorporated in New York City and headquartered in Boston. As of 2018, the company operates through the following segments: aviation, healthcare, power, renewable energy, digital industry, additive manufacturing and venture capital and finance. If you have forgotten your password you can reset it here.

Google Cloud and medical technology vendor Hologic, a women's health specialist, are working together on a new AI algorithmic approach to diagnosing cervical cancer. Cervical cancer is the fourth most common cancer in women. The World Health Organization (WHO) has targeted the disease for eradication. Hologic, based in Marlborough, Mass., in 2020 introduced its Genius Digital Diagnostic system, a digital cytology platform that combines advanced volumetric medical imaging technology and AI algorithms to help researchers identify abnormal cells in cervical and other cancers in women. Toward the WHO's ambitious goal, Google Cloud and Hologic in February 2021 unveiled a multiyear strategic collaboration based on integrating Google Cloud's machine learning (ML) technologies with Hologic's Genius system to significantly improve cervical cancer screening.