Learning spurious correlations and biases, harmful shortcuts, obstructs deep neural networks from acquiring meaningful and useful representations, leading to compromised generalizability and interpretability of the resulting model. The limited and restricted clinical data in medical image analysis intensifies the seriousness of the situation; thereby demanding exceptionally reliable, generalizable, and transparent learned models. This paper presents a novel eye-gaze-guided vision transformer (EG-ViT) model, designed to mitigate the pitfalls of shortcut learning in medical imaging applications. It leverages radiologists' visual attention to proactively focus the vision transformer (ViT) on regions indicative of potential pathology, instead of distracting spurious correlations. The EG-ViT model utilizes masked image patches of radiologic interest as input, supplemented by a residual connection to the final encoder layer, preserving interactions among all patches. Experiments performed on two medical imaging datasets indicate that the EG-ViT model effectively counteracts harmful shortcut learning, leading to enhanced model interpretability. In the meantime, leveraging the specialized knowledge of the experts can also enhance the overall performance of the large-scale Vision Transformer (ViT) model compared to baseline methods, particularly when only a limited number of samples are accessible. EG-ViT, in its overall functionality, draws upon the advantages of sophisticated deep neural networks, thereby overcoming the detrimental implications of shortcut learning using the knowledge base of human experts. This study also presents novel possibilities for upgrading prevailing artificial intelligence systems by weaving in human intelligence.

The non-invasive nature and excellent spatial and temporal resolution of laser speckle contrast imaging (LSCI) make it a widely adopted technique for in vivo, real-time detection and assessment of local blood flow microcirculation. Despite advancements, the precise segmentation of vascular structures in LSCI images remains a formidable task, due to a multitude of unique noise artifacts originating from the complex structure of blood microcirculation and the irregular vascular abnormalities often present in diseased regions. In addition, the process of accurately annotating LSCI image data has proven challenging, thus limiting the widespread use of supervised deep learning methods for vascular segmentation within LSCI imagery. To surmount these challenges, we present a sturdy weakly supervised learning approach, which automatically determines threshold combinations and processing sequences, bypassing the need for extensive manual annotation to establish the dataset's ground truth, and constructs a deep neural network, FURNet, using UNet++ and ResNeXt as its foundation. By virtue of its training, the model achieves a high degree of precision in vascular segmentation, identifying and representing multi-scene vascular features consistently on both constructed and unseen datasets, showcasing its broad applicability. Furthermore, we confirmed the viability of this approach on a tumor sample prior to and subsequent to embolization therapy. This work's innovative technique in LSCI vascular segmentation creates new possibilities for AI-enhanced disease diagnosis at the application level.

The high-demanding nature of paracentesis, a routine surgical procedure, could be significantly mitigated and its benefits amplified through the creation of semi-autonomous procedures. Efficiently segmenting the ascites from ultrasound images is essential for the facilitation of semi-autonomous paracentesis. The ascites, however, typically shows substantial variation in shape and texture among individual patients, and its dimensions/contour change dynamically during the paracentesis. The efficiency and accuracy of current ascites segmentation methods from its background are often mutually exclusive, resulting in either time-consuming procedures or inaccurate segmentations. A two-stage active contour method is presented in this work for the purpose of accurately and efficiently segmenting ascites. An automatic method, utilizing morphological thresholding, is developed to identify the initial ascites contour. Hepatocelluar carcinoma Following the identification of the initial outline, a novel sequential active contour algorithm is utilized to precisely separate the ascites from the background. In a comparative study with state-of-the-art active contour methods, the proposed methodology was assessed on a dataset of over one hundred real ultrasound images of ascites. The obtained results clearly showcase the superior accuracy and efficiency of our approach.

The work introduces a multichannel neurostimulator using a novel charge balancing technique, culminating in maximal integration. Safe neurostimulation requires precise charge balancing of stimulation waveforms to prevent the undesirable accumulation of charge at the electrode-tissue interface. DTDC (digital time-domain calibration) digitally adjusts the second phase of biphasic stimulation pulses, leveraging a one-time ADC characterization of every stimulator channel on the chip. By prioritizing time-domain corrections over precise stimulation current amplitude control, circuit matching constraints are eased, resulting in a smaller channel area. The presented theoretical analysis of DTDC provides expressions for the necessary temporal resolution and relaxed circuit matching requirements. Employing a 65 nm CMOS process, a 16-channel stimulator was fabricated to empirically validate the DTDC principle, achieving a remarkably small area footprint of 00141 mm² per channel. To maintain compatibility with high-impedance microelectrode arrays, a common feature of high-resolution neural prostheses, the 104 V compliance was achieved despite the device being built using standard CMOS technology. This stimulator, operating within a 65 nm low-voltage process, represents the first instance, to the authors' knowledge, of achieving an output swing exceeding 10 volts. Measurements taken after calibration show DC error reduced to below 96 nanoamperes for each channel. A channel's static power consumption amounts to 203 watts.

This research details a portable NMR relaxometry system, designed for on-site analysis of biological fluids like blood. An NMR-on-a-chip transceiver ASIC, a reference frequency generator with arbitrary phase adjustment, and a custom-designed, miniaturized NMR magnet (0.29 Tesla, 330 grams) form the foundation of the presented system. Within the NMR-ASIC chip, a low-IF receiver, a power amplifier, and a PLL-based frequency synthesizer are co-integrated, resulting in a chip area of 1100 [Formula see text] 900 m[Formula see text]. The generator, utilizing arbitrary reference frequencies, facilitates the use of both conventional CPMG and inversion sequences, as well as modified water-suppression strategies. Moreover, a function is incorporated to achieve an automatic frequency lock, thereby rectifying the impact of temperature on magnetic field drifts. Measurements performed on NMR phantoms and human blood samples for proof-of-concept purposes exhibited remarkable concentration sensitivity, yielding a value of v[Formula see text] = 22 mM/[Formula see text]. This system's high-quality performance strongly indicates its potential as a leading candidate for future NMR-based point-of-care detection of biomarkers, including blood glucose.

One of the most dependable countermeasures against adversarial attacks is adversarial training. Models trained with AT demonstrate a decrease in overall accuracy and limited capability to adapt to previously unencountered attacks. Recent publications illustrate improved generalization on adversarial samples by using unseen threat models, encompassing the on-manifold and neural perceptual threat model types. Conversely, the precise details of the manifold are needed for the first approach, whereas the second method relies on algorithmic adjustments. These considerations motivate a novel threat model, the Joint Space Threat Model (JSTM), which employs Normalizing Flow to uphold the precise manifold assumption. Leber’s Hereditary Optic Neuropathy Adversarial attacks and defenses, novel in nature, are developed by our team under JSTM. H-151 Our novel Robust Mixup strategy centers around maximizing the adversarial properties of the interpolated images, thus enhancing robustness and counteracting overfitting. Interpolated Joint Space Adversarial Training (IJSAT) has proven, through our experiments, to deliver superior results in standard accuracy, robustness, and generalization measures. IJSAT's flexibility facilitates its application as a data augmentation technique, improving standard accuracy while augmenting robustness in combination with other existing AT approaches. We evaluate the potency of our method across the CIFAR-10/100, OM-ImageNet, and CIFAR-10-C benchmark datasets.

Temporal action localization, weakly supervised, automates the identification and precise location of action occurrences in unedited videos, utilizing only video-level labels for guidance. This endeavor presents two pivotal hurdles: (1) precisely identifying action categories within unedited video footage (what is to be discovered); (2) meticulously pinpointing the precise temporal span of each action occurrence (where emphasis is required). The empirical identification of action categories requires extracting discriminative semantic information, and equally critical is the incorporation of robust temporal contextual information for complete action localization. Unfortunately, prevailing WSTAL methods typically do not explicitly and comprehensively represent the interconnected semantic and temporal contextual data for the two difficulties presented above. A Semantic and Temporal Contextual Correlation Learning Network (STCL-Net) is proposed, featuring semantic contextual learning (SCL) and temporal contextual correlation learning (TCL) components. This network models the semantic and temporal contextual correlations in both inter- and intra-video snippets to achieve precise action discovery and complete localization. A noteworthy aspect of the two proposed modules is their unified dynamic correlation-embedding design. On a variety of benchmarks, extensive experiments are carried out. The proposed methodology showcases performance equivalent to or exceeding the current best-performing models across various benchmarks, with a substantial 72% improvement in average mAP observed specifically on the THUMOS-14 data set.