Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading.

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting.

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

Deep learning-based pathology signature could reveal lymph node status and act as a novel prognostic marker across multiple cancer types.

BACKGROUND: Identifying lymph node metastasis (LNM) relies mainly on indirect radiology. Current studies omitted the quantified associations with traits beyond cancer types, failing to provide generalisation performance across various tumour types. METHODS: 4400 whole slide images across 11 cancer types were collected for training, cross-verification, and external validation of the pan-cancer lymph node metastasis (PC-LNM) model. We proposed an attention-based weakly supervised neural network based on self-supervised cancer-invariant features for the prediction task. RESULTS: PC-LNM achieved a test area under the curve (AUC) of 0.732 (95% confidence interval: 0.717-0.746, P < 0.0001) in fivefold cross-validation of multiple cancer types, which also demonstrated good generalisation in the external validation cohort with AUC of 0.699 (95% confidence interval: 0.658-0.737, P < 0.0001). The interpretability results derived from PC-LNM revealed that the regions with the highest attention scores identified by the model generally correspond to tumours with poorly differentiated morphologies. PC-LNM achieved superior performance over previously reported methods and could also act as an independent prognostic factor for patients across multiple tumour types. DISCUSSION: We presented an automated pan-cancer model for predicting the LNM status from primary tumour histology, which could act as a novel prognostic marker across multiple cancer types.

The devil is in the details: a small-lesion sensitive weakly supervised learning framework for prostate cancer detection and grading.

Prostate cancer (PCa) is a significant health concern in aging males, and the diagnosis depends primarily on histopathological assessments to determine tumor size and Gleason score. This process is highly time-consuming, subjective, and relies on the extensive experience of the pathologists. Deep learning based artificial intelligence shows an ability to match pathologists on many prostate cancer diagnostic scenarios. However, it is easy to make mistakes on some hard cases with small tumor areas considering the extensively high-resolution of whole slide images (WSIs). The absence of fine-grained and large-scale annotations of such small tumor lesions makes this problem more challenging. Existing methods usually perform uniform cropping of the foreground of WSI and then use convolutional neural networks as the backbone network to predict the classification results. However, cropping can damage the structure of tiny tumors, which affects classification accuracy. To solve this problem, we propose an Intensive-Sampling Multiple Instance Learning Framework (ISMIL), which focuses on tumor regions and improves the recognition of small tumor regions by intensively sampling the crucial regions. Experiments of prostate cancer detection show that our method achieves an area under the receiver operating characteristic curve (AUC) of 0.987 on the PANDA sets, which improves recall by at least 33% with higher specificity over the current primary methods for hard cases. The ISMIL also demonstrates comparable abilities to human experts on the prostate cancer grading task. Moreover, ISMIL has shown good robustness in independent cohorts, which makes it a potential tool to improve the diagnostic efficiency of pathologists.

MMV-Net: A Multiple Measurement Vector Network for Multifrequency Electrical Impedance Tomography.

Multifrequency electrical impedance tomography (mfEIT) is an emerging biomedical imaging modality to reveal frequency-dependent conductivity distributions in biomedical applications. Conventional model-based image reconstruction methods suffer from low spatial resolution, unconstrained frequency correlation, and high computational cost. Deep learning has been extensively applied in solving the EIT inverse problem in biomedical and industrial process imaging. However, most existing learning-based approaches deal with the single-frequency setup, which is inefficient and ineffective when extended to the multifrequency setup. This article presents a multiple measurement vector (MMV) model-based learning algorithm named MMV-Net to solve the mfEIT image reconstruction problem. MMV-Net considers the correlations between mfEIT images and unfolds the update steps of the Alternating Direction Method of Multipliers for the MMV problem (MMV-ADMM). The nonlinear shrinkage operator associated with the weighted l2,1 regularization term of MMV-ADMM is generalized in MMV-Net with a cascade of a Spatial Self-Attention module and a Convolutional Long Short-Term Memory (ConvLSTM) module to better capture intrafrequency and interfrequency dependencies. The proposed MMV-Net was validated on our Edinburgh mfEIT Dataset and a series of comprehensive experiments. The results show superior image quality, convergence performance, noise robustness, and computational efficiency against the conventional MMV-ADMM and the state-of-the-art deep learning methods.

Automatic diagnosis and grading of Prostate Cancer with weakly supervised learning on whole slide images.

BACKGROUND: The workflow of prostate cancer diagnosis and grading is cumbersome and the results suffer from substantial inter-observer variability. Recent trials have shown potential in using machine learning to develop automated systems to address this challenge. Most automated deep learning systems for prostate cancer Gleason grading focused on supervised learning requiring demanding fine-grained pixel-level annotations. METHODS: A weakly-supervised deep learning model with slide-level labels is presented in this study for the diagnosis and grading of prostate cancer with whole slide image (WSI). WSIs are first cropped into small patches and then processed with a deep learning model to extract patch-level features. A graph convolution network (GCN) is used to aggregate the features for classifications. Throughout the training process, the noisy labels are progressively filtered out to reduce inter-observer variations in clinical reports. Finally, multi-center independent test cohorts with 6,174 slides are collected to evaluate the prostate cancer diagnosis and grading performance of our model. RESULTS: The cancer diagnosis (2-level classification) results on two external test sets (n= 4,675, n= 844) show an area under the receiver operating characteristic curve (AUC) of 0.985 and 0.986. The Gleason grading (6-level classification) results reach 0.931 quadratic weighted kappa on the internal test set (n= 531). It generalizes well on the external test dataset (n= 844) with 0.801 quadratic weighted kappa with the reference standard set independently. The model enables pathological meaningful interpretability by visualizing the most attended lesions which are highly consistent with expert annotations. CONCLUSION: The proposed model incorporates a graph network in weakly supervised learning with only slide-level reports. A robust learning strategy is also employed to correct the label noise. It is highly accurate (>0.985 AUC for diagnosis) and also interpretable with intuitive heatmap visualization. It can be unified with a digital pathology pipeline to deliver prostate cancer metrics for a pathology report.

Genome-scale signatures of adaptive gene expression changes in an invasive seaweed Gracilaria vermiculophylla.

Invasive species can successfully and rapidly colonize new niches and expand ranges via founder effects and enhanced tolerance towards environmental stresses. However, the underpinning molecular mechanisms (i.e., gene expression changes) facilitating rapid adaptation to harsh environments are still poorly understood. The red seaweed Gracilaria vermiculophylla, which is native to the northwest Pacific but invaded North American and European coastal habitats over the last 100 years, provides an excellent model to examine whether enhanced tolerance at the level of gene expression contributed to its invasion success. We collected G. vermiculophylla from its native range in Japan and from two non-native regions along the Delmarva Peninsula (Eastern United States) and in Germany. Thalli were reared in a common garden for 4 months at which time we performed comparative transcriptome (mRNA) and microRNA (miRNA) sequencing. MRNA-expression profiling identified 59 genes that were differently expressed between native and non-native thalli. Of these genes, most were involved in metabolic pathways, including photosynthesis, abiotic stress, and biosynthesis of products and hormones in all four non-native sites. MiRNA-based target-gene correlation analysis in native/non-native pairs revealed that some target genes are positively or negatively regulated via epigenetic mechanisms. Importantly, these genes are mostly associated with metabolism and defence capability (e.g., metal transporter Nramp5, senescence-associated protein, cell wall-associated hydrolase, ycf68 protein and cytochrome P450-like TBP). Thus, our gene expression results indicate that resource reallocation to metabolic processes is most likely a predominant mechanism contributing to the range-wide persistence and adaptation of G. vermiculophylla in the invaded range. This study, therefore, provides molecular insight into the speed and nature of invasion-mediated rapid adaption.

Recent Advances in Design Strategies of Tough Hydrogels.

Hydrogels are a fascinating class of materials popular in numerous fields, including tissue engineering, drug delivery, soft robotics, and sensors, thanks to their 3D network porous structure containing a significant amount of water. However, traditional hydrogels exhibit poor mechanical strength, limiting their practical applications. Thus, many researchers have focused on the development of mechanically enhanced hydrogels. This review describes the design considerations for constructing tough hydrogels and some of the latest strategies in recent years. These tough hydrogels have an up-and-coming prospect and bring great hope to the fields of biomedicine and others. Nonetheless, it is still no small challenge to realize hydrogel materials that are tough, multifunctional, intelligent, and with zero defects.

A novel hydrogel based on Bletilla striata polysaccharide for rapid hemostasis: Synthesis, characterization and evaluation.

The purpose of this study is to develop a new polysaccharide-based hydrogel. The Box-Behnken design was used to optimize the optimal synthesis conditions of the hydrogel, with the swelling parameters as indicators. The findings of rheologic tests confirm that free radical polymerization and the introduction of linear polymers improved the mechanical strength of the hydrogel. Combined with the characterization results, the gel mechanism of BSP-g-PAA/PVA DN hydrogel was proposed. The intermolecular association and entanglement increase, which effectively dissipates energy, thereby enhancing the mechanical properties of the hydrogel. In vitro blood compatibility experiments show that DN hydrogel has a low hemolysis rate and a good coagulation effect. The material is non-cytotoxic to L929 cells. The hepatic haemorrhage and mouse-tail amputation models of rats and mice were used to further evaluate the in vivo wound sealing and hemostatic properties of the hydrogel. The blood loss and hemostatic time were significantly lower than those of the control group, indicating that the hydrogel has excellent hemostatic effects. Therefore, the obtained BSP-g-PAA/PVA DN network hydrogel has good comprehensive properties and is expected to be used as a hemostatic material or a precursor of a drug carrier and a tissue engineering scaffold.

FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging.

Inverse problems are essential to imaging applications. In this letter, we propose a model-based deep learning network, named FISTA-Net, by combining the merits of interpretability and generality of the model-based Fast Iterative Shrinkage/Thresholding Algorithm (FISTA) and strong regularization and tuning-free advantages of the data-driven neural network. By unfolding the FISTA into a deep network, the architecture of FISTA-Net consists of multiple gradient descent, proximal mapping, and momentum modules in cascade. Different from FISTA, the gradient matrix in FISTA-Net can be updated during iteration and a proximal operator network is developed for nonlinear thresholding which can be learned through end-to-end training. Key parameters of FISTA-Net including the gradient step size, thresholding value and momentum scalar are tuning-free and learned from training data rather than hand-crafted. We further impose positive and monotonous constraints on these parameters to ensure they converge properly. The experimental results, evaluated both visually and quantitatively, show that the FISTA-Net can optimize parameters for different imaging tasks, i.e. Electromagnetic Tomography (EMT) and X-ray Computational Tomography (X-ray CT). It outperforms the state-of-the-art model-based and deep learning methods and exhibits good generalization ability over other competitive learning-based approaches under different noise levels.

Multi-Frequency Electromagnetic Tomography for Acute Stroke Detection Using Frequency-Constrained Sparse Bayesian Learning.

Imaging the bio-impedance distribution of the brain can provide initial diagnosis of acute stroke. This paper presents a compact and non-radiative tomographic modality, i.e. multi-frequency Electromagnetic Tomography (mfEMT), for the initial diagnosis of acute stroke. The mfEMT system consists of 12 channels of gradiometer coils with adjustable sensitivity and excitation frequency. To solve the image reconstruction problem of mfEMT, we propose an enhanced Frequency-Constrained Sparse Bayesian Learning (FC-SBL) to simultaneously reconstruct the conductivity distribution at all frequencies. Based on the Multiple Measurement Vector (MMV) model in the Sparse Bayesian Learning (SBL) framework, FC-SBL can recover the underlying distribution pattern of conductivity among multiple images by exploiting the frequency constraint information. A realistic 3D head model was established to simulate stroke detection scenarios, showing the capability of mfEMT to penetrate the highly resistive skull and improved image quality with FC-SBL. Both simulations and experiments showed that the proposed FC-SBL method is robust to noisy data for image reconstruction problems of mfEMT compared to the single measurement vector model, which is promising to detect acute strokes in the brain region with enhanced spatial resolution and in a baseline-free manner.

Electronics of a Wearable ECG With Level Crossing Sampling and Human Body Communication.

In this paper, the human body communication (HBC) and level crossing sampling (LCS) are combined to design electronics for a wearable electrocardiograph (ECG). The ECG signals acquired by capacitively coupled electrodes are sampled with LCS in place of conventional synchronous sampling. In order to transmit signals through HBC at low frequencies (100 kHz, 1 MHz), an electric field sensor with high input impedance is adopted as the front end of the HBC receiver. The HBC channel gain is enhanced by more than 30 dB with the electric field sensor. An LCS structure based on the send-on-delta concept is implemented with discrete components to convert the ECG signals into binary impulses. The converted impulses are modulated by an on-off keying modulator and then transmitted via the human body to the receiver. A prototype ECG waist belt is developed with commercially available components and experimentally evaluated. The results indicate that the acquired ECG waveforms exhibit good agreement with regular Ag/AgCl ECG methods. The heartbeat detection using a technique based on the Kadane's algorithm and the power consumption performance of the proposed system are also discussed.

Capturing Electrocardiogram Signals from Chairs by Multiple Capacitively Coupled Unipolar Electrodes.

A prototype of an electrocardiogram (ECG) signal acquisition system with multiple unipolar capacitively coupled electrodes is designed and experimentally tested. Capacitively coupled electrodes made of a standard printed circuit board (PCB) are used as the sensing electrodes. Different from the conventional measurement schematics, where one single lead ECG signal is acquired from a pair of sensing electrodes, the sensing electrodes in our approaches operate in a unipolar mode, i.e., the biopotential signals picked up by each sensing electrodes are amplified and sampled separately. Four unipolar electrodes are mounted on the backrest of a regular chair and therefore four channel of signals containing ECG information are sampled and processed. It is found that the qualities of ECG signal contained in the four channel are different from each other. In order to pick up the ECG signal, an index for quality evaluation, as well as for aggregation of multiple signals, is proposed based on phase space reconstruction. Experimental tests are carried out while subjects sitting on the chair and clothed. The results indicate that the ECG signals can be reliably obtained in such a unipolar way.