Digital mammography is still the most common imaging tool for breast cancer screening. Although the benefits of using digital mammography for cancer screening outweigh the risks associated with the x-ray exposure, the radiation dose must be kept as low as possible while maintaining the diagnostic utility of the generated images, thus minimizing patient risks. Many studies investigated the feasibility of dose reduction by restoring low-dose images using deep neural networks. In these cases, choosing the appropriate training database and loss function is crucial and impacts the quality of the results. In this work, a modification of the ResNet architecture, with hierarchical skip connections, is proposed to restore low-dose digital mammography. We compared the restored images to the standard full-dose images. Moreover, we evaluated the performance of several loss functions for this task. For training purposes, we extracted 256,000 image patches from a dataset of 400 images of retrospective clinical mammography exams, where different dose levels were simulated to generate low and standard-dose pairs. To validate the network in a real scenario, a physical anthropomorphic breast phantom was used to acquire real low-dose and standard full-dose images in a commercially avaliable mammography system, which were then processed through our trained model. An analytical restoration model for low-dose digital mammography, previously presented, was used as a benchmark in this work. Objective assessment was performed through the signal-to-noise ratio (SNR) and mean normalized squared error (MNSE), decomposed into residual noise and bias. Results showed that the perceptual loss function (PL4) is able to achieve virtually the same noise levels of a full-dose acquisition, while resulting in smaller signal bias compared to other loss functions.
Inspired by diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons of our interest replaces the inner-product operation in the conventional neuron with a quadratic function. Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed. Theoretically, the superior expressivity of a quadratic network over either a conventional network or a conventional network via quadratic activation is not fully elucidated, which makes the use of quadratic networks not well grounded. Practically, although a quadratic network can be trained via generic backpropagation, it can be subject to a higher risk of collapse than the conventional counterpart. To address these issues, we first apply the spline theory and a measure from algebraic geometry to give two theorems that demonstrate better model expressivity of a quadratic network than the conventional counterpart with or without quadratic activation. Then, we propose an effective and efficient training strategy referred to as ReLinear to stabilize the training process of a quadratic network, thereby unleashing the full potential in its associated machine learning tasks. Comprehensive experiments on popular datasets are performed to support our findings and evaluate the performance of quadratic deep learning.
The treatment decisions for brain metastatic disease are driven by knowledge of the primary organ site cancer histology, often requiring invasive biopsy. This study aims to develop a novel deep learning approach for accurate and rapid non-invasive identification of brain metastatic tumor histology with conventional whole-brain MRI. The use of clinical whole-brain data and the end-to-end pipeline obviate external human intervention. This IRB-approved single-site retrospective study was comprised of patients (n=1,293) referred for MRI treatment-planning and gamma knife radiosurgery from July 2000 to May 2019. Contrast-enhanced T1-weighted contrast enhanced and T2-weighted-Fluid-Attenuated Inversion Recovery brain MRI exams (n=1,428) were minimally preprocessed (voxel resolution unification and signal-intensity rescaling/normalization), requiring only seconds per an MRI scan, and input into the proposed deep learning workflow for tumor segmentation, modality transfer, and primary site classification associated with brain metastatic disease in one of four classes (lung, melanoma, renal, and other). Ten-fold cross-validation generated the overall AUC of 0.941, lung class AUC of 0.899, melanoma class AUC of 0.882, renal class AUC of 0.870, and other class AUC of 0.885. It is convincingly established that whole-brain imaging features would be sufficiently discriminative to allow accurate diagnosis of the primary organ site of malignancy. Our end-to-end deep learning-based radiomic method has a great translational potential for classifying metastatic tumor types using whole-brain MRI images, without additional human intervention. Further refinement may offer invaluable tools to expedite primary organ site cancer identification for treatment of brain metastatic disease and improvement of patient outcomes and survival.
Contrastive learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negative samples) apart. As revealed in recent works, CL can benefit from hard negative samples (negative samples that are difficult to distinguish from the anchor). However, we observe minor improvement or even performance drop when we adopt existing hard negative mining techniques in Graph Contrastive Learning (GCL). We find that many hard negative samples similar to anchor point are false negative ones (samples from the same class as anchor point) in GCL, which is different from CL in computer vision and will lead to unsatisfactory performance of existing hard negative mining techniques in GCL. To eliminate this bias, we propose Debiased Graph Contrastive Learning (DGCL), a novel and effective method to estimate the probability whether each negative sample is true or not. With this probability, we devise two schemes (i.e., DGCL-weight and DGCL-mix) to boost the performance of GCL. Empirically, DGCL outperforms or matches previous unsupervised state-of-the-art results on several benchmarks and even exceeds the performance of supervised ones.
Adversarial attack transferability is a well-recognized phenomenon in deep learning. Prior work has partially explained transferability by recognizing common adversarial subspaces and correlations between decision boundaries, but we have found little explanation in the literature beyond this. In this paper, we propose that transferability between seemingly different models is due to a high linear correlation between features that different deep neural networks extract. In other words, two models trained on the same task that are seemingly distant in the parameter space likely extract features in the same fashion, just with trivial shifts and rotations between the latent spaces. Furthermore, we show how applying a feature correlation loss, which decorrelates the extracted features in a latent space, can drastically reduce the transferability of adversarial attacks between models, suggesting that the models complete tasks in semantically different ways. Finally, we propose a Dual Neck Autoencoder (DNA), which leverages this feature correlation loss to create two meaningfully different encodings of input information with reduced transferability.
A first stationary multi-source computed tomography (CT) system is prototyped for preclinical imaging to achieve real-time temporal resolution for dynamic cardiac imaging. This unique is featured by 29 source-detector pairs fixed on a circular track for each detector to collect x-ray signals only from the opposite x-ray source. The new system architecture potentially leads to a major improvement in temporal resolution. To demonstrate the feasibility of this Stationary Multi-source AI-based Real-time Tomography (SMART) system, we develop a novel reconstruction scheme integrating both sparsified image prior (SIP) and deep image prior (DIP), which is referred to as the SIP-DIP network. Then, the SIP-DIP network for cardiac imaging is evaluated on preclinical cardiac datasets of alive rats. The reconstructed image volumes demonstrate the feasibility of the SMART system and the SIP-DIP network and the merits over other reconstruction methods.
Prostate cancer biopsy benefits from accurate fusion of transrectal ultrasound (TRUS) and magnetic resonance (MR) images. In the past few years, convolutional neural networks (CNNs) have been proved powerful in extracting image features crucial for image registration. However, challenging applications and recent advances in computer vision suggest that CNNs are quite limited in its ability to understand spatial correspondence between features, a task in which the self-attention mechanism excels. This paper aims to develop a self-attention mechanism specifically for cross-modal image registration. Our proposed cross-modal attention block effectively maps each of the features in one volume to all features in the corresponding volume. Our experimental results demonstrate that a CNN network designed with the cross-modal attention block embedded outperforms an advanced CNN network 10 times of its size. We also incorporated visualization techniques to improve the interpretability of our network. The source code of our work is available at https://github.com/DIAL-RPI/Attention-Reg .
By the ALARA (As Low As Reasonably Achievable) principle, ultra-low-dose CT reconstruction is a holy grail to minimize cancer risks and genetic damages, especially for children. With the development of medical CT technologies, the iterative algorithms are widely used to reconstruct decent CT images from a low-dose scan. Recently, artificial intelligence (AI) techniques have shown a great promise in further reducing CT radiation dose to the next level. In this paper, we demonstrate that AI-powered CT reconstruction offers diagnostic image quality at an ultra-low-dose level comparable to that of radiography. Specifically, here we develop a Split Unrolled Grid-like Alternative Reconstruction (SUGAR) network, in which deep learning, physical modeling and image prior are integrated. The reconstruction results from clinical datasets show that excellent images can be reconstructed using SUGAR from 36 projections. This approach has a potential to change future healthcare.
Existing deep learning methods for diagnosis of gastric cancer commonly use convolutional neural networks (CNN). Recently, the Visual Transformer (VT) has attracted a major attention because of its performance and efficiency, but its applications are mostly in the field of computer vision. In this paper, a multi-scale visual transformer model, referred to as GasHis-Transformer, is proposed for gastric histopathology image classification (GHIC), which enables the automatic classification of microscopic gastric images into abnormal and normal cases. The GasHis-Transformer model consists of two key modules: a global information module (GIM) and a local information module (LIM) to extract pathological features effectively. In our experiments, a public hematoxylin and eosin (H&E) stained gastric histopathology dataset with 280 abnormal or normal images using the GasHis-Transformer model is applied to estimate precision, recall, F1-score, and accuracy on the testing set as 98.0%, 100.0%, 96.0% and 98.0% respectively. Furthermore, a critical study is conducted to evaluate the robustness of GasHis-Transformer according to add ten different noises including adversarial attack and traditional image noise. In addition, a clinically meaningful study is executed to test the gastric cancer identification of GasHis-Transformerwith 420 abnormal images and achieves 96.2% accuracy. Finally, a comparative study is performed to test the generalizability with both H&E and Immunohistochemical (IHC) stained images on a lymphoma image dataset, a breast cancer dataset and a cervical cancer dataset, producing comparable F1-scores (85.6%, 82.8% and 65.7%, respectively) and accuracy (83.9%, 89.4% and 65.7%, respectively) respectively. In conclusion, GasHis-Transformerdemonstrates a high classification performance and shows its significant potential in histopathology image analysis.