Medical Image Analysis Research Articles

AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3

ObjectiveThe incidence of osteosarcoma (OS) is low, but primary malignant bone tumors rank third among the causes of death in cancer patients under the age of 20. Currently, analysis of cellular structure and tumor morphology through microscopic images remains one of the main diagnostic methods for osteosarcoma. However, this completely manual approach is tedious, time-consuming, and difficult to diagnose accurately due to the similarities in certain characteristics of malignant and benign tumors. MethodsLeveraging the potential of artificial intelligence (AI) in assessing and classifying images, this study explored a modified CA-MobileNet V3 model that was embedded into innovative microscope products to enhance the microscope’s feature extraction capabilities and help reduce misclassification during diagnosis. ResultsThe intelligent recognition model method introduced in this paper has significant advantages in retrieval and classification of osteosarcoma cells and other cell types. Compared with models such as ShuffleNet V2, EfficientNet V2, Mobilenet V3 (without transfer learning), TL-MobileNet V3 (with transfer learning), etc., the model size is only 5.33 MB, is a lightweight model, and the accuracy of the improved model reached 98.69 %. In addition, the artificial intelligence microscope (AIM) with integrated design based on this model can also help improve diagnostic efficiency. ConclusionThe innovative method of the CA-MobileNet V3 automatic classification model based on deep learning provides an efficient and reliable solution for the pathological diagnosis of osteosarcoma. This study contributes to medical image analysis and provides doctors with an accurate and valuable tool for microscopic diagnosis. It also promotes the advancement of artificial intelligence in medical imaging technology.

Enhancing physician support in pancreatic cancer diagnosis: New M-F-RCNN artificial intelligence model using endoscopic ultrasound.

Background and study aims Endoscopic ultrasound (EUS) is vital for early pancreatic cancer diagnosis. Advances in artificial intelligence (AI), especially deep learning, have improved medical image analysis. We developed and validated the Modified Faster R-CNN (M-F-RCNN), an AI algorithm using EUS images to assist in diagnosing pancreatic cancer. Methods We collected EUS images from 155 patients across three endoscopy centers from July 2022 to July 2023. M-F-RCNN development involved enhancing feature information through data preprocessing and utilizing an improved Faster R-CNN model to identify cancerous regions. Its diagnostic capabilities were validated against an external set of 1,000 EUS images. In addition, five EUS doctors participated in a study comparing the M-F-RCNN model's performance with that of human experts, assessing diagnostic skill improvements with AI assistance. Results Internally, the M-F-RCNN model surpassed traditional algorithms with an average precision of 97.35%, accuracy of 96.49%, and recall rate of 5.44%. In external validation, its sensitivity, specificity, and accuracy were 91.7%, 91.5%, and 91.6%, respectively, outperforming non-expert physicians. The model also significantly enhanced the diagnostic skills of doctors. Conclusions: The M-F-RCNN model shows exceptional performance in diagnosing pancreatic cancer via EUS images, greatly improving diagnostic accuracy and efficiency, thus enhancing physician proficiency and reducing diagnostic errors.

Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges

Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting in potential misdiagnosis in clinical practice. Oppositely, recent years have also witnessed remarkable progress in defense against these tailored adversarial examples in deep medical diagnosis systems. In this exposition, we present a comprehensive survey on recent advances in adversarial attacks and defenses for medical image analysis with a systematic taxonomy in terms of the application scenario. We also provide a unified framework for different types of adversarial attack and defense methods in the context of medical image analysis. For a fair comparison, we establish a new benchmark for adversarially robust medical diagnosis models obtained by adversarial training under various scenarios. To the best of our knowledge, this is the first survey paper that provides a thorough evaluation of adversarially robust medical diagnosis models. By analyzing qualitative and quantitative results, we conclude this survey with a detailed discussion of current challenges for adversarial attack and defense in medical image analysis systems to shed light on future research directions. Code is available on GitHub.

Attention Score Enhancement Model Through Pairwise Image Comparison

This study proposes the Pairwise Attention Enhancement (PAE) model to address the limitations of the Vision Transformer (ViT). While the ViT effectively models global relationships between image patches, it encounters challenges in medical image analysis where fine-grained local features are crucial. Although the ViT excels at capturing global interactions within the entire image, it may potentially underperform due to its inadequate representation of local features such as color, texture, and edges. The proposed PAE model enhances local features by calculating cosine similarity between the attention maps of training and reference images and integrating attention maps in regions with high similarity. This approach complements the ViT’s global capture capability, allowing for a more accurate reflection of subtle visual differences. Experiments using Clock Drawing Test data demonstrated that the PAE model achieved a precision of 0.9383, recall of 0.8916, F1-Score of 0.9133, and accuracy of 92.69%, showing a 12% improvement over API-Net and a 1% improvement over the ViT. This study suggests that the PAE model can enhance performance in computer vision fields where local features are crucial by overcoming the limitations of the ViT.

Machine learning techniques for diagnosis of rare diseases from medical images

Introduction/Background: Rare diseases are life-threatening or chronically debilitating conditions that affect a small percentage of the population. Early and accurate diagnosis of rare diseases is challenging due to their complexity and limited understanding. Conventional diagnostic methods are often inadequate, time-consuming, and expensive. Machine learning (ML) has emerged as a promising technique for the analysis of medical images to support the diagnosis of various diseases including rare disorders. ML algorithms can learn complex patterns from large medical imaging datasets to aid clinicians in disease diagnosis, prognosis, and detection of complications. Materials and Methods: A structured search was conducted in electronic databases, including PubMed, Scopus, Web of Science, and Google Scholar to identify peer-reviewed articles published between 2013 to 2023 related to ML-based diagnosis of rare diseases from medical images. A total of 187 articles were identified after removing duplicates. The titles and abstracts of retrieved articles were screened to determine their relevance based on the research objective. Finally, 51 full-text articles were selected for the final review. The key data extracted from selected studies included diseases, imaging modalities, ML algorithms, performance metrics, datasets, and limitations. Results: Most studies evaluated deep learning-based ML techniques, with convolutional neural networks (CNN) being the most applied algorithm. CNNs were mainly used to classify rare diseases based on specific imaging features in X-rays, CT, and MRI scans. Diseases frequently investigated included cardiovascular, neurological, and rare genetic disorders. Publicly available datasets such as Deep Lesion, MSD, and ChestX-ray14 were commonly utilized. Most studies reported high classification accuracy ranging from 80-95% on test datasets. However, limited generalizability due to small private datasets and lack of external validation were limitations. Discussion: The results demonstrate the potential of deep learning for the image-based diagnosis of rare diseases. Features learned from large imaging data sets enabled CNNs to distinguish subtle abnormalities. Hybrid models combining CNNs with other techniques like recurrent neural networks further improved performance. Overall, ML showed promise as a decision support tool. However, more multi-center validation studies are needed using larger and diverse datasets before clinical adoption. Standardization of performance metrics and reporting is also required to establish reliability and generalizability. Conclusion: This comprehensive review provided insights into ongoing research applying ML to medical images for rare disease diagnosis. While initial results are encouraging, further work is still necessary before ML can be reliably used in clinical decision making. Larger collaborative efforts and open-source datasets are needed to advance the field. Standardization of ML frameworks can also promote reproducible research and comparison of different methodologies.

VLFATRollout: Fully transformer-based classifier for retinal OCT volumes

Background and Objective:Despite the promising capabilities of 3D transformer architectures in video analysis, their application to high-resolution 3D medical volumes encounters several challenges. One major limitation is the high number of 3D patches, which reduces the efficiency of the global self-attention mechanisms of transformers. Additionally, background information can distract vision transformers from focusing on crucial areas of the input image, thereby introducing noise into the final representation. Moreover, the variability in the number of slices per volume complicates the development of models capable of processing input volumes of any resolution while simple solutions like subsampling may risk losing essential diagnostic details. Methods:To address these challenges, we introduce an end-to-end transformer-based framework, variable length feature aggregator transformer rollout (VLFATRollout), to classify volumetric data. The proposed VLFATRollout enjoys several merits. First, the proposed VLFATRollout can effectively mine slice-level fore-background information with the help of transformer’s attention matrices. Second, randomization of volume-wise resolution (i.e. the number of slices) during training enhances the learning capacity of the learnable positional embedding (PE) assigned to each volume slice. This technique allows the PEs to generalize across neighboring slices, facilitating the handling of high-resolution volumes at the test time. Results:VLFATRollout was thoroughly tested on the retinal optical coherence tomography (OCT) volume classification task, demonstrating a notable average improvement of 5.47% in balanced accuracy over the leading convolutional models for a 5-class diagnostic task. These results emphasize the effectiveness of our framework in enhancing slice-level representation and its adaptability across different volume resolutions, paving the way for advanced transformer applications in medical image analysis. The code is available at https://github.com/marziehoghbaie/VLFATRollout/.

Kidney Disease Classification

Kidney diseases, such as tumors, cysts, and stones, are serious health conditions that affect millions globally. Medical imaging, particularly Computed-Tomography (CT) scans, plays an important role in diagnosing these conditions. Although, manual analysis of CT images by radiologist can be tiresome, fallible, and affected by human variability. This paper introduces a deep learning approach that employs Convolutional Neural Networks (CNN) for the automated classification of kidney CT scan images into four distinct categories : normal, cysts, tumors, and stones. The system is designed to boost diagnostic accuracy, reduce human error, and expedite clinical decision making. Through data preprocessing, CNN architecture design, training, and evaluation, the proposed model achieved a classification accuracy of 92%. This study highlights the significance of CNNs in medical image analysis anddtheir implicit for real- time deployment in clinical surroundings. Additionally, we compare our CNN-based approach with other advanced architectures like Vision Transformers, demonstrating CNNs' robustness and efficiency in this domain.

Temporomandibular joint CBCT image segmentation via multi-view ensemble learning network.

Accurate segmentation of the temporomandibular joint (TMJ) from cone beam CT (CBCT) images holds significant clinical value for diagnosing temporomandibular joint osteoarthrosis (TMJOA) and related conditions. Convolutional neural network-based medical image segmentation methods have achieved state-of-the-art performance in various segmentation tasks. However, 3D medical images segmentation requires substantial global context and rich spatial semantic information, demanding much more GPU memory and computational resources. To address these challenges in 3D medical image segmentation, we propose a novel network- the MVEL-Net (Multi-view Ensemble Learning Network) for TMJ CBCT image segmentation. By resampling images along three dimensions, we generate multiple weak learners with different spatial semantic information. A subsequent strong learning network effectively integrates the outputs from these weak learners to achieve more accurate segmentation results. We evaluated our network model using a clinical dataset comprising 88 subjects with TMJ CBCT images. The average Dice similarity coefficient (DSC) was 0.9817 ± 0.0049, the average surface distance was 0.0540 ± 0.0179mm, and the 95% Hausdorff distance was 0.1743 ± 0.0550mm. Our proposed MVEL-Net demonstrates excellent segmentation performance on TMJ from CBCT images, while using fewer GPU memory resources compared to other 3D networks. The effectiveness of this method in capturing spatial context could be leveraged for tasks like organ segmentation from volumetric scans. This may facilitate wider adoption of AI-based solutions for automated analysis of 3D medical images.

Evaluating and enhancing the robustness of vision transformers against adversarial attacks in medical imaging.

Deep neural networks (DNNs) have demonstrated exceptional performance in medical image analysis. However, recent studies have uncovered significant vulnerabilities in DNN models, particularly their susceptibility to adversarial attacks that manipulate these models into making inaccurate predictions. Vision Transformers (ViTs), despite their advanced capabilities in medical imaging tasks, have not been thoroughly evaluated for their robustness against such attacks in this domain. This study addresses this research gap by conducting an extensive analysis of various adversarial attacks on ViTs specifically within medical imaging contexts. We explore adversarial training as a potential defense mechanism and assess the resilience of ViT models against state-of-the-art adversarial attacks and defense strategies using publicly available benchmark medical image datasets. Our findings reveal that ViTs are vulnerable to adversarial attacks even with minimal perturbations, although adversarial training significantly enhances their robustness, achieving over 80% classification accuracy. Additionally, we perform a comparative analysis with state-of-the-art convolutional neural network models, highlighting the unique strengths and weaknesses of ViTs in handling adversarial threats. This research advances the understanding of ViTs robustness in medical imaging and provides insights into their practical deployment in real-world scenarios.

Improving Prostate Image Segmentation Based on Equilibrium Optimizer and Cross-Entropy

Over the past decade, the development of computer-aided detection tools for medical image analysis has seen significant advancements. However, tasks such as the automatic differentiation of tissues or regions in medical images remain challenging. Magnetic resonance imaging (MRI) has proven valuable for early diagnosis, particularly in conditions like prostate cancer, yet it often struggles to produce high-resolution images with clearly defined boundaries. In this article, we propose a novel segmentation approach based on minimum cross-entropy thresholding using the equilibrium optimizer (MCE-EO) to enhance the visual differentiation of tissues in prostate MRI scans. To validate our method, we conducted two experiments. The first evaluated the overall performance of MCE-EO using standard grayscale benchmark images, while the second focused on a set of transaxial-cut prostate MRI scans. MCE-EO’s performance was compared against six stochastic optimization techniques. Statistical analysis of the results demonstrates that MCE-EO offers superior performance for prostate MRI segmentation, providing a more effective tool for distinguishing between various tissue types.

CTARR: A fast and robust method for identifying anatomical regions on CT images via atlas registration

Medical image analysis tasks often focus on regions or structures located in a particular location within the patient’s body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based approaches, this causes an unnecessary increases the computational burden during inference and raises the chance of errors. In this paper, we introduce CTARR, a novel generic method for CT Anatomical Re- gion Recognition. The method serves as a pre-processing step for any deep learning-based CT image analysis pipeline by automatically identifying the pre-defined anatomical region that is relevant for the follow-up task and removing the rest. It can be used in (i) image segmentation to prevent false positives in anatomically implausible regions and speeding up the inference, (ii) image classification to produce image crops that are consistent in their anatomical context, and (iii) image registration by serving as a fast pre-registration step. Our proposed method is based on atlas registration and provides a fast and robust way to crop any anatomical region encoded as one or multiple bounding box(es) from any unlabeled CT scan of the brain, chest, abdomen and/or pelvis. We demonstrate the utility and robustness of the proposed method in the context of medical image segmentation by evaluating it on six datasets of public segmentation challenges. The foreground voxels in the regions of interest are preserved in the vast majority of cases and tasks (97.45-100%) while taking only fractions of a seconds to compute (0.1-0.21s) on a deep learning worksta- tion and greatly reducing the segmentation runtime (2.0-12.7x). Our code is available at <a href='https://github.com/ThomasBudd/ctarr'>https://github.com/ThomasBudd/ctarr</a>

Fairness in artificial intelligence‐driven multi‐organ image segmentation

AbstractFairness is an emerging consideration when assessing the segmentation performance of machine learning models across various demographic groups. During clinical decision‐making, an unfair segmentation model exhibits risks in that it can pose inappropriate diagnoses and unsuitable treatment plans for underrepresented demographic groups, resulting in severe consequences for patients and society. In medical artificial intelligence (AI), the fairness of multi‐organ segmentation is imperative to augment the integration of models into clinical practice. As the use of multi‐organ segmentation in medical image analysis expands, it is crucial to systematically examine fairness to ensure equitable segmentation performance across diverse patient populations and ensure health equity. However, comprehensive studies assessing the problem of fairness in multi‐organ segmentation remain lacking. This study aimed to provide an overview of the fairness problem in multi‐organ segmentation. We first define fairness and discuss the factors that lead to fairness problems such as individual fairness, group fairness, counterfactual fairness, and max–min fairness in multi‐organ segmentation, focusing mainly on datasets and models. We then present strategies to potentially improve fairness in multi‐organ segmentation. Additionally, we highlight the challenges and limitations of existing approaches and discuss future directions for improving the fairness of AI models for clinically oriented multi‐organ segmentation.

FedATA: Adaptive attention aggregation for federated self-supervised medical image segmentation

Pre-trained on large-scale datasets has profoundly promoted the development of deep learning models in medical image analysis. For medical image segmentation, collecting a large number of labeled volumetric medical images from multiple institutions is an enormous challenge due to privacy concerns. Self-supervised learning with mask image modeling (MIM) can learn general representation without annotations. Integrating MIM into FL enables collaborative learning of an efficient pre-trained model from unlabeled data, followed by fine-tuning with limited annotations. However, setting pixels as reconstruction targets in traditional MIM fails to facilitate robust representation learning due to the medical image's complexity and distinct characteristics. On the other hand, the generalization of the aggregated model in FL is also impaired under the heterogeneous data distributions among institutions. To address these issues, we proposed a novel self-supervised federated learning, which combines masked self-distillation with adaptive attention federated learning. Such incorporation enjoys two vital benefits. First, masked self-distillation sets high-quality latent representations of masked tokens as the target, improving the descriptive capability of the learned presentation rather than reconstructing low-level pixels. Second, adaptive attention aggregation with Personalized federate learning effectively captures specific-related representation from the aggregated model, thus facilitating local fine-tuning performance for target tasks. We conducted comprehensive experiments on two medical segmentation tasks using a large-scale dataset consisting of volumetric medical images from multiple institutions, demonstrating superior performance compared to existing federated self-supervised learning approaches.

Artificial Intelligence In Healthcare: A Review Of Deep Learning Models For Medical Image Analysis

Artificial Intelligence In Healthcare: A Review Of Deep Learning Models For Medical Image Analysis

Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection.

Background: Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. Methods: We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. Results: Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients' 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. Conclusions: Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients' lives.

Comprehensive segmentation of gray matter structures on T1-weighted brain MRI: A Comparative Study of CNN, CNN hybrid-transformer or -Mamba architectures.

Recent advances in deep learning have shown promising results in medical image analysis and segmentation. However, most brain MRI segmentation models are limited by the size of their datasets and/or the number of structures they can identify. This study evaluates the performance of six advanced deep learning models in segmenting 122 brain structures from T1-weighted MRI scans, aiming to identify the most effective model for clinical and research applications. 1,510 T1-weighted MRIs were used to compare six deep-learning models for the segmentation of 122 distinct gray matter structures: nnU-Net, SegResNet, SwinUNETR, UNETR, U-Mamba_BOT and U-Mamba_ Enc. Each model was rigorously tested for accuracy using the Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95). Additionally, the volume of each structure was calculated and compared between normal control (NC) and Alzheimer's Disease (AD) patients. U-Mamba_Bot achieved the highest performance with a median DSC of 0.9112 [IQR:0.8957, 0.9250]. nnU-Net achieved a median DSC of 0.9027 [IQR: 0.8847, 0.9205] and had the highest HD95 of 1.392[IQR: 1.174, 2.029]. The value of each HD95 (<3mm) indicates its superior capability in capturing detailed brain structures accurately. Following segmentation, volume calculations were performed, and the resultant volumes of normal controls and AD patients were compared. The volume changes observed in thirteen brain substructures were all consistent with those reported in existing literature, reinforcing the reliability of the segmentation outputs. This study underscores the efficacy of U-Mamba_Bot as a robust tool for detailed brain structure segmentation in T1-weighted MRI scans. The congruence of our volumetric analysis with the literature further validates the potential of advanced deep-learning models to enhance the understanding of neurodegenerative diseases such as AD. Future research should consider larger datasets to validate these findings further and explore the applicability of these models in other neurological conditions. AD = Alzheimer's Disease; ADNI = Alzheimer's Disease Neuroimaging Initiative; DSC = Dice Similarity Coefficient; HD95 = the 95th Percentile Hausdorff Distance; IQR = Interquartile Range; NC = Normal Control; SSMs = State-space Sequence Models.

A hybrid feature fusion deep learning framework for multi-source medical image analysis

Despite the widespread adoption of deep learning to enhance image classification, significant obstacles remain. First, multisource data with diverse sizes and formats is a great challenge for most current deep learning models. Second, lacking manual labeled data for model training limits the application of deep learning. Third, the widely used CNN-based methods shows their limitations in extracting global features and yield poor performance for image topology. To address these issues, we propose a Hybrid Feature Fusion Deep Learning (HFFDL) framework for image classification. This framework consists of an automated image segmentation module, a two-stream backbone module, and a classification module. The automatic image segmentation module utilizes the U-Net model and transfer learning to detect region of interest (ROI) in multisource images; the two-stream backbone module integrates the Swin Transformer architecture with the Inception CNN, with the aim of simultaneous extracting local and global features for efficient representation learning. We evaluate the performance of HFFDL framework with two publicly available image datasets: one for identifying COVID-19 through X-ray scans of the chest (30,386 images), and another for multiclass skin cancer screening using dermoscopy images (25,331 images). The HFFDL framework exhibited greater performance in comparison to many cutting-edge models, achieving the AUC score 0.9835 and 0.8789, respectively. Furthermore, a practical application study conducted in a hospital, identifying viable embryos using medical images, revealed the HFFDL framework outperformed embryologists.

Multi-domain improves classification in out-of-distribution and data-limited scenarios for medical image analysis

Current machine learning methods for medical image analysis primarily focus on developing models tailored for their specific tasks, utilizing data within their target domain. These specialized models tend to be data-hungry and often exhibit limitations in generalizing to out-of-distribution samples. In this work, we show that employing models that incorporate multiple domains instead of specialized ones significantly alleviates the limitations observed in specialized models. We refer to this approach as multi-domain model and compare its performance to that of specialized models. For this, we introduce the incorporation of diverse medical image domains, including different imaging modalities like X-ray, MRI, CT, and ultrasound images, as well as various viewpoints such as axial, coronal, and sagittal views. Our findings underscore the superior generalization capabilities of multi-domain models, particularly in scenarios characterized by limited data availability and out-of-distribution, frequently encountered in healthcare applications. The integration of diverse data allows multi-domain models to utilize information across domains, enhancing the overall outcomes substantially. To illustrate, for organ recognition, multi-domain model can enhance accuracy by up to 8% compared to conventional specialized models.

Core-Periphery Multi-Modality Feature Alignment for Zero-Shot Medical Image Analysis.

Multi-modality learning, exemplified by the language-image pair pre-trained CLIP model, has demonstrated remarkable performance in enhancing zero-shot capabilities and has gained significant attention recently. However, simply applying language-image pre-trained CLIP to medical image analysis encounters substantial domain shifts, resulting in severe performance degradation due to inherent disparities between natural (non-medical) and medical image characteristics. To address this challenge and uphold or even enhance CLIP's zero-shot capability in medical image analysis, we develop a novel approach, Core-Periphery feature alignment for CLIP (CP-CLIP), to model medical images and corresponding clinical text jointly. To achieve this, we design an auxiliary neural network whose structure is organized by the core-periphery (CP) principle. This auxiliary CP network not only aligns medical image and text features into a unified latent space more efficiently but also ensures alignment driven by principles of brain network organization. In this way, our approach effectively mitigates and further enhances CLIP's zero-shot performance in medical image analysis. More importantly, the proposed CP-CLIP exhibits excellent explanatory capability, enabling the automatic identification of critical disease-related regions in clinical analysis. Extensive experiments and evaluation across five public datasets covering different diseases underscore the superiority of our CP-CLIP in zero-shot medical image prediction and critical features detection, showing its promising utility in multimodal feature alignment in current medical applications.

Diffusion probabilistic priors for zero-shot low-dose CT image denoising.

Denoising low-dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning-based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low-dose and normal-dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning-based methods often require training with a large number of low-dose CT images or rely on specially designed data acquisition processes to obtain training data. To address these limitations, we propose a novel unsupervised method that only utilizes normal-dose CT images during training, enabling zero-shot denoising of low-dose CT images. Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high-quality normal-dose CT images from low-resolution to high-resolution. The cascaded architecture makes the training of high-resolution diffusion models more feasible. Subsequently, we introduce low-dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low-dose CT images. We test our method on low-dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods. Our method achieves PSNR of 45.02 and 35.35dB on the abdomen CT dataset and the chest CT dataset, respectively, surpassing the best unsupervised algorithm Noise2Sim in the comparative methods by 0.39 and 0.85dB, respectively. We propose a novel low-dose CT image denoising method based on diffusion model. Our proposed method only requires normal-dose CT images as training data, greatly alleviating the data scarcity issue faced by most deep learning-based methods. At the same time, as an unsupervised algorithm, our method achieves very good qualitative and quantitative results. The Codes are available in https://github.com/DeepXuan/Dn-Dp.