Lung CT Images Research Articles

Mitigating adversarial threats in deep CT image diagnosis models via a dual-stage inference-time defense

Artificial intelligence (AI), particularly deep learning (DL) and machine learning (ML) have revolutionized disease diagnosis using complex medical images such as X-rays and CT scans, significantly improving accuracy in identifying various medical conditions. However, concerns arise regarding the trustworthiness of these models due to their vulnerability to adversarial attacks, potentially leading to inaccurate predictions. In response, we propose an innovative pipeline defensive approach that integrates denoising techniques like Total Variation Minimization (TVM) and Non-local (NL) means, followed by a fuzzy logic-based image transformer called Fuzzy Image Transformations (FIT). Deployed during the inferencing phase as a preprocessing module, this strategy aims to fortify DL medical diagnosis models, addressing adversarial vulnerabilities and ensuring their reliability in critical healthcare applications. Our focus is narrowed down to COVID-19 diagnosis, where we initially developed a model for accurately classifying lung CT images, covering both normal and COVID-19 pneumonia cases. Our experimental procedures, employing the Stratified K-Fold cross-validation method with K=5, systematically evaluate the model’s susceptibility to benchmark adversarial attacks such as the Fast Gradient Sign Method (FGSM), revealing a significant drop in aggregate average metrics across all folds under adversarial conditions. Specifically, precision (P), recall (R), accuracy (A), and F1-score (F) metrics decrease from 95.86 %, 96.16 %, 95.85 %, and 96.00–12.54 %, 13.13 %, 12.63 %, and 12.83 %, respectively. Notably, our proposed pipeline defense approach demonstrates substantial efficacy in enhancing diagnostic models, with average P, R, A, and F metrics improving impressively to 92.65 %, 92.39 %, 92.65 %, and 92.51 %, respectively, when applied to the same adversarial images. These promising results underscore the potential of our proposed pipeline defense techniques to enhance the resilience and reliability of AI-based diagnostic systems.

Longitudinal changes in the volume of residual lung lobes after lobectomy for lung cancer: a retrospective cohort study.

It is unclear how the residual lobe volume changes over time after lobectomy. This study aims to clarify the temporal patterns of volume changes in each remaining lung lobe post-lobectomy. A retrospective review was conducted on patients who underwent lobectomy for lung cancer at Yueyang Central Hospital from January to December 2021. Lung CT images were reconstructed in three dimensions to calculate the volumes of each lung lobe preoperatively and at 1, 6, and 12months postoperatively. A total of 182 patients were included. Postoperatively, the median total lung volume change rates relative to preoperative values were -20.1%, -9.3%, and -5.9% at 1, 6, and 12months, respectively. Except for the right middle lobe in patients who underwent right upper lobectomy, the volumes of individual lung lobes exceeded preoperative values. The volume growth of the lung on the side of the resection was significantly more than that of the lung on the opposite side. For left lobectomy patients, the right lower lobe's volume change rate exceeded that of the right upper and middle lobes. Among right lobectomy patients, the left lower lobe and the relatively inferior lobe of right lung had higher volume change rates than the superior one. Right middle lobe change rate was more in patients with right lower lobectomy than right upper lobectomy. Six months postoperatively, FEV1% and right middle lobectomy were positively correlated with the overall volume change rate. One year postoperatively, only age was negatively correlated with the overall volume change rate. 75 patients had pulmonary function tests. Postoperative FEV1 change linearly correlated with 1-year lung volume change rate, but not with theoretical total lung volume change rate or segmental method calculated FEV1 change. Time-dependent compensatory volume changes occur in remaining lung lobe post-lobectomy, with stronger compensation observed in the relatively inferior lobe compared to the superior one(s). Preoperative lung function and age may affect compensation level.

Unsupervised lung CT image registration via stochastic decomposition of deformation fields

We address the problem of lung CT image registration, which underpins various diagnoses and treatments for lung diseases. The main crux of the problem is the large deformation that the lungs undergo during respiration. This physiological process imposes several challenges from a learning point of view. In this paper, we propose a novel training scheme, called stochastic decomposition, which enables deep networks to effectively learn such a difficult deformation field during lung CT image registration. The key idea is to stochastically decompose the deformation field, and supervise the registration by synthetic data that have the corresponding appearance discrepancy. The stochastic decomposition allows for revealing all possible decompositions of the deformation field. At the learning level, these decompositions can be seen as a prior to reduce the ill-posedness of the registration yielding to boost the performance. We demonstrate the effectiveness of our framework on Lung CT data. We show, through extensive numerical and visual results, that our technique outperforms existing methods.

Lung Cancer Classification using Optimized Attention-based Convolutional Neural Network with DenseNet-201 Transfer Learning Model on CT image

In this paper, the Lung Cancer Classification using Convolutional Neural Network with DenseNet-201 Transfer Learning model optimized through Namib Beetle Optimization Algorithm on CT image (AtCNN-DenseNet-201 TL-NBOA-CT) is proposed. The input data are gathered from the CT Lung image. In pre-processing section, it removes the noise and enhances input images by Modified Sage-Husa Kalman Filtering (MSHKF).The pre-processed image is given into feature extraction phase. Then, six statistical features including mean, variance, entropy, energy, Average Amplitude, kurtosis are extracted based on Improved Empirical Wavelet Transforms (IEWT). Then, the extracted features are given to the Attention-based Convolutional Neural Network with DenseNet-201Transfer Learning (AtCNN-DenseNet-201 TL) to classify the Cancer and Non-Cancer of the CT image, where batch normalization layer of At CNN eliminated and added by DenseNet-201 layer. Namib Beetle Optimization Algorithm (NBOA) proposed in this work to enhance the AtCNN-DenseNet-201 classifier, which precisely classifies the lung cancer. The proposed AtCNN-DenseNet-201 TL-NBOA-CT method is implemented and the effectiveness is assessed with some performance measures. The proposed AtCNN-DenseNet-201 TL-NBOA-CT method attains 18.30 %, 21.37 % and 23.07 % greater precision, 24.84 %, 16.32 % and 31.36 % greater accuracy and 14.32 %, 21.97 % and 23.38 % greater F1-Score compared with existing techniques like detection and categorization of lung cancer CT pictures utilizing improved deep belief network along Gabor filters (CLC-CT-EDBN), presented categorization of lung cancer CT pictures utilizing a three dimensional deep CNN with multi-layer filter (CLC-CT-3D-DCNN), and novel hybrid deep learning technique for early identification of lung cancer utilizing neural networks (CLC-CT-3D-CNN) respectively.

Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning.

The assessment of deformable registration uncertainty is an important task for the safety and reliability of registration methods in clinical applications. However, it is typically done by a manual and time-consuming procedure. We propose a novel automatic method to predict registration uncertainty based on multi-category features and supervised learning. Three types of features, including deformation field statistical features, deformation field physiologically realistic features, and image similarity features, are introduced and calculated to train the random forest regressor for local registration uncertain prediction. Deformation field statistical features represent the numerical stability of registration optimization, which are correlated to the uncertainty of deformation fields; deformation field physiologically realistic features represent the biomechanical properties of organ motions, which mathematically reflect the physiological reality of deformation; image similarity features reflect the similarity between the warped image and fixed image. The multi-category features comprehensively reflect the registration uncertainty. The strategy of spatial adaptive random perturbations is also introduced to accurately simulate spatial distribution of registration uncertainty, which makes deformation field statistical features more discriminative to the uncertainty of deformation fields. Experiments were conducted on three publicly available thoracic CT image datasets. Seventeen randomly selected image pairs are used to train the random forest model, and 9 image pairs are used to evaluate the prediction model. The quantitative experiments on lung CT images show that the proposed method outperforms the baseline method for uncertain prediction of classical iterative optimization-based registration and deep learning-based registration with different registration qualities. The proposed method achieves good performance for registration uncertain prediction, which has great potential in improving the accuracy of registration uncertain prediction.

COVID-19 Diagnosis by Extracting New Features from Lung CT Images Using Fractional Fourier Transform

COVID-19 is a lung disease caused by a coronavirus family virus. Due to its extraordinary prevalence and associated death rates, it has spread quickly to every country in the world. Thus, achieving peaks and outlines and curing different types of relapses is extremely important. Given the worldwide prevalence of coronavirus and the participation of physicians in all countries, information has been gathered regarding the properties of the virus, its diverse types, and the means of analyzing it. Numerous approaches have been used to identify this evolving virus. It is generally considered the most accurate and acceptable method of examining the patient’s lungs and chest through a CT scan. As part of the feature extraction process, a method known as fractional Fourier transform (FrFT) has been applied as one of the time-frequency domain transformations. The proposed method was applied to a database consisting of 2481 CT images. Following the transformation of all images into equal sizes and the removal of non-lung areas, multiple combination windows are used to reduce the number of features extracted from the images. In this paper, the results obtained for KNN and SVM classification have been obtained with accuracy values of 99.84% and 99.90%, respectively.

Development and Validation of an Algorithm Model for Predicting Heat Sink Effects during Pulmonary Thermal Ablation

The aim of this study was to develop an algorithm model to predict the heat sink effect during thermal ablation of lung tumors and to assist doctors in the formulation and adjustment of surgical protocols. The heat sink effect is an important factor affecting the therapeutic effect of tumor thermal ablation. At present, there is no algorithm model to predict the intraoperative heat sink effect automatically, which needs to be measured manually, which lacks accuracy and consumes time. To construct a segmentation model based on a convolutional neural network that can automatically identify and segment pulmonary nodules and vascular structure and measure the distance between the nodule and vascular. First, the classical Faster RCNN model was used as the nodule detection network. After obtaining the bounding box of pulmonary nodules, the VSPP-NET model was used to segment nodules in the bounding box. The distance from the nodule to the vasculature was measured after the surrounding vasculature was segmented by the VSPP-NET model. The lung CT images of 392 patients with pulmonary nodules were used as the training data for the algorithm. 68 cases were used as algorithm validation data, 29 as nodule algorithm test data, and 80 as vascular algorithm test data. We compared the heat sink effect of 29 cases of data with the results of the algorithm model and expert segmentation and compared the difference between the two results. In pulmonary CT image vasculature segmentation, the recall and precision of the algorithm model reached >0.88 and >0.78, respectively. The average time for automatic segmentation of each image model is 29 seconds, and the average time for manual segmentation is 158 seconds. The output image of the model shows that the results of nodule segmentation and nodule distance measurement are satisfactory. In terms of heat sink effect prediction, the positive rate of the algorithm group was 28.3%, and that of the expert group was 32.1%, with no significant difference between the two groups (p=0.687). The algorithm model developed in this study shows good performance in predicting the heat sink effect during pulmonary thermal ablation. It can improve the speed and accuracy of nodule and vessel segmentation, save ablation planning time, reduce the interference of human factors, and provide more reference information for surgeons to make ablation plans to improve the ablation effect.

Distributed U-net model-based image segmentation for lung cancer detection

Until now, in the wake of the COVID-19 pandemic in 2019, lung diseases, especially diseases such as lung cancer and Chronic Obstructive Pulmonary Disease (COPD), have become an urgent global health issue. In order to mitigate the goal problem, early detection and accurate diagnosis of these conditions are critical for effective treatment and improved patient outcomes. To further research and reduce the error rate of hospital diagnoses, this comprehensive study explored the potential of Computer-Aided Design (CAD) systems, especially utilizing advanced deep learning models such as U-Net. And compared with the literature content of other authors, this study explores the capabilities of U-Net in detail and enhances the ability to simulate CAD systems through the VGG16 algorithm. An extensive dataset consisting of lung CT images and corresponding segmentation masks, curated collaboratively by multiple academic institutions, serves as the basis for empirical validation. In this paper, the efficiency of U-Net model is evaluated rigorously and precisely under multiple hardware configurations, such as single CPU, single GPU, distributed GPU and federated learning, and the effectiveness and development of the method in the segmentation task of lung disease are demonstrated. Empirical results clearly affirm the robust performance of the U-Net model, most effectively utilizing four GPUs for distributed learning, and these results highlight the potential of U-Net-based CAD systems for accurate and timely lung disease detection and diagnosis huge potential.

MSA-UNet: A Multiscale Lightweight U-Net Lung CT Image Segmentation Algorithm Under Attention Mechanism

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy.

Enhancing medical image segmentation with a multi-transformer U-Net.

Various segmentation networks based on Swin Transformer have shown promise in medical segmentation tasks. Nonetheless, challenges such as lower accuracy and slower training convergence have persisted. To tackle these issues, we introduce a novel approach that combines the Swin Transformer and Deformable Transformer to enhance overall model performance. We leverage the Swin Transformer's window attention mechanism to capture local feature information and employ the Deformable Transformer to adjust sampling positions dynamically, accelerating model convergence and aligning it more closely with object shapes and sizes. By amalgamating both Transformer modules and incorporating additional skip connections to minimize information loss, our proposed model excels at rapidly and accurately segmenting CT or X-ray lung images. Experimental results demonstrate the remarkable, showcasing the significant prowess of our model. It surpasses the performance of the standalone Swin Transformer's Swin Unet and converges more rapidly under identical conditions, yielding accuracy improvements of 0.7% (resulting in 88.18%) and 2.7% (resulting in 98.01%) on the COVID-19 CT scan lesion segmentation dataset and Chest X-ray Masks and Labels dataset, respectively. This advancement has the potential to aid medical practitioners in early diagnosis and treatment decision-making.

An efficient combined intelligent system for segmentation and classification of lung cancer computed tomography images

Background and Objective One of the illnesses with most significant mortality and morbidity rates worldwide is lung cancer. From CT images, automatic lung tumor segmentation is significantly essential. However, segmentation has several difficulties, such as different sizes, variable shapes, and complex surrounding tissues. Therefore, a novel enhanced combined intelligent system is presented to predict lung cancer in this research. Methods Non-small cell lung cancer should be recognized for detecting lung cancer. In the pre-processing stage, the noise in the CT images is eliminated by using an average filter and adaptive median filter, and histogram equalization is used to enhance the filtered images to enhance the lung image quality in the proposed model. The adapted deep belief network (ADBN) is used to segment the affected region with the help of network layers from the noise-removed lung CT image. Two cascaded RBMs are used for the segmentation process in the structure of ADBN, including Bernoulli–Bernoulli (BB) and Gaussian-Bernoulli (GB), and then relevant significant features are extracted. The hybrid spiral optimization intelligent-generalized rough set (SOI-GRS) approach is used to select compelling features of the CT image. Then, an optimized light gradient boosting machine (LightGBM) model using the Ensemble Harris hawk optimization (EHHO) algorithm is used for lung cancer classification. Results LUNA 16, the Kaggle Data Science Bowl (KDSB), the Cancer Imaging Archive (CIA), and local datasets are used to train and test the proposed approach. Python and several well-known modules, including TensorFlow and Scikit-Learn, are used for the extensive experiment analysis. The proposed research accurately spot people with lung cancer according to the results. The method produced the least classification error possible while maintaining 99.87% accuracy. Conclusion The integrated intelligent system (ADBN-Optimized LightGBM) gives the best results among all input prediction models, taking performance criteria into account and boosting the system’s effectiveness, hence enabling better lung cancer patient diagnosis by physicians and radiologists.

Detection of Ground Glass Opacities in COVID-19 Lung CT Images using Frangi Multiscale Vesselness Measure

In this work, an automated technique for the quick and accurate detection of Ground Glass Opacities (GGO) in chest CT images of COVID-19 pneumonia patients is presented. The method uses mathematical morphology-based methods and Otsu's thresholding during the segmentation of GGO regions in order to extract the lung fields. The program uses the Frangi Multiscale Vesselness Measure to identify and remove these structures based on the anatomical features of bronchioles. Using a dataset of 155 lung CT images, the study outperformed previous algorithms in terms of sensitivity, specificity, and accuracy, all exceeding 97.22%. Radiologists can be helped by this automated screening method to quickly find GGOs in lung CT scans.

Segmentation of Lung Lesions through Bilateral Learning Branches to Aggregating Contextual and Local Characteristics

Detecting and analyzing lung lesion regions using artificial intelligence is of great significance in the medical diagnosis of lung CT images, which can substantially improve the efficiency of doctors. However, segmentation of the inflammatory region in the CT image of the lung remains challenging due to the varied sizes, blurry local details, irregular shapes, and limited sizes of datasets. Faced with these challenges, this paper proposes a novel lung lesion segmentation network that incorporates two feature extraction branches to achieve a balance of speed and accuracy. We first design a context branch (CB) to preserve the scale-invariant global context information by the transformer-like module. Besides, a shallow detail branch (DB) based on a deep aggregation pyramid (DAP) module is designed to provide detailed information. Extensive experiments are conducted on two datasets, including the public COVID-19 dataset and a private dataset. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods. Moreover, the trade-off between accuracy and inference speed is achieved.

APNet: Adaptive projection network for medical image denoising.

In clinical medicine, low-dose radiographic image noise reduces the quality of the detected image features and may have a negative impact on disease diagnosis. In this study, Adaptive Projection Network (APNet) is proposed to reduce noise from low-dose medical images. APNet is developed based on an architecture of the U-shaped network to capture multi-scale data and achieve end-to-end image denoising. To adaptively calibrate important features during information transmission, a residual block of the dual attention method throughout the encoding and decoding phases is integrated. A non-local attention module to separate the noise and texture of the image details by using image adaptive projection during the feature fusion. To verify the effectiveness of APNet, experiments on lung CT images with synthetic noise are performed, and the results demonstrate that the proposed approach outperforms recent methods in both quantitative index and visual quality. In addition, the denoising experiment on the dental CT image is also carried out and it verifies that the network has a certain generalization. The proposed APNet is an effective method that can reduce image noise and preserve the required image details in low-dose radiographic images.

Accurate diagnosis of COVID-19 from lung CT images using transfer learning.

In this study, it is aimed to classify data by feature extraction from tomographic images for the diagnosis of COVID-19 using image processing and transfer learning. In the proposed study, CT images are made better detectable by artificial intelligence through preliminary processes such as masking and segmentation. Then, the number of data was increased by applying data augmentation. The size of the dataset contains a large number of images in numerical terms. Therefore, the results of the models are more reliable. The dataset is split into 70% training and 30% testing. In this way, different features of the applied models were found, and positive effects were achieved on the result. Transfer Learning was used to reduce training times and further increase the success rate. To find the best method, many different pre-trained Transfer Learning models have been tried and compared with many different studies. A total of 8,354 images were used in the research. Of these, 2,695 consist of COVID-19 patients and the remaining healthy chest tomography images. All of these images were given to the models through masking and segmentation processes. As a result of the experimental evaluation, the best model was determined to be ResNet-50 and the highest results were found (accuracy 95.7%, precision 94.7%, recall 99.2%, specificity 88.3%, F1 score 96.9%, ROC-AUC score 97%). The presence of a COVID-19 lesion in the images was identified with high accuracy and recall rate using the transfer learning model we developed using thorax CT images. This outcome demonstrates that the strategy will speed up the diagnosis of COVID-19.

Assessing Chronic Obstructive Pulmonary Disease (COPD) Mortality and Morbidity: A Review

From PubMed, referencing articles over the previous 4 years, 146 articles addressing morbidity and mortality of chronic obstructive pulmonary disease (COPD) were reviewed. The major topics covered in this article include the epidemiology of COPD, spirometry with ATS/ERS and GOLD staging, scoring Indices (BODE, ADO, FODEP), trajectories in the development of COPD, pathophysiology of COPD, classification of COPD phenotypes, pharmacotherapy of COPD, causes of Acute Exacerbation of COPD (AECOPD), CT Lung imaging in COPD, and COPD comorbidities. All studies are referenced allowing for greater exploration into given areas of interest (76 ref.).

Multiscale lung nodule segmentation based on 3D coordinate attention and edge enhancement

<abstract> <p>An important prerequisite for improving the reliability of lung cancer surveillance and clinical interventions is accurate lung nodule segmentation. Although deep learning is effective at performing medical image segmentation, lung CT image heterogeneity, nodule size, shape, and location variations, convolutional localized feature extraction characteristics, the receptive field limitations of continuous downsampling, lesion edge information losses, fuzzy boundary segmentation challenges, and the low segmentation accuracy achieved when segmenting lung CT images using deep learning remain. An edge-enhanced multiscale Sobel coordinate attention-atrous spatial convolutional pooling pyramid V-Net (SCA-VNet) algorithm for lung nodule segmentation was proposed to solve these problems. First, a residual edge enhancement module was designed, which was used to enhance the edges of the original data. Using an edge detection operator in combination with a residual module, this module could reduce data redundancy and alleviate the gray level similarity between the foreground and background. Then, a 3D atrous spatial convolutional pooling pyramid module set different expansion rates, which could obtain feature maps under different receptive fields and capture the multiscale information of the segmentation target. Finally, a three-dimensional coordinate attention network (3D CA-Net) module was added to the encoding and decoding paths to extract channel weights from multiple dimensions. This step propagated the spatial information in the coding layer to the subsequent layers, and it could reduce the loss of information during the forward propagation process. The proposed method achieved a Dice coefficient of 87.50% on the lung image database consortium and image database resource initiative (LIDC-IDRI). It significantly outperformed the existing lung nodule segmentation models (UGS-Net, REMU-Net, and multitask models) and compared favorably with the Med3D, CENet, and PCAM_Net segmentation models in terms of their Dice coefficients, which were 3.37%, 2.2%, and 1.43%, respectively. The experimental results showed that the proposed SCA-VNet model attained improved lung nodule segmentation accuracy and laid a good foundation for improving the early detection rate of lung cancer.</p> </abstract>

Design of compensation algorithms for zero padding and its application to a patch based deep neural network.

In this article, compensation algorithms for zero padding are suggested to enhance the performance of deep convolutional neural networks. By considering the characteristics of convolving filters, the proposed methods efficiently compensate convolutional output errors due to zero padded inputs in a convolutional neural network. Primarily the algorithms are developed for patch based SRResNet for Single Image Super Resolution and the performance comparison is carried out using the SRResNet model but due to generalized nature of the padding algorithms its efficacy is tested in U-Net for Lung CT Image Segmentation. The proposed algorithms show better performance than the existing algorithm called partial convolution based padding (PCP), developed recently.

Combination of CNN and Transformer for Lesion-Guided Honeycomb Lung CT Image Recognition

Combination of CNN and Transformer for Lesion-Guided Honeycomb Lung CT Image Recognition

MedSyn: Text-Guided Anatomy-Aware Synthesis of High-Fidelity 3-D CT Images.

This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. Algorithmic comparative assessments and blind evaluations conducted by 10 board-certified radiologists indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines and airways. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.