Computer-aided Disease Diagnosis Research Articles

Performance enhancement of machine learning algorithm for breast cancer diagnosis using hyperparameter optimization

Breast cancer is the most fatal women’s cancer, and accurate diagnosis of this disease in the initial phase is crucial to abate death rates worldwide. The demand for computer-aided disease diagnosis technologies in healthcare is growing significantly to assist physicians in ensuring the effectual treatment of critical diseases. The vital purpose of this study is to analyze and evaluate the classification efficiency of several machine learning algorithms with hyperparameter optimization techniques using grid search and random search to reveal an efficient breast cancer diagnosis approach. Choosing the optimal combination of hyperparameters using hyperparameter optimization for machine learning models has a straight influence on the performance of models. According to the findings of several evaluation studies, the k-nearest neighbor is addressed in this study for effective diagnosis of breast cancer, which got a 100.00% recall value with hyperparameters found utilizing grid search. k-nearest neighbor, logistic regression, and multilayer perceptron obtained 99.42% accuracy after utilizing hyperparameter optimization. All machine learning models showed higher efficiency in breast cancer diagnosis with grid search-based hyperparameter optimization except for XGBoost. Therefore, the evaluation outcomes strongly validate the effectiveness and reliability of the proposed technique for breast cancer diagnosis.

Volumetric Model Genesis in Medical Domain for the Analysis of Multimodality 2-D/3-D Data Based on the Aggregation of Multilevel Features

The automatic and accurate classification of medical imaging data has potential applications in computer-aided disease diagnosis, prognosis, and treatment. However, it remains a challenge to optimize recent deep learning algorithms in medical domain for the accurate classification of large-scale 3D volumetric data. To address these challenges, we propose an efficient deep volumetric classification network based on the aggregation of multilevel deep features for accurate classification of large-scale medical 2D/3D imaging data. To perform a detailed quantitative analysis of our method, 26 different datasets were fused to construct a single large-scale multimodal database that comprises a total of seventy different classes, including 151,095 data samples. Additionally, 15 different baseline methods were configured under the same experimental protocol for volumetric model genesis and extensive performance comparison with our method. The experimental results of our method exhibited promising performance as area under the curve of 93.66% and outperformed various state-of-the-art methods.

Reciprocal cross-modal guidance for liver lesion segmentation from multiple phases under incomplete overlap

Objective:Liver lesion segmentation is beneficial for computer-aided disease diagnosis, which can be further enhanced by incorporating multi-phase images. Nevertheless, existing segmentation models still need improvement as they build on the unsolid assumption that lesions are well-aligned between different phases. Our goal was to develop a robust model that achieves high accuracy in lesion segmentation, even in cases where incomplete overlap occurs across multiple phases. Methods:To overcome the strong assumption of precise alignment between phases, we introduce a novel deep neural network featuring multi-scale feature fusion and cross-phase feature guidance. The former enables the retrieval of effective information from each phase that is helpful in lesion segmentation, while the latter ensures exchanging of guidance maps for interphase segmentation. Results:Comprehensive experiments were carried out on an in-house multi-phase dataset having liver lesions, as well as a multi-modal dataset from the CHAOS challenge. Results show that our model surpasses existing state-of-the-art methods in segmenting liver lesions and abdominal organs from multi-phase images, even if the registration between phases is inaccurate. Conclusion:A competent solution was proposed for accurate liver lesion segmentation from multi-phase images, considering the imperfect registration between phases. The model was proved to be effective in extracting pertinent information from each phase and sharing useful information between phases. Significance:The accommodation of incomplete overlap in multi-phase images provides a new paradigm of accurate and robust lesion segmentation, which is particularly helpful in real-world scenarios where registration accuracy may be compromised.

Exploring the role of ChatGPT in medical image analysis

The rapid advancement of artificial intelligence (AI) in the field of medical image analysis has demonstrated various applications such as computer-aided disease diagnosis and prognosis, image registration, tissue segmentation, image fusion, annotations, etc. However, its real-time use in routine clinical settings is still far-fetched due to numerous factors including lack of clinical trials in AI, development of diverse datasets, generalization of AI models in real-time, their interpretability, and associated biases. The introduction of Chat Generative Pre-trained Transformer (ChatGPT) has further created both an opportunity and havoc in the minds of researchers for its use and applications in this field. This editorial aims to highlight the role of ChatGPT in the field of medical image analysis. An exploratory analysis was conducted on ChatGPT by asking more than a hundred questions related to this field like “what is medical image analysis”, “how can you help me with medical image analysis”, “generate a code for --- to perform medical image analysis”, “perform literature survey on --- for medical datasets”, “analyze the anomaly in this frame”, “write an editorial on ---”, “give road map for --- in medical image analysis” etc in February and May 2023. The inferences of the responses generated by ChatGPT, their variation over a two-month gap, our viewpoint, its shortcomings, and concluding remarks have been discussed in this editorial.

High-Dimensional Feature Selection Based on Improved Binary Ant Colony Optimization Combined with Hybrid Rice Optimization Algorithm

In the realm of high-dimensional data analysis, numerous fields stand to benefit from its applications, including the biological and medical sectors that are crucial for computer-aided disease diagnosis and prediction systems. However, the presence of a significant number of redundant or irrelevant features can adversely affect system accuracy and real-time diagnosis efficiency. To mitigate this issue, this paper proposes two innovative wrapper feature selection (FS) methods that integrate the ant colony optimization (ACO) algorithm and hybrid rice optimization (HRO). HRO is a recently developed metaheuristic that mimics the breeding process of the three-line hybrid rice, which is yet to be thoroughly explored in the context of solving high-dimensional FS problems. In the first hybridization, ACO is embedded as an evolutionary operator within HRO and updated alternately with it. In the second form of hybridization, two subpopulations evolve independently, sharing the local search results to assist individual updating. In the initial stage preceding hybridization, a problem-oriented heuristic factor assignment strategy based on the importance of the knee point feature is introduced to enhance the global search capability of ACO in identifying the smallest and most representative features. The performance of the proposed algorithms is evaluated on fourteen high-dimensional biomedical datasets and compared with other recently advanced FS methods. Experimental results suggest that the proposed methods are efficient and computationally robust, exhibiting superior performance compared to the other algorithms involved in this study.

A novel collaborative self-supervised learning method for radiomic data

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity of information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.

Parameter adaptive unit-linking pulse coupled neural network based MRI–PET/SPECT image fusion

Medical image fusion has many applications to healthcare that is accomplished by extracting and then combining the complementary information from multiple medical images into a single image. The pulse coupled neural network (PCNN) is greatly applied to image fusion due to its efficient coupling of surrounding neurons, but suffers from network complexity and manual parameter settings. This paper proposes a novel parameter adaptive unit-linking PCNN (PAULPCNN) model, whose parameters are automatically obtained from the external stimulus and exhibits a simpler structure than the original PCNN. The multi-scale decomposition-based methods, particularly based on the non-subsampled shearlet transform (NSST), are widely employed by researchers to perform medical image fusion due to their efficient separation of spatial details at different scales. Motivated by the advantages of the PCNN and multi-scale decomposition-based methods, a hybrid medical image fusion method based on the PAULPCNN model is introduced in the NSST domain that merges the salient complementary details from a gray-scale and the corresponding pseudo-color medical image captured at different modalities to produce a more informative image that is more useful to medical experts in computer-aided diagnosis of diseases. The proposed method first employs NSST to transform the source images into a low-pass and several high-pass sub-bands, respectively. The high-pass sub-bands are combined using the firing times of the proposed PAULPCNN model, whereas a new distance-weighted regional energy-based rule is applied to construct the fused low-pass sub-band, which while estimating regional energy, assigns weight to different neighboring pixels depending on their distance from the central pixel. Finally, inverse NSST is applied on the fused sub-bands to construct the fused image. The effectiveness of the proposed technique is shown using the fusion results of eleven state-of-the-art methods on thirty gray-scale and pseudo-color brain medical image pairs comprising mild Alzheimer’s disease, Huntington’s disease, motor neuron disease, sagittal plane, coronal plane, transaxial plane, and glioma image pairs, where eight objective metrics are considered for the quantitative assessment. Experimental results demonstrate that the proposed method is competitive with the state-of-the-art methods, which even outperforms some of these methods by providing fused images with better visual quality and greater objective performance, which are more suitable for specialists to diagnose brain diseases.

Brain Tumor Classification using SLIC Segmentation with Superpixel Fusion, GoogleNet, and Linear Neighborhood Semantic Segmentation

Brain tumor is an abnormal tissue mass resultant of uncontrolled growth of cells. Brain tumors often reduce life expectancy and cause death in the later stages. Automatic detection of brain tumors is a challenging and important task in computer-aided disease diagnosis systems. This paper presents a deep learning-based approach to the classification of brain tumors. The noise in the brain MRI image is removed using Edge Directional Total Variation Denoising. The brain MRI image is segmented using SLIC segmentation with superpixel fusion. The segments are given to a trained GoogleNet model, which identifies the tumor parts in the image. Once the tumor is identified, a Convolution Neural Network (CNN) based modified semantic segmentation model is used to classify the pixels along the edges of the tumor segments. The modified sematic segmentation uses a linear neighborhood of the pixel for better classification. The final tumor identified is accurate as pixels at the border are classified precisely. The experimental results show that the proposed method has produced an accuracy of 97.3% with GoogleNet classification model, and the linear neighborhood semantic segmentation has delivered an accuracy of 98%.

Segmentation of retinal vessels based on MRANet

The segmentation of retinal vessel takes a crucial part in computer-aided diagnosis of diseases and eye disorders. However, the insufficient segmentation of the capillary vessels and weak anti-noise interference ability make such task more difficult. To solve this problem, we proposed a multi-scale residual attention network (MRANet) which is based on U-Net network. Firstly, to collect useful information about the blood vessels more effectively, we proposed a multi-level feature fusion block (MLF block). Then, different weights of each fused feature are learned by using attention blocks, which can retain more useful feature information while reducing the interference of redundant features. Thirdly, multi-scale residual connection block (MSR block) is constructed, which can better extract the image features. Finally, we use the DropBlock layer in the network to reduce the network parameters and alleviate network overfitting. Experiments show that based on DRIVE, the accuracy rate and the AUC performance value of our network are 0.9698 and 0.9899 respectively, and based on CHASE_DB1 dataset, they are 0.9755 and 0.9893 respectively. Our network has a better segmentation effect compared with other methods, which can ensure the continuity and completeness of blood vessel segmentation.

Deep feature extraction of retinal images for diabetic retinopathy enhanced diagnosis

Most people of working age groups globally around are affected by diabetic retinopathy, which is the most common cause of preventable vision impairment. Recent studies have improved our comprehension of the need for more effective and affordable methods of identifying, managing, diagnosing, and treating retinal disease in clinical eye care practice. The development of computer-aided diagnosis tools must consider the significance of diabetic retinopathy screening programmes and the challenge of obtaining a valid early diagnosis of diabetic retinopathy at an affordable price. Retinal image analysis using computer-aided disease diagnosis may make it easier to screen the population for diabetes mellitus on a mass scale and may also assist physicians to make better use of their time. The creation of image processing models using big data analysis may run into many technical challenges, including the visualization analysis needed by image processing technologies, the semantic expression, and storage of large image samples, the complexity of the algorithms needed for feature extraction, recognition, and prediction analysis using big data, as well as the time and memory requirements.

Atrous residual convolutional neural network based on U-Net for retinal vessel segmentation.

Extracting features of retinal vessels from fundus images plays an essential role in computer-aided diagnosis of diseases, such as diabetes, hypertension, and cerebrovascular diseases. Although a number of deep learning-based methods have been used in this field, the accuracy of retinal vessel segmentation remains challenging due to limited densely annotated data, inter-vessel differences, and structured prediction problems, especially in areas of small blood vessels and the optic disk. In this paper, we propose an ARN model with a atrous block to address these issues, which can avoid the loss of data structure, and enlarge the receptive field, so that each convolution output contains a larger range of information. In addition, we also introduce residual convolution network to increase the network depth and improve the network performance.Some key parameters are used to measure the feasibility of the model, such as sensitivity (Se), specificity (Sp), F1-score (F1), accuracy (Acc), and area under each curve (AUC). Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed methods, which accuracy are 0.9686 on the DRIVE and 0.9746 on the CHASE DB1. The segmentation structure can assist the doctor in diagnosis more effectively.

Blockchain-Based Privacy Access Control Mechanism and Collaborative Analysis for Medical Images

Medical image analysis technology based on deep learning has played an important role in computer-aided disease diagnosis and treatment. Classification accuracy has always been the primary goal pursued by researchers. However, the image transmission process also faces the problems of limited wireless ad-hoc network (WAN) bandwidth and increased security risks. Moreover, when user data are exposed to unauthorized users, platforms can easily leak personal privacy. Aiming at the abovementioned problems, a system model and an access control scheme for the collaborative analysis of the diagnosis of diabetic retinopathy (DR) are constructed in this paper. The system model includes two stages of data cleaning and lesion classification. In the data cleaning phase, the private cloud writes the model obtained after training into the blockchain, and other private clouds use the best-performing model on the chain to identify the image quality when cleaning data and pass the high-quality image to the lesion classification model for use. In the lesion classification stage, each private cloud trains the classification model separately; uploads its own model parameters to the public cloud for aggregation to obtain a global model; and then sends the global model to each private cloud to achieve collaborative learning, reduce the amount of data transmission, and protect personal privacy. Access control schemes include improved role-based access control (RAC) used within the private cloud and blockchain-based access control used during the interaction between the private cloud and the public cloud program (BAC). RAC grants both functional rights and data access rights to roles and takes into account object attributes for fine-grained level control. Based on certificateless public-key encryption technology and blockchain technology, BAC can realize the identity authentication and authority identification of the private cloud while requesting the transmission of model parameters from the private cloud to the public cloud and protect the security of the identity, authority, and model parameters of the private cloud to achieve the effect of lightweight access control. In the experimental part, two retinal datasets are used for DR classification analysis. The results show that data cleaning can effectively remove low-quality images and improve the accuracy of early lesion classification for doctors, with an accuracy rate of 90.2%.

An Improved Expectation-Maximization Algorithm to Detect Liver Image Boundary in CT Scan Images

Liver segmentation is a prolific and important area of research that has been deeply studied for the last three decades. Its prominence is increasing in modern Computer-Aided disease Diagnosis (CAD) to deal with a huge amount of images. In this paper, the CT scan image is resized to 256 X 256, and noise is reduced by a median filter, and then local peaks are acquired. The optimal clusters (k) to be formed by Expectation-Maximization (EM) algorithm are obtained by setting the distance between local peaks and height greater than 5. Formulate k number of clusters using the EM algorithm. Crop random section of liver and obtain all the local peaks greater than average of local peaks. This provides the minimum and maximum threshold values using which a threshold-based segmentation is performed. The anticipated algorithm that is verified on 55 CT scan images offers promising results. The experimental outcomes are compared with the existing cluster-based liver segmentation algorithms.

An efficient two-step multi-organ registration on abdominal CT via deep-learning based segmentation

Registration of three dimensional (3D) abdominal computed tomography (CT) scans is essential for computer-aided disease diagnosis and treatment, but the non-rigid respiratory movements of abdomen increase its difficulty. An automatic two-step multi-organ registration method is presented in this paper for abdominal CT scans. First, the lightweight squeeze-and-excitation (SE) attention blocks and the fully connected conditional random field (CRF)-based post-processing are integrated into a fully convolutional networks (FCN) based model, which can achieve more accurate segmentation results for abdominal multiple organs such as liver, kidneys, and spleen. Then, a non-rigid local correlation coefficient (LCC) similarity metric and an isotropic total variation regularization are combined to register the multi-organ regions, which can reduce computation time and avoid the over-smooth problem of deformation field. The proposed method is validated on three public abdominal CT databases, and the experimental results show that the segmentation and registration performances of our method outperform those of some competing methods. Moreover, compared with global registration strategy, the average registration time of the proposed method is shortened by 20.45%, and the average MSE, PSNR, SSIM, and DICE values are also improved by 7.21%, 22.37%, 15.80%, and 14.43%, respectively.

Convolutional-Neural-Network Assisted Segmentation and SVM Classification of Brain Tumor in Clinical MRI Slices

Due to the increased disease occurrence rates in humans, the need for the Automated Disease Diagnosis (ADD) systems is also raised. Most of the ADD systems are proposed to support the doctor during the screening and decision making process. This research aims at developing a Computer Aided Disease Diagnosis (CADD) scheme to categorize the brain tumour of 2D MRI slices into Glioblastoma/Glioma class with better accuracy. The main contribution of this research work is to develop a CADD system with Convolutional-Neural-Network (CNN) supported segmentation and classification. The proposed CADD framework consist of the following phases; (i) Image collection and resizing, (ii) Automated tumour segmentation using VGG-UNet, (iv) Deep-feature extraction using VGG16 network, (v) Handcrafted feature extraction, (vi) Finest feature choice by firefly-algorithm, and (vii) Serial feature concatenation and binary classification. The merit of the executed CADD is confirmed using an investigation realized using the benchmark as well as clinically collected brain MRI slices. In this work, a binary classification with a 10-fold cross validation is implemented using well known classifiers and the results attained with the SVM-Cubic (accuracy >98%) is superior. This result confirms that the combination of CNN assisted segmentation and classification helps to achieve enhanced disease detection accuracy.

Towards evaluating the robustness of deep diagnostic models by adversarial attack.

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference process and may pose severe security concerns in clinical practice. Among all the factors that make the model not robust, the most serious one is adversarial examples. The so-called "adversarial example" is a well-designed perturbation that is not easily perceived by humans but results in a false output of deep diagnostic models with high confidence. In this paper, we evaluate the robustness of deep diagnostic models by adversarial attack. Specifically, we have performed two types of adversarial attacks to three deep diagnostic models in both single-label and multi-label classification tasks, and found that these models are not reliable when attacked by adversarial example. We have further explored how adversarial examples attack the models, by analyzing their quantitative classification results, intermediate features, discriminability of features and correlation of estimated labels for both original/clean images and those adversarial ones. We have also designed two new defense methods to handle adversarial examples in deep diagnostic models, i.e., Multi-Perturbations Adversarial Training (MPAdvT) and Misclassification-Aware Adversarial Training (MAAdvT). The experimental results have shown that the use of defense methods can significantly improve the robustness of deep diagnostic models against adversarial attacks.

Content-based image retrieval algorithm for nuclei segmentation in histopathology images

In today’s world, the medical diagnostic system shows a high reliance on medical imagery and digital nosology. To facilitate the fast and precise screening of samples, technology is leading towards the computer-aided disease diagnosis and grading. Image segmentation possesses high worth in the computer-aided disease diagnosis and grading systems to extract the region of interest. This paper presents a content-based image retrieval algorithm for histopathology image segmentation for identification and extraction of nuclei. The proposed technique furnishes nuclei segmentation in three cascaded stages; pre-processing, nuclei points and region refining, and composite nuclei segmentation. The performance of nuclei segmentation is investigated on six hematoxylins and eosin (H&E) stained histopathology images datasets. Simulation outcomes of the segmentation schemes confirm the superiority of the proposed method for nuclei segmentation in histopathology images in qualitative and quantitative analysis.

Polyp-Net: A Multimodel Fusion Network for Polyp Segmentation

Computer-aided diagnosis of disease primarily depends on proper vision-based measurement (VBM). The traditional approach followed for diagnosis of colorectal cancer includes a manual screening of colorectum via a colonoscope and resection of polyps for histopathological analysis to decide the grade of malignancy. This procedure is time-consuming and expensive, and removal of benign polyp for analysis signifies the inefficiency of the diagnosis system. These drawbacks inspired us to develop an automatic vision-based analysis method for preliminary in vivo malignancy analysis of the polyp region. In this work, we have proposed a fusion-based polyp segmentation network, namely, Polyp-Net. Recently, convolutional neural networks (CNNs) have shown immense success in the domain of medical image analysis as it can exploit in-depth significant features with high discrimination capabilities. Therefore, motivated by these insights, we have proposed an enriched version of CNN with a nascent pooling mechanism, namely dual-tree wavelet pooled CNN (DT-WpCNN). The resultant segmented mask contains some surplus high-intensity regions apart from the polyp region. These shortcomings are avoided using a new variation of the region-based level-set method, namely, the local gradient weighting-embedded level-set method (LGWe-LSM), which shows a significant reduction of false-positive rate. The pixel-level fusion of the two enhanced methods shows more potentiality in the segmentation of the polyp regions. Our proposed network is trained on CVC-colon DB and tested on CVC-clinic DB. It achieves a dice score of 0.839, volume-similarity of 0.863, precision of 0.836, recall of 0.811, F1-score of 0.823, F2-score of 0.815, and Hausdorff distance of 21.796 which outperforms the existing baseline CNN’s and recent state-of-the-art methods.

Artificial Intelligence-Based Diagnosis of Cardiac and Related Diseases.

Automatic chest anatomy segmentation plays a key role in computer-aided disease diagnosis, such as for cardiomegaly, pleural effusion, emphysema, and pneumothorax. Among these diseases, cardiomegaly is considered a perilous disease, involving a high risk of sudden cardiac death. It can be diagnosed early by an expert medical practitioner using a chest X-Ray (CXR) analysis. The cardiothoracic ratio (CTR) and transverse cardiac diameter (TCD) are the clinical criteria used to estimate the heart size for diagnosing cardiomegaly. Manual estimation of CTR and other diseases is a time-consuming process and requires significant work by the medical expert. Cardiomegaly and related diseases can be automatically estimated by accurate anatomical semantic segmentation of CXRs using artificial intelligence. Automatic segmentation of the lungs and heart from the CXRs is considered an intensive task owing to inferior quality images and intensity variations using nonideal imaging conditions. Although there are a few deep learning-based techniques for chest anatomy segmentation, most of them only consider single class lung segmentation with deep complex architectures that require a lot of trainable parameters. To address these issues, this study presents two multiclass residual mesh-based CXR segmentation networks, X-RayNet-1 and X-RayNet-2, which are specifically designed to provide fine segmentation performance with a few trainable parameters compared to conventional deep learning schemes. The proposed methods utilize semantic segmentation to support the diagnostic procedure of related diseases. To evaluate X-RayNet-1 and X-RayNet-2, experiments were performed with a publicly available Japanese Society of Radiological Technology (JSRT) dataset for multiclass segmentation of the lungs, heart, and clavicle bones; two other publicly available datasets, Montgomery County (MC) and Shenzhen X-Ray sets (SC), were evaluated for lung segmentation. The experimental results showed that X-RayNet-1 achieved fine performance for all datasets and X-RayNet-2 achieved competitive performance with a 75% parameter reduction.

Privileged Modality Distillation for Vessel Border Detection in Intracoronary Imaging.

Intracoronary imaging is a crucial imaging technology in coronary disease diagnosis as it visualizes the internal tissue morphologies of coronary arteries. Vessel border detection in intracoronary images (VBDI) is desired because it can help the succeeding procedures of computer-aided disease diagnosis. However, existing VDBI methods suffer from the challenge of vessel-environment variability (i.e. high intra- and inter-subject diversity of vessels and their surrounding tissues appeared in images). This challenge leads to the ineffectiveness in the vessel region representation for hand-crafted features, in the receptive field extraction for deeply-represented features, as well as performance suppression derived from clinical data limitation. To solve this challenge, we propose a novel privileged modality distillation (PMD) framework for VBDI. PMD transforms the single-input-single-task (SIST) learning problem in the single-mode VBDI to a multiple-input-multiple-task (MIMT) problem by using the privileged image modality to help the learning model in the target modality. This learns the enriched high-level knowledge with similar semantics and generalizes PMD on diversity-increased low-level image features for improving the model adaptation to diverse vessel environments. Moreover, PMD refines MIMT to SIST by distilling the learned knowledge from multiple to one modality. This eliminates the reliance on privileged modality in the test phase, and thus enables the applicability to each of different intracoronary modalities. A structure-deformable neural network is proposed as an elaborately-designed implementation of PMD. It expands a conventional SIST network structure to the MIMT structure, and then recovers it to the final SIST structure. The PMD is validated on intravascular ultrasound imaging and optical coherence tomography imaging. One modality is the target, and the other one can be considered as the privileged modality owing to their semantic relatedness. The experiments show that our PMD is effective in VBDI (e.g. the Dice index is larger than 0.95), as well as superior to six state-of-the-art VBDI methods.