To address issues such as loss of detailed information, blurred target boundaries, and unclear structural hierarchy in medical image fusion, this paper proposes an adaptive feature medical image fusion network based on a full-scale diffusion model. First, a region-level feature map is generated using a kernel-based saliency map to enhance local features and boundary details. Then, a full-scale diffusion feature extraction network is employed for global feature extraction, alongside a multi-scale denoising U-shaped network designed to fully capture cross-layer information. A multi-scale feature integration module is introduced to reinforce texture details and structural information extracted by the encoder. Finally, an adaptive fusion scheme is applied to progressively fuse region-level features, global features, and source images layer by layer, enhancing the preservation of detail information. To validate the effectiveness of the proposed method, this paper validates the proposed model on the publicly available Harvard dataset and an abdominal dataset. By comparing with nine other representative image fusion methods, the proposed approach achieved improvements across seven evaluation metrics. The results demonstrate that the proposed method effectively extracts both global and local features of medical images, enhances texture details and target boundary clarity, and generates fusion image with high contrast and rich information, providing more reliable support for subsequent clinical diagnosis.
Humans ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Neural Networks, Computer ; Diagnostic Imaging/methods* ; Image Interpretation, Computer-Assisted/methods*

Objective To explore the optimal parameters for virtual mono-energetic imaging of liver solid lesions. Methods A retrospective analysis was performed on 60 patients undergoing contrast-enhanced spectral CT of the abdomen.The iodine concentration values of hepatic arterial phase images and the CT values of different mono-energetic images were measured.The correlation coefficient and coefficient of variation were calculated. Results The average correlation coefficients between iodine concentrations and CT values of hepatic solid lesion images at 40,45,50,55,60,65,and 70 keV were 0.996,0.995,0.993,0.989,0.978,0.970,and 0.961,respectively.The correlation coefficients at 40(P=0.007),45(P=0.022),50 keV (P=0.035)were higher than that at 55 keV,and the correlation coefficients at 40 keV(P=0.134) and 45 keV(P=0.368) had no significant differences from that at 50 keV.The coefficients of variation of the CT values at 40,45,and 50 keV were 0.146,0.154,and 0.163,respectively. Conclusion The energy of 40 keV is optimal for virtual mono-energetic imaging of liver solid lesions in the late arterial phase,which is helpful for the diagnosis of liver diseases.
Humans ; Tomography, X-Ray Computed ; Retrospective Studies ; Abdomen ; Iodine ; Liver/diagnostic imaging* ; Signal-To-Noise Ratio ; Radiographic Image Interpretation, Computer-Assisted/methods*

Objective To evaluate the impact of deep learning reconstruction algorithm on the image quality of head and neck CT angiography (CTA) at 100 kVp. Methods CT scanning was performed at 100 kVp for the 37 patients who underwent head and neck CTA in PUMC Hospital from March to April in 2021.Four sets of images were reconstructed by three-dimensional adaptive iterative dose reduction (AIDR 3D) and advanced intelligent Clear-IQ engine (AiCE) (low,medium,and high intensity algorithms),respectively.The average CT value,standard deviation (SD),signal-to-noise ratio (SNR),and contrast-to-noise ratio (CNR) of the region of interest in the transverse section image were calculated.Furthermore,the four sets of sagittal maximum intensity projection images of the anterior cerebral artery were scored (1 point:poor,5 points:excellent). Results The SNR and CNR showed differences in the images reconstructed by AiCE (low,medium,and high intensity) and AIDR 3D (all P<0.01).The quality scores of the image reconstructed by AiCE (low,medium,and high intensity) and AIDR 3D were 4.78±0.41,4.92±0.27,4.97±0.16,and 3.92±0.27,respectively,which showed statistically significant differences (all P<0.001). Conclusion AiCE outperformed AIDR 3D in reconstructing the images of head and neck CTA at 100 kVp,being capable of improving image quality and applicable in clinical examinations.
Humans ; Computed Tomography Angiography/methods* ; Radiation Dosage ; Deep Learning ; Radiographic Image Interpretation, Computer-Assisted/methods* ; Signal-To-Noise Ratio ; Algorithms

Objective: To investigate the detection and diagnostic efficacy of chest radiographs for ≤30 mm pulmonary nodules and the factors affecting them, and to compare the level of consistency among readers. Methods: A total of 43 patients with asymptomatic pulmonary nodules who consulted in Cancer Hospital, Chinese Academy of Medical Sciences from 2012 to 2014 and had chest CT and X-ray chest radiographs during the same period were retrospectively selected, and one nodule ≤30 mm was visible on chest CT images in the whole group (total 43 nodules in the whole group). One senior radiologist with more than 20 years of experience in imaging diagnosis reviewed CT images and recording the size, morphology, location, and density of nodules was selected retrospectively. Six radiologists with different levels of experience (2 residents, 2 attending physicians and 2 associate chief physicians independently reviewed the chest images and recorded the time of review, nodule detection, and diagnostic opinion. The CT imaging characteristics of detected and undetected nodules on X images were compared, and the factors affecting the detection of nodules on X-ray images were analyzed. Detection sensitivity and diagnosis accuracy rate of 6 radiologists were calculated, and the level of consistency among them was compared to analyze the influence of radiologists' seniority and reading time on the diagnosis results. Results: The number of nodules detected by all 6 radiologists was 17, with a sensitivity of detection of 39.5%(17/43). The number of nodules detected by ≥5, ≥4, ≥3, ≥2, and ≥1 physicians was 20, 21, 23, 25, and 28 nodules, respectively, with detection sensitivities of 46.5%, 48.8%, 53.5%, 58.1%, and 65.1%, respectively. Reasons for false-negative result of detection on X-ray images included the size, location, density, and morphology of the nodule. The sensitivity of detecting ≤30 mm, ≤20 mm, ≤15 mm, and ≤10 mm nodules was 46.5%-58.1%, 45.9%-54.1%, 36.0%-44.0%, and 36.4% for the 6 radiologists, respectively; the diagnosis accuracy rate was 19.0%-85.0%, 16.7%-6.5%, 18.2%-80.0%, and 0%-75.0%, respectively. The consistency of nodule detection among 6 doctors was good (Kappa value: 0.629-0.907) and the consistency of diagnostic results among them was moderate or poor (Kappa value: 0.350-0.653). The higher the radiologist's seniority, the shorter the time required to read the images. The reading time and the seniority of the radiologists had no significant influence on the detection and diagnosis results (P>0.05). Conclusions: The ability of radiographs to detect lung nodules ≤30 mm is limited, and the ability to determine the nature of the nodules is not sufficient, and the increase in reading time and seniority of the radiologists will not improve the diagnostic accuracy. X-ray film exam alone is not suitable for lung cancer diagnosis.
Humans ; Retrospective Studies ; Solitary Pulmonary Nodule/diagnostic imaging* ; Radiography ; Multiple Pulmonary Nodules/diagnostic imaging* ; Tomography, X-Ray Computed/methods* ; Lung Neoplasms/diagnostic imaging* ; Sensitivity and Specificity ; Radiographic Image Interpretation, Computer-Assisted/methods*

Early screening based on computed tomography (CT) pulmonary nodule detection is an important means to reduce lung cancer mortality, and in recent years three dimensional convolutional neural network (3D CNN) has achieved success and continuous development in the field of lung nodule detection. We proposed a pulmonary nodule detection algorithm by using 3D CNN based on a multi-scale attention mechanism. Aiming at the characteristics of different sizes and shapes of lung nodules, we designed a multi-scale feature extraction module to extract the corresponding features of different scales. Through the attention module, the correlation information between the features was mined from both spatial and channel perspectives to strengthen the features. The extracted features entered into a pyramid-similar fusion mechanism, so that the features would contain both deep semantic information and shallow location information, which is more conducive to target positioning and bounding box regression. On representative LUNA16 datasets, compared with other advanced methods, this method significantly improved the detection sensitivity, which can provide theoretical reference for clinical medicine.
Algorithms ; Humans ; Lung Neoplasms/diagnostic imaging* ; Neural Networks, Computer ; Radiographic Image Interpretation, Computer-Assisted/methods* ; Tomography, X-Ray Computed/methods*

Objective To evaluate the effect of a deep learning reconstruction (DLR) method on the visibility of contrast-enhanced CT images of the biliary system by comparing it with different iterative reconstruction algorithms including the adaptive iterative dose reduction 3D (AIDR 3D) algorithm,forward projected model based iterative reconstruction solution (FIRST),and filtered back projection (FBP) algorithm. Methods A total of 30 patients subjected to abdominal contrast-enhanced CT and diagnosed with dilatation of common bile duct or extrahepatic bile duct were retrospectively included in this study.The images of the portal phase were reconstructed via four different algorithms (FBP,AIDR 3D,FIRST,and DLR).Signal to noise ratio (SNR) and contrast to noise ratio (CNR) of the dilated bile duct,liver parenchyma,measurable bile duct lesions,and image noise were compared between the four datasets.In subjective analyses,two radiologists independently scored the image quality (best:4 points,second:3 points;third:2 points;fourth:1 point) of the four datasets based on the noise and image visual quality of the biliary system.The Friedman and the Bonferroni-Dunn post-hoc tests were performed for comparison. Results The DLR images (bile duct:4.42±0.87;liver parenchyma:3.78±1.47) yielded higher CNR than the FBP (bile duct:2.21±1.02,P<0.001;liver parenchyma:1.43±1.29,P<0.001),AIDR 3D (bile duct:2.81±0.91,P=0.024;liver parenchyma:2.39±1.94,P=0.278),and FIRST (bile duct:2.51±1.24,P<0.001;liver parenchyma:2.45±1.81,P=0.003) images.Furthermore,the DLR images had higher SNR (bile duct:1.39±0.85,liver parenchyma:9.75±1.90) than the FBP (bile duct:0.86±0.63,P<0.001;liver parenchyma:3.31±1.12,P<0.001) and FIRST (bile duct:1.01±0.61,P=0.013;liver parenchyma:5.73±1.37,P<0.001) images,and showed lower noise (10.51±3.53) than the FBP(4.10±3.92,P<0.001),AIDR 3D (15.72±2.41,P=0.032),and FIRST (17.20±3.82,P<0.001) images.SNR and CNR showed no significant differences between FIRST and AIDR 3D images (all P>0.05).DLR images [4(4,4)] obtained higher score than FPB [1(1,1),P<0.001],AIDR3D[3 (2,3),P=0.029],and FIRST[2 (2,3),P<0.001] images. Conclusion DLR algorithm improved the subjective and objective quality of the contrast-enhanced CT image of the biliary system.
Biliary Tract ; Deep Learning ; Humans ; Imaging, Three-Dimensional ; Radiographic Image Interpretation, Computer-Assisted/methods* ; Retrospective Studies ; Tomography, X-Ray Computed/methods*

To assess the value of noise-optimized virtual monoenergetic imaging (VMI+) reconstruction technique on objective and subjective image quality in patients with inflammatory bowel disease (IBD) undergoing abdominal dual-energy computed tomography (DECT).
 Methods: Datasets from 32 patients (22 men, 10 women) with IBD, who underwent abdominal DECT, were reconstructed by using the standard linearly blended (M_0.6), traditional monoenergetic (VMI) and VMI+ algorithms in 10-keV intervals from 40-100 keV. Attenuation in IBD lesions was measured to perform objective evaluation using signal-to-noise (SNR) and contrast-to-noise ratios (CNR). Subjective evaluation was performed by 3 independent blinded radiologists using 5-point Likert scales. The overall image quality, image sharpness, lesion delineation, and image noise were analyzed. 
 Results: Mean SNR and CNR peaked at 40 keV VMI+ series (SNR 8.28±2.34, CNR 5.10±2.10) and they were significantly higher than those in linearly blended (SNR 5.82±1.44, CNR 1.53±0.86) and all VMI series (all P<0.01). Subjective image parameter was the highest for the 50 keV VMI+ series regarding overall image quality (mean 4.80, all P<0.01). The highest image sharpness scores were observed at 40 and 50 keV VMI+ reconstructions (mean 4.14 and 4.25, respectively; P=0.415). VMI+ series at 40 keV provided the highest lesion delineation (mean 4.52, all P<0.01). Image noise was low at the 100 keV VMI+ and VMI series (mean 4.58 and 4.40, respectively; P≥0.11).
 Conclusion: Low-keV VMI+ reconstructions improves SNR, CNR, and subjective image quality significantly in patients with IBD.
Female ; Humans ; Inflammatory Bowel Diseases ; diagnostic imaging ; Male ; Radiographic Image Interpretation, Computer-Assisted ; Radiography, Dual-Energy Scanned Projection ; methods ; Reproducibility of Results ; Retrospective Studies ; Signal-To-Noise Ratio ; Tomography, X-Ray Computed ; methods

Radiology is a unique medical specialty that focuses on image interpretation and report generation with limited patient contact. Resident read-out sessions with teaching are a quintessential part of reporting workflow practices in teaching institutions. However, most radiologist-educators do not have formal training in teaching and learning experiences vary. The five-step 'microskills' model ('one-minute preceptor' technique) developed by Neher is an easily adopted teaching model that complements the workflow of the typical read-out session, and can be utilised by radiologists of varied teaching experience and seniority. The steps are: (a) get a commitment; (b) probe for supporting evidence; (c) teach general rules; (d) reinforce what was done right; and (e) correct mistakes. Feedback is important to the model and accounts for two out of five microskills. The teaching model emphasises knowledge application and establishing relevance, which is useful in engaging the millennial resident. It is easily assimilated and applied by radiologist-educators.
Curriculum ; Education, Medical ; methods ; Humans ; Internship and Residency ; Learning ; Physicians ; Preceptorship ; Radiographic Image Interpretation, Computer-Assisted ; Radiography ; Radiology ; education ; trends ; Teaching

Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of human health and disease. Developed from artificial neural networks, deep learning-based algorithms show great promise in extracting features and learning patterns from complex data. The aim of this paper is to provide an overview of deep learning techniques and some of the state-of-the-art applications in the biomedical field. We first introduce the development of artificial neural network and deep learning. We then describe two main components of deep learning, i.e., deep learning architectures and model optimization. Subsequently, some examples are demonstrated for deep learning applications, including medical image classification, genomic sequence analysis, as well as protein structure classification and prediction. Finally, we offer our perspectives for the future directions in the field of deep learning.
Algorithms ; Computational Biology ; methods ; Diagnostic Imaging ; Genomics ; methods ; Humans ; Image Interpretation, Computer-Assisted ; methods ; Machine Learning ; Neural Networks (Computer) ; Protein Structure, Secondary ; Proteins ; metabolism

PURPOSE: The purpose of this study was to examine whether periodontal pocket could be satisfactorily visualized by optical coherence tomography (OCT) and to suggest quantitative methods for measuring periodontal pocket depth. METHODS: We acquired OCT images of periodontal pockets in a porcine model and determined the actual axial resolution for measuring the exact periodontal pocket depth using a calibration method. Quantitative measurements of periodontal pockets were performed by real axial resolution and compared with the results from manual periodontal probing. RESULTS: The average periodontal pocket depth measured by OCT was 3.10±0.15 mm, 4.11±0.17 mm, 5.09±0.17 mm, and 6.05±0.21 mm for each periodontal pocket model, respectively. These values were similar to those obtained by manual periodontal probing. CONCLUSIONS: OCT was able to visualize periodontal pockets and show attachment loss. By calculating the calibration factor to determine the accurate axial resolution, quantitative standards for measuring periodontal pocket depth can be established regardless of the position of periodontal pocket in the OCT image.
Calibration ; Gingiva ; Image Interpretation, Computer-Assisted ; Methods ; Periodontal Pocket* ; Tomography, Optical Coherence*