Machine learning and new insights for breast cancer diagnosis.

Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.

Project to improve the management of the head injury patients presenting to the emergency department.

INTRODUCTION: At Sandwell General Hospital, there was no risk stratification tool or pathway for head injury (HI) patients presenting to the emergency department (ED). This resulted in significant delays in the assessment of HI patients, compromising patient safety and quality of care. AIMS: To employ quality improvement methodology to design an effective adult HI pathway that: ensured >90% of high-risk HI patients being assessed by ED clinicians within 15 min of arrival, reduce CT turnaround times, and aiming to keep the final decision making <4 hours. METHODS: SWOT analysis was performed; driver diagrams were used to set out the aims and objectives. Plan-Do-Study-Act cycle was used to facilitate the change and monitor the outcomes. Process map was designed to identify the areas for improvement. A new HI pathway was introduced, imaging and transporting the patients was modified, and early decisions were made to meet the standards. RESULTS: Data were collected and monitored following the interventions. The new pathway improved the proportion of patients assessed by the ED doctors within 15 min from 31% to 63%. The average time to CT head scan was decreased from 69 min to 53 min. Average CT scan reporting time also improved from 98 min to 71 min. Overall, the average time to decision for admission or discharge decreased from 6 hours 48 min to 4 hours 24 min. CONCLUSIONS: Following implementation of the new HI pathway, an improvement in the patient safety and quality of care was noted. High-risk HI patients were picked up earlier, assessed quicker and had CT head scans performed sooner. Decision time for admission/discharge was improved. The HI pathway continues to be used and will be reviewed and re-audited between 3 and 6 months to ensure the sustained improvement.

MRCT and CT in the diagnosis of pediatric disease imaging: assessing imaging performance and clinical effects.

OBJECTIVE: This study focused on analyzing the clinical value and effect of magnetic resonance imaging plus computed tomography (MRCT) and CT in the clinical diagnosis of cerebral palsy in children. METHODS: From February 2021 to April 2023, 94 children diagnosed with cerebral palsy were selected from our hospital for study subjects. These patients were divided into CT and MRI groups, with CT examination given to the CT group and MRI examination given to the MRI group. The positive rate of the two examination methods in the diagnosis of cerebral palsy was compared, different imaging signs in two groups of children with cerebral palsy were compared, and the diagnostic test typing results between two groups were further analyzed. RESULTS: The diagnostic positivity rate of the children in the MRI group was 91.49%, which was significantly higher than that of the children in the CT group (70.21%) (P < 0.05). In both groups, encephalomalacia, bilateral frontal subdural effusions, and gray-white matter atrophy of the brain were the main signs, and the difference in the proportion of these three imaging signs between the two groups was not significant (P > 0.05). Differences between the two groups examined for cerebral palsy subtypes were not significant (P > 0.05). CONCLUSION: The positive rate of pediatric cerebral palsy examined by MRI is higher than that of CT diagnosis, but the clinic should organically combine the two to further improve the detection validity and accuracy.

Visual Interpretation of Radiomics Features in Filtered Computed Tomography Images during the Portal Phase of Acute Pancreatitis.

BACKGROUND: Current research on radiomics for diagnosing and prognosing acute pancreatitis predominantly revolves around model development and testing. However, there is a notable absence of ongoing interpretation and analysis regarding the physical significance of these models and features. Additionally, there is a lack of extensive exploration of visual information within the images. This limitation hinders the broad applicability of radiomics findings. This study aims to address this gap by specifically analyzing filtered Computed Tomography (CT) image features of acute pancreatitis to identify meaningful visual markers in the pancreas and peripancreatic area. METHODS: Numerous filtered CT images were obtained through pyradiomics. The window width and window level were fine-tuned to emphasize the pancreas and peripancreatic regions. Subsequently, the LightGBM algorithm was employed to conduct an embedded feature screening, followed by statistical analysis to identify features with statistical significance (p-value < 0.01). Within the purview of the study, for each filtering method, features of high importance to the preceding prediction model were incorporated into the analysis. The image visual markers were then systematically sought in reverse, and their medical interpretation was undertaken to a certain extent. RESULTS: In Laplacian of Gaussian filtered images within the pancreatic region, severe acute pancreatitis (SAP) exhibited fewer small areas with repetitive greyscale patterns. Conversely, in the peripancreatic region, SAP displayed greater irregularity in both area size and the distribution of greyscale levels. In logarithmic images, SAP demonstrated reduced low greyscale connectivity in the pancreatic region, while showcasing a higher average variation in greyscale between two adjacent pixels in the peripancreatic region. Moreover, in gradient images, SAP presented with decreased repetition of two adjacent pixel greyscales within the pancreatic region, juxtaposed with an increased inhomogeneity in the size of the same greyscale region within the δ range in the peripancreatic region. CONCLUSIONS: Various filtered images convey distinct physical significance and properties. The selection of the appropriate filtered image, contingent upon the characteristics of the Region of Interest (ROI), enables a more comprehensive capture of the heterogeneity of the disease.

Dépistage du cancer du poumon de routine dans la pratique clinique : que des bénéfices ?

Le dépistage annuel du cancer du poumon (lung cancer screening, LCS) par CT-scan à faible dose (LDCT) chez les adultes éligibles augmente la détection précoce de cancer pulmonaire dans la pratique communautaire et réduit la mortalité dans des études cliniques randomisées. Cependant, le LCS peut aussi présenter des inconvénients tels que des résultats faussement positifs, des imageries avec irradiation, la nécessité de procédures diagnostiques invasives et le risque de complications. Par conséquent, comprendre l'équilibre entre les avantages et les risques liés au LCS dans la pratique clinique est primordial afin d'optimiser les directives et les critères de qualité pour améliorer l'efficacité du dépistage à travers l'ensemble des systèmes de santé et des populations.

CBCT-DRRs superior to CT-DRRs for target-tracking applications for pancreatic SBRT.

Objective.In current radiograph-based intra-fraction markerless target-tracking, digitally reconstructed radiographs (DRRs) from planning CTs (CT-DRRs) are often used to train deep learning models that extract information from the intra-fraction radiographs acquired during treatment. Traditional DRR algorithms were designed for patient alignment (i.e.bone matching) and may not replicate the radiographic image quality of intra-fraction radiographs at treatment. Hypothetically, generating DRRs from pre-treatment Cone-Beam CTs (CBCT-DRRs) with DRR algorithms incorporating physical modelling of on-board-imagers (OBIs) could improve the similarity between intra-fraction radiographs and DRRs by eliminating inter-fraction variation and reducing image-quality mismatches between radiographs and DRRs. In this study, we test the two hypotheses that intra-fraction radiographs are more similar to CBCT-DRRs than CT-DRRs, and that intra-fraction radiographs are more similar to DRRs from algorithms incorporating physical models of OBI components than DRRs from algorithms omitting these models.Approach.DRRs were generated from CBCT and CT image sets collected from 20 patients undergoing pancreas stereotactic body radiotherapy. CBCT-DRRs and CT-DRRs were generated replicating the treatment position of patients and the OBI geometry during intra-fraction radiograph acquisition. To investigate whether the modelling of physical OBI components influenced radiograph-DRR similarity, four DRR algorithms were applied for the generation of CBCT-DRRs and CT-DRRs, incorporating and omitting different combinations of OBI component models. The four DRR algorithms were: a traditional DRR algorithm, a DRR algorithm with source-spectrum modelling, a DRR algorithm with source-spectrum and detector modelling, and a DRR algorithm with source-spectrum, detector and patient material modelling. Similarity between radiographs and matched DRRs was quantified using Pearson's correlation and Czekanowski's index, calculated on a per-image basis. Distributions of correlations and indexes were compared to test each of the hypotheses. Distribution differences were determined to be statistically significant when Wilcoxon's signed rank test and the Kolmogorov-Smirnov two sample test returnedp≤ 0.05 for both tests.Main results.Intra-fraction radiographs were more similar to CBCT-DRRs than CT-DRRs for both metrics across all algorithms, with allp≤ 0.007. Source-spectrum modelling improved radiograph-DRR similarity for both metrics, with allp< 10-6. OBI detector modelling and patient material modelling did not influence radiograph-DRR similarity for either metric.Significance.Generating DRRs from pre-treatment CBCT-DRRs is feasible, and incorporating CBCT-DRRs into markerless target-tracking methods may promote improved target-tracking accuracies. Incorporating source-spectrum modelling into a treatment planning system's DRR algorithms may reinforce the safe treatment of cancer patients by aiding in patient alignment.

Multi-scale feature aggregation and fusion network with self-supervised multi-level perceptual loss for textures preserving low-dose CT denoising.

Objective. The textures and detailed structures in computed tomography (CT) images are highly desirable for clinical diagnosis. This study aims to expand the current body of work on textures and details preserving convolutional neural networks for low-dose CT (LDCT) image denoising task.Approach. This study proposed a novel multi-scale feature aggregation and fusion network (MFAF-net) for LDCT image denoising. Specifically, we proposed a multi-scale residual feature aggregation module to characterize multi-scale structural information in CT images, which captures regional-specific inter-scale variations using learned weights. We further proposed a cross-level feature fusion module to integrate cross-level features, which adaptively weights the contributions of features from encoder to decoder by using a spatial pyramid attention mechanism. Moreover, we proposed a self-supervised multi-level perceptual loss module to generate multi-level auxiliary perceptual supervision for recovery of salient textures and structures of tissues and lesions in CT images, which takes advantage of abundant semantic information at various levels. We introduced parameters for the perceptual loss to adaptively weight the contributions of auxiliary features of different levels and we also introduced an automatic parameter tuning strategy for these parameters.Main results. Extensive experimental studies were performed to validate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method can achieve better performance on both fine textures preservation and noise suppression for CT image denoising task compared with other competitive convolutional neural network (CNN) based methods.Significance. The proposed MFAF-net takes advantage of multi-scale receptive fields, cross-level features integration and self-supervised multi-level perceptual loss, enabling more effective recovering of fine textures and detailed structures of tissues and lesions in CT images.

Take CT, get PET free: AI-powered breakthrough in lung cancer diagnosis and prognosis.

PET scans provide additional clinical value but are costly and not universally accessible. Salehjahromi et al.1 developed an AI-based pipeline to synthesize PET images from diagnostic CT scans, demonstrating its potential clinical utility across various clinical tasks for lung cancer.

CNN application for automated determination of the patient's size to obtain the size-specific dose estimated in CT.

Introduction. The currently available dosimetry techniques in computed tomography can be inaccurate which overestimate the absorbed dose. Therefore, we aimed to provide an automated and fast methodology to more accurately calculate the SSDE usingDwobtained by using CNN from thorax and abdominal CT study images.Methods. The SSDE was determined from the 200 records files. For that purpose, patients' size was measured in two ways: (a) by developing an algorithm following the AAPM Report No. 204 methodology; and (b) using a CNN according to AAPM Report No. 220.Results. The patient's size measured by the in-house software in the region of thorax and abdomen was 27.63 ± 3.23 cm and 28.66 ± 3.37 cm, while CNN was 18.90 ± 2.6 cm and 21.77 ± 2.45 cm. The SSDE in thorax according to 204 and 220 reports were 17.26 ± 2.81 mGy and 23.70 ± 2.96 mGy for women and 17.08 ± 2.09 mGy and 23.47 ± 2.34 mGy for men. In abdomen was 18.54 ± 2.25 mGy and 23.40 ± 1.88 mGy in women and 18.37 ± 2.31 mGy and 23.84 ± 2.36 mGy in men.Conclusions. Implementing CNN-based automated methodologies can contribute to fast and accurate dose calculations, thereby improving patient-specific radiation safety in clinical practice.

Utilizing Deep Learning and Computed Tomography to Determine Pulmonary Nodule Activity in Patients With Nontuberculous Mycobacterial-Lung Disease.

PURPOSE: To develop and evaluate a deep convolutional neural network (DCNN) model for the classification of acute and chronic lung nodules from nontuberculous mycobacterial-lung disease (NTM-LD) on computed tomography (CT). MATERIALS AND METHODS: We collected a data set of 650 nodules (316 acute and 334 chronic) from the CT scans of 110 patients with NTM-LD. The data set was divided into training, validation, and test sets in a ratio of 4:1:1. Bounding boxes were used to crop the 2D CT images down to the area of interest. A DCNN model was built using 11 convolutional layers and trained on these images. The performance of the model was evaluated on the hold-out test set and compared with that of 3 radiologists who independently reviewed the images. RESULTS: The DCNN model achieved an area under the receiver operating characteristic curve of 0.806 for differentiating acute and chronic NTM-LD nodules, corresponding to sensitivity, specificity, and accuracy of 76%, 68%, and 72%, respectively. The performance of the model was comparable to that of the 3 radiologists, who had area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of 0.693 to 0.771, 61% to 82%, 59% to 73%, and 60% to 73%, respectively. CONCLUSIONS: This study demonstrated the feasibility of using a DCNN model for the classification of the activity of NTM-LD nodules on chest CT. The model performance was comparable to that of radiologists. This approach can potentially and efficiently improve the diagnosis and management of NTM-LD.

Spontaneous isolated gastric intramural hematoma combined with spontaneous superior mesenteric artery intermural hematoma: a rare case.

BACKGROUND: Gastric intramural hematoma is a rare disease. Here we report a case of spontaneous isolated gastric intramural hematoma combined with spontaneous superior mesenteric artery intermural hematoma. CASE PRESENTATION: A 75-years-old man was admitted to our department with complaints of abdominal pain. He underwent a whole abdominal computed tomography (CT) scan in the emergency department, which showed extensive thickening of the gastric wall in the gastric body and sinus region with enlarged surrounding lymph nodes, localized thickening of the intestinal wall in the transverse colon, localized indistinct demarcation between the stomach and transverse colon, and a small amount of fluid accumulation in the abdominal cavity. Immediately afterwards, he was admitted to our department, and then we arranged a computed tomography with intravenously administered contrast agent showed a spontaneous isolated gastric intramural hematoma combined with spontaneous superior mesenteric artery intermural hematoma. Therefore, we treated him with anticoagulation and conservative observation. During his stay in the hospital, he was given low-molecular heparin by subcutaneous injection for anticoagulation therapy, and after discharge, he was given oral anticoagulation therapy with rivaroxaban. At the follow-up of more than 4 months, most of the intramural hematoma was absorbed and became significantly smaller, and the intermural hematoma of the superior mesenteric artery was basically absorbed, which also confirmed that the intramural mass was an intramural hematoma. CONCLUSION: A gastric intramural hematoma should be considered, when an intra-abdominal mass was found to be attached to the gastric wall. Proper recognition of gastric intramural hematoma can reduce the misdiagnosis rate of confusion with gastric cancer.

Deep learning in the radiologic diagnosis of osteoporosis: a literature review.

OBJECTIVE: Osteoporosis is a systemic bone disease characterized by low bone mass, damaged bone microstructure, increased bone fragility, and susceptibility to fractures. With the rapid development of artificial intelligence, a series of studies have reported deep learning applications in the screening and diagnosis of osteoporosis. The aim of this review was to summary the application of deep learning methods in the radiologic diagnosis of osteoporosis. METHODS: We conducted a two-step literature search using the PubMed and Web of Science databases. In this review, we focused on routine radiologic methods, such as X-ray, computed tomography, and magnetic resonance imaging, used to opportunistically screen for osteoporosis. RESULTS: A total of 40 studies were included in this review. These studies were divided into three categories: osteoporosis screening (n = 20), bone mineral density prediction (n = 13), and osteoporotic fracture risk prediction and detection (n = 7). CONCLUSIONS: Deep learning has demonstrated a remarkable capacity for osteoporosis screening. However, clinical commercialization of a diagnostic model for osteoporosis remains a challenge.

Exploring the link between a novel approach for computer aided lung sound analysis and imaging biomarkers: a cross-sectional study.

BACKGROUND: Computer Aided Lung Sound Analysis (CALSA) aims to overcome limitations associated with standard lung auscultation by removing the subjective component and allowing quantification of sound characteristics. In this proof-of-concept study, a novel automated approach was evaluated in real patient data by comparing lung sound characteristics to structural and functional imaging biomarkers. METHODS: Patients with cystic fibrosis (CF) aged > 5y were recruited in a prospective cross-sectional study. CT scans were analyzed by the CF-CT scoring method and Functional Respiratory Imaging (FRI). A digital stethoscope was used to record lung sounds at six chest locations. Following sound characteristics were determined: expiration-to-inspiration (E/I) signal power ratios within different frequency ranges, number of crackles per respiratory phase and wheeze parameters. Linear mixed-effects models were computed to relate CALSA parameters to imaging biomarkers on a lobar level. RESULTS: 222 recordings from 25 CF patients were included. Significant associations were found between E/I ratios and structural abnormalities, of which the ratio between 200 and 400 Hz appeared to be most clinically relevant due to its relation with bronchiectasis, mucus plugging, bronchial wall thickening and air trapping on CT. The number of crackles was also associated with multiple structural abnormalities as well as regional airway resistance determined by FRI. Wheeze parameters were not considered in the statistical analysis, since wheezing was detected in only one recording. CONCLUSIONS: The present study is the first to investigate associations between auscultatory findings and imaging biomarkers, which are considered the gold standard to evaluate the respiratory system. Despite the exploratory nature of this study, the results showed various meaningful associations that highlight the potential value of automated CALSA as a novel non-invasive outcome measure in future research and clinical practice.

Feasibility Study of Computed Tomographic Radiomics Model for the Prediction of Early and Intermediate Stage Hepatocellular Carcinoma Using BCLC Staging.

BACKGROUND: Hepatocellular carcinoma (HCC) is a serious health concern because of its high morbidity and mortality. The prognosis of HCC largely depends on the disease stage at diagnosis. Computed tomography (CT) image textural analysis is an image analysis technique that has emerged in recent years. OBJECTIVE: To probe the feasibility of a CT radiomic model for predicting early (stages 0, A) and intermediate (stage B) HCC using Barcelona Clinic Liver Cancer (BCLC) staging. METHODS: A total of 190 patients with stages 0, A, or B HCC according to CT-enhanced arterial and portal vein phase images were retrospectively assessed. The lesions were delineated manually to construct a region of interest (ROI) consisting of the entire tumor mass. Consequently, the textural profiles of the ROIs were extracted by specific software. Least absolute shrinkage and selection operator dimensionality reduction was used to screen the textural profiles and obtain the area under the receiver operating characteristic curve values. RESULTS: Within the test cohort, the area under the curve (AUC) values associated with arterial-phase images and BCLC stages 0, A, and B disease were 0.99, 0.98, and 0.99, respectively. The overall accuracy rate was 92.7%. The AUC values associated with portal vein phase images and BCLC stages 0, A, and B disease were 0.98, 0.95, and 0.99, respectively, with an overall accuracy of 90.9%. CONCLUSION: The CT radiomic model can be used to predict the BCLC stage of early-stage and intermediate-stage HCC.

Gender differences in spinal mobility during postural changes: a detailed analysis using upright CT.

Lumbar spinal alignment is crucial for spine biomechanics and is linked to various spinal pathologies. However, limited research has explored gender-specific differences using CT scans. The objective was to evaluate and compare lumbar spinal alignment between standing and sitting CT in healthy individuals, focusing on gender differences. 24 young and 25 elderly males (M) and females (F) underwent standing and sitting CT scans to assess lumbar spinal alignment. Parameters measured and compared between genders included lumbar lordosis (LL), sacral slope (SS), pelvic tilt (PT), pelvic incidence (PI), lordotic angle (LA), foraminal height (FH), and bony boundary area (BBA). Females showed significantly larger changes in SS and PT when transitioning from standing to sitting (p = .044, p = .038). A notable gender difference was also observed in the L4-S LA among the elderly, with females showing a significantly larger decrease in lordotic angle compared to males (- 14.1° vs. - 9.2°, p = .039*). Females consistently exhibited larger FH and BBA values, particularly in lower lumbar segments, which was more prominent in the elderly group (M vs. F: L4/5 BBA 80.1 mm2 [46.3, 97.8] vs. 109.7 mm2 [74.4, 121.3], p = .019 in sitting). These findings underline distinct gender-related variations in lumbar alignment and flexibility, with a focus on noteworthy changes in BBA and FH in females. Gender differences in lumbar spinal alignment were evident, with females displaying greater pelvic and sacral mobility. Considering gender-specific characteristics is crucial for assessing spinal alignment and understanding spinal pathologies. These findings contribute to our understanding of lumbar spinal alignment and have implications for gender-specific spinal conditions and treatments.

[Identifying Novel Coronavirus Pneumonia With CT Images: A Deep Learning Approach With Detail Upsampling and Attention Guidance]. / 从CTå›¾åƒä¸­æ£€æµ‹æ–°åž‹å† çŠ¶ç— æ¯’æ„ŸæŸ“å¯¼è‡´çš„è‚ºç‚Žï¼šä¸€ç§ç»†èŠ‚ä¸Šé‡‡æ ·å’Œæ³¨æ„åŠ›å¼•å¯¼çš„æ·±åº¦å­¦ä¹ æ–¹æ³•.

Objective: To construct a deep learning-based target detection method to help radiologists perform rapid diagnosis of lesions in the CT images of patients with novel coronavirus pneumonia (NCP) by restoring detailed information and mining local information. Methods: We present a deep learning approach that integrates detail upsampling and attention guidance. A linear upsampling algorithm based on bicubic interpolation algorithm was adopted to improve the restoration of detailed information within feature maps during the upsampling phase. Additionally, a visual attention mechanism based on vertical and horizontal spatial dimensions embedded in the feature extraction module to enhance the capability of the object detection algorithm to represent key information related to NCP lesions. Results: Experimental results on the NCP dataset showed that the detection method based on the detail upsampling algorithm improved the recall rate by 1.07% compared with the baseline model, with the AP50 reaching 85.14%. After embedding the attention mechanism in the feature extraction module, 86.13% AP50, 73.92% recall, and 90.37% accuracy were achieved, which were better than those of the popular object detection models. Conclusion: The feature information mining of CT images based on deep learning can further improve the lesion detection ability. The proposed approach helps radiologists rapidly identify NCP lesions on CT images and provides an important clinical basis for early intervention and high-intensity monitoring of NCP patients.

Comparison of vestibular aqueduct visualization on computed tomography and magnetic resonance imaging in patients with Ménière's disease.

BACKGROUND: The vestibular aqueduct (VA) serves an essential role in homeostasis of the inner ear and pathogenesis of Ménière's disease (MD). The bony VA can be clearly depicted by high-resolution computed tomography (HRCT), whereas the optimal sequences and parameters for magnetic resonance imaging (MRI) are not yet established. We investigated VA characteristics and potential factors influencing MRI-VA visibility in unilateral MD patients. METHODS: One hundred patients with unilateral MD underwent MRI with three-dimensional sampling perfection with application optimized contrasts using different flip angle evolutions (3D-SPACE) sequence and HRCT evaluation. The imaging variables included MRI-VA and CT-VA visibility, CT-VA morphology and CT-peri-VA pneumatization. RESULTS: The most frequent type of MRI-VA and CT-VA visualization was invisible VA and continuous VA, respectively. The MRI-VA visibility was significantly lower than CT-VA visibility. MRI-VA visibility had a weak positive correlation with ipsilateral CT-VA visualization. For the affected side, the MRI-VA visualization was negatively correlated with the incidence of obliterated-shaped CT-VA and positively with that of tubular-shaped CT-VA. MRI-VA visualization was not affected by CT-peri-VA pneumatization. CONCLUSION: In patients with MD, the VA visualization on 3D-SPACE MRI is poorer than that observed on CT and may be affected by its osseous configuration. These findings may provide a basis for further characterization of VA demonstrated by MRI and its clinical significance.

Acquired tracheomalacia due to SARS-CoV-2 pneumonia.

INTRODUCTION: Several studies mentioned parenchymal findings after SARS-CoV-2 pneumonia, but few studies have mentioned alterations in the airways. The aim of this study was to estimate the prevalence of tracheomalacia and to analyse the clinical characteristics in a cohort of patients with SARS-CoV-2. METHODS: The study population consisted of all patients with SARS-CoV-2 admitted a hospital serving a population of 500 000 inhabitants. Patients were visited between 2 and 6 months after hospital discharge. In this visit, all patients were subjected to an exhaustive clinical questionnaire and underwent clinical examination, pulmonary function tests and chest CT. RESULTS: From February 2020 to August 2021, 1920 patients were included in the cohort and tracheomalacia was observed in 15 (0.8%) on expiratory HRCT imaging. All patients with tracheomalacia also presented ground glass opacities in the CT scan and 12 patients had airway sequelae. CONCLUSIONS: Tracheomalacia is an exceptional sequela of SARS-CoV-2 survivors.

Deep Learning Prediction of Axillary Lymph Node Metastasis in Breast Cancer Patients Using Clinical Implication-Applied Preprocessed CT Images.

Background: Accurate detection of axillary lymph node (ALN) metastases in breast cancer is crucial for clinical staging and treatment planning. This study aims to develop a deep learning model using clinical implication-applied preprocessed computed tomography (CT) images to enhance the prediction of ALN metastasis in breast cancer patients. Methods: A total of 1128 axial CT images of ALN (538 malignant and 590 benign lymph nodes) were collected from 523 breast cancer patients who underwent preoperative CT scans between January 2012 and July 2022 at Hallym University Medical Center. To develop an optimal deep learning model for distinguishing metastatic ALN from benign ALN, a CT image preprocessing protocol with clinical implications and two different cropping methods (fixed size crop [FSC] method and adjustable square crop [ASC] method) were employed. The images were analyzed using three different convolutional neural network (CNN) architectures (ResNet, DenseNet, and EfficientNet). Ensemble methods involving and combining the selection of the two best-performing CNN architectures from each cropping method were applied to generate the final result. Results: For the two different cropping methods, DenseNet consistently outperformed ResNet and EfficientNet. The area under the receiver operating characteristic curve (AUROC) for DenseNet, using the FSC and ASC methods, was 0.934 and 0.939, respectively. The ensemble model, which combines the performance of the DenseNet121 architecture for both cropping methods, delivered outstanding results with an AUROC of 0.968, an accuracy of 0.938, a sensitivity of 0.980, and a specificity of 0.903. Furthermore, distinct trends observed in gradient-weighted class activation mapping images with the two cropping methods suggest that our deep learning model not only evaluates the lymph node itself, but also distinguishes subtler changes in lymph node margin and adjacent soft tissue, which often elude human interpretation. Conclusions: This research demonstrates the promising performance of a deep learning model in accurately detecting malignant ALNs in breast cancer patients using CT images. The integration of clinical considerations into image processing and the utilization of ensemble methods further improved diagnostic precision.

Chronological Course and Clinical Features after Denver Peritoneovenous Shunt Placement in Decompensated Liver Cirrhosis.

BACKGROUND: Refractory ascites affects the prognosis and quality of life in patients with liver cirrhosis. Peritoneovenous shunt (PVS) is a treatment procedure of palliative interventional radiology for refractory ascites. Although it is reportedly associated with serious complications (e.g., heart failure, thrombotic disease), the clinical course of PVS has not been thoroughly evaluated. OBJECTIVES: To evaluate the relationship between chronological course and complications after PVS for refractory ascites in liver cirrhosis patients. MATERIALS AND METHODS: This was a retrospective study of 14 patients with refractory ascites associated with decompensated cirrhosis who underwent PVS placement between June 2011 and June 2023. The clinical characteristics, changes in cardiothoracic ratio (CTR), and laboratory data (i.e., brain natriuretic peptide (BNP), D-dimer, platelet) were evaluated. Follow-up CT images in eight patients were also evaluated for ascites and complications. RESULTS: No serious complication associated with the procedure occurred in any case. Transient increases in BNP and D-dimer levels, decreased platelet counts, and the worsening of CTR were observed in the 2 days after PVS; however, they were improved in 7 days in all cases except one. In the follow-up CT, the amount of ascites decreased in all patients, but one patient with a continuous increase in D-dimer 2 and 7 days after PVS had thrombotic disease (renal and splenic infarction). The mean PVS patency was 345.4 days, and the median survival after PVS placement was 474.4 days. CONCLUSIONS: PVS placement for refractory ascites is a technically feasible palliative therapy. The combined evaluation of chronological changes in BNP, D-dimer, platelet count and CTR, and follow-up CT images may be useful for the early prediction of the efficacy and complications of PVS.