-
Medicine Jun 2024The diagnosis of pneumoconiosis is complex and subjective, leading to inevitable variability in readings. This is especially true for inexperienced doctors. To improve... (Observational Study)
Observational Study
The diagnosis of pneumoconiosis is complex and subjective, leading to inevitable variability in readings. This is especially true for inexperienced doctors. To improve accuracy, a computer-assisted diagnosis system is used for more effective pneumoconiosis diagnoses. Three models (Resnet50, Resnet101, and DenseNet) were used for pneumoconiosis classification based on 1250 chest X-ray images. Three experienced and highly qualified physicians read the collected digital radiography images and classified them from category 0 to category III in a double-blinded manner. The results of the 3 physicians in agreement were considered the relative gold standards. Subsequently, 3 models were used to train and test these images and their performance was evaluated using multi-class classification metrics. We used kappa values and accuracy to evaluate the consistency and reliability of the optimal model with clinical typing. The results showed that ResNet101 was the optimal model among the 3 convolutional neural networks. The AUC of ResNet101 was 1.0, 0.9, 0.89, and 0.94 for detecting pneumoconiosis categories 0, I, II, and III, respectively. The micro-average and macro-average mean AUC values were 0.93 and 0.94, respectively. The accuracy and Kappa values of ResNet101 were 0.72 and 0.7111 for quadruple classification and 0.98 and 0.955 for dichotomous classification, respectively, compared with the relative standard classification of the clinic. This study develops a deep learning based model for screening and staging of pneumoconiosis is using chest radiographs. The ResNet101 model performed relatively better in classifying pneumoconiosis than radiologists. The dichotomous classification displayed outstanding performance, thereby indicating the feasibility of deep learning techniques in pneumoconiosis screening.
Topics: Humans; Pneumoconiosis; Deep Learning; Radiography, Thoracic; Male; Middle Aged; Reproducibility of Results; Female; Diagnosis, Computer-Assisted; Aged; Neural Networks, Computer
PubMed: 38905434
DOI: 10.1097/MD.0000000000038478 -
Medicine Jun 2024The aim of this study is to estimate the normal cross-sectional area and diameter of the stellate ganglion (SG) by ultrasound (US) in healthy adults. The study sample... (Observational Study)
Observational Study
The aim of this study is to estimate the normal cross-sectional area and diameter of the stellate ganglion (SG) by ultrasound (US) in healthy adults. The study sample included 80 stellate ganglia in 40 participants (15 males, 25 females), mean age 38 years, mean height 162.5 cm, mean weight 67.8 kg, mean body mass index 25.4 kg/m2. Two radiologists separately obtained US images of the bilateral SG. Each participant was scanned 3 times bilaterally to assess for intra-observer reliability. The mean diameter of the SG was 1 mm (range: 0.1-2). The mean CSA of the bilateral SG was 1.3 mm2 (range: 0.6-3.9). The SG diameter positively correlated with age. Our study demonstrates the ability of US to image the SG and estimate its normal diameter and CSA. Knowledge of how to identify and measure the SG during ultrasound-guided procedures would be expected to decrease the risk of associated complications and help establish normal reference values.
Topics: Humans; Male; Female; Adult; Stellate Ganglion; Ultrasonography; Middle Aged; Reference Values; Healthy Volunteers; Young Adult; Reproducibility of Results; Observer Variation
PubMed: 38905380
DOI: 10.1097/MD.0000000000038646 -
Cureus Jun 2024Accessory liver lobes are indeed morphological variations of the liver, representing additional lobes or smaller structures connected to the main liver mass. Beaver tail...
Accessory liver lobes are indeed morphological variations of the liver, representing additional lobes or smaller structures connected to the main liver mass. Beaver tail liver is a rare anatomic variation where the left lobe of the liver encroaches to enclose the spleen. These variants, often found by chance in patients, can create challenges in accurately distinguishing between the liver and spleen in imaging, potentially leading to misdiagnosis as splenic trauma or a subcapsular hematoma. While conducting routine dissections of the abdomen region, a variation in the size, position, and anatomical connections of the liver was noticed in a female cadaver of age 45 years. The left lobe of the liver was elongated more towards the left lateral side with some angulated narrowing after extending across the midline, encroaching the left upper quadrant of the abdomen, reaching in between the stomach and the visceral surface of the spleen, above the hilum of the spleen. The narrow end of the left lobe of the liver, placed in between the stomach and spleen, is named the hiding beaver tail liver. This variation differs from the typical beaver tail liver as well as the "kissing sign" of the liver and spleen. Unfamiliarity with such an anomaly of the liver may lead radiologists and clinicians to identify a normal anatomical variant as a pathological condition mistakenly or could confuse radiologists with fluid collections that often suggest trauma, potentially leading to fatal outcomes during invasive abdominal procedures.
PubMed: 38903980
DOI: 10.7759/cureus.62665 -
Frontiers in Medicine 2024Previous studies showed that contrast-enhanced (CE) morpho-functional magnetic resonance imaging (MRI) detects abnormalities in lung morphology and perfusion in patients...
Contrast agent-free functional magnetic resonance imaging with matrix pencil decomposition to quantify abnormalities in lung perfusion and ventilation in patients with cystic fibrosis.
BACKGROUND
Previous studies showed that contrast-enhanced (CE) morpho-functional magnetic resonance imaging (MRI) detects abnormalities in lung morphology and perfusion in patients with cystic fibrosis (CF). Novel matrix pencil decomposition MRI (MP-MRI) enables quantification of lung perfusion and ventilation without intravenous contrast agent administration.
OBJECTIVES
To compare MP-MRI with established morpho-functional MRI and spirometry in patients with CF.
METHODS
Thirty-nine clinically stable patients with CF (mean age 21.6 ± 10.7 years, range 8-45 years) prospectively underwent morpho-functional MRI including CE perfusion MRI, MP-MRI and spirometry. Two blinded chest radiologists assessed morpho-functional MRI and MP-MRI employing the validated chest MRI score. In addition, MP-MRI data were processed by automated software calculating perfusion defect percentage (QDP) and ventilation defect percentage (VDP).
RESULTS
MP perfusion score and QDP correlated strongly with the CE perfusion score (both = 0.81; < 0.01). MP ventilation score and VDP showed strong inverse correlations with percent predicted FEV1 ( = -0.75 and = -0.83; < 0.01). The comparison of visual and automated parameters showed that both MP perfusion score and QDP, and MP ventilation score and VDP were strongly correlated ( = 0.74 and = 0.78; both < 0.01). Further, the MP perfusion score and MP ventilation score, as well as QDP and VDP were strongly correlated ( = 0.88 and = 0.86; both < 0.01).
CONCLUSION
MP-MRI detects abnormalities in lung perfusion and ventilation in patients with CF without intravenous or inhaled contrast agent application, and correlates strongly with the well-established CE perfusion MRI score and spirometry. Automated analysis of MP-MRI may serve as quantitative noninvasive outcome measure for diagnostic monitoring and clinical trials.
PubMed: 38903825
DOI: 10.3389/fmed.2024.1349466 -
ArXiv Feb 2024In radiology, Artificial Intelligence (AI) has significantly advanced report generation, but automatic evaluation of these AI-produced reports remains challenging....
In radiology, Artificial Intelligence (AI) has significantly advanced report generation, but automatic evaluation of these AI-produced reports remains challenging. Current metrics, such as Conventional Natural Language Generation (NLG) and Clinical Efficacy (CE), often fall short in capturing the semantic intricacies of clinical contexts or overemphasize clinical details, undermining report clarity. To overcome these issues, our proposed method synergizes the expertise of professional radiologists with Large Language Models (LLMs), like GPT-3.5 and GPT-4. Utilizing In-Context Instruction Learning (ICIL) and Chain of Thought (CoT) reasoning, our approach aligns LLM evaluations with radiologist standards, enabling detailed comparisons between human and AI-generated reports. This is further enhanced by a Regression model that aggregates sentence evaluation scores. Experimental results show that our "Detailed GPT-4 (5-shot)" model achieves a 0.48 score, outperforming the METEOR metric by 0.19, while our "Regressed GPT-4" model shows even greater alignment with expert evaluations, exceeding the best existing metric by a 0.35 margin. Moreover, the robustness of our explanations has been validated through a thorough iterative strategy. We plan to publicly release annotations from radiology experts, setting a new standard for accuracy in future assessments. This underscores the potential of our approach in enhancing the quality assessment of AI-driven medical reports.
PubMed: 38903745
DOI: No ID Found -
ArXiv May 2024Multi-parametric MRI (mpMRI) studies are widely available in clinical practice for the diagnosis of various diseases. As the volume of mpMRI exams increases yearly,...
Multi-parametric MRI (mpMRI) studies are widely available in clinical practice for the diagnosis of various diseases. As the volume of mpMRI exams increases yearly, there are concomitant inaccuracies that exist within the DICOM header fields of these exams. This precludes the use of the header information for the arrangement of the different series as part of the radiologist's hanging protocol, and clinician oversight is needed for correction. In this pilot work, we propose an automated framework to classify the type of 8 different series in mpMRI studies. We used 1,363 studies acquired by three Siemens scanners to train a DenseNet-121 model with 5-fold cross-validation. Then, we evaluated the performance of the DenseNet-121 ensemble on a held-out test set of 313 mpMRI studies. Our method achieved an average precision of 96.6%, sensitivity of 96.6%, specificity of 99.6%, and F1 score of 96.6% for the MRI series classification task. To the best of our knowledge, we are the first to develop a method to classify the series type in mpMRI studies acquired at the level of the chest, abdomen, and pelvis. Our method has the capability for robust automation of hanging protocols in modern radiology practice.
PubMed: 38903740
DOI: No ID Found -
Cureus May 2024Cancer is often accompanied by bone metastasis, which may lead to skeletal-related events (SREs), such as pain, hypercalcemia, pathological fractures, spinal cord...
Cancer is often accompanied by bone metastasis, which may lead to skeletal-related events (SREs), such as pain, hypercalcemia, pathological fractures, spinal cord compression, orthopedic surgical intervention, and palliative radiation directed at the bone. Herein, we report the case of a 75-year-old female patient diagnosed with diffuse large B-cell lymphoma (DLBCL) with bone metastasis and a pathological fracture of the right iliac bone. The management strategy and follow-up were determined by a multidisciplinary cancer board comprising physicians, physiatrists, orthopedic surgeons, radiologists, and rehabilitation therapists. A conservative approach was chosen, incorporating a bone-modifying agent and weight-bearing restrictions for the right leg, along with rehabilitation therapy and post-discharge support. A multidisciplinary rehabilitation approach for two months enabled the patient to walk independently upon discharge. She maintains her activities of daily living (ADL) for over six months after discharge without any skeletal issues. This case highlights the effectiveness of a multidisciplinary approach in managing bone metastasis or involvement in patients with lymphoma.
PubMed: 38903364
DOI: 10.7759/cureus.60713 -
Canadian Association of Radiologists... Jun 2024In the immunocompromised setting, there are distinct radiologic findings of primary central nervous system lymphoma (PCNSL), including necrotic ring-enhancing lesions,... (Review)
Review
In the immunocompromised setting, there are distinct radiologic findings of primary central nervous system lymphoma (PCNSL), including necrotic ring-enhancing lesions, increased propensity for intralesional haemorrhage, and multiplicity. In this clinical context, advanced imaging with MR perfusion, spectroscopy, and diffusion-weighted imaging can be used to increase accuracy in the diagnosis of lymphoma over mimics such as high-grade glioma, metastases, or infection. This review summarizes the histology and pathophysiology of PCNSL in immunodeficient hosts, which provide a basis for its imaging appearances, prognosis, and treatment. This discussion is important for the general radiologist as the incidence of immunodeficiency-related PCNSL may be increasing.
PubMed: 38902978
DOI: 10.1177/08465371241259951 -
European Radiology Experimental Jun 2024We compared magnetic resonance imaging (MRI) turbo spin-echo images reconstructed using a deep learning technique (TSE-DL) with standard turbo spin-echo (TSE-SD) images...
BACKGROUND
We compared magnetic resonance imaging (MRI) turbo spin-echo images reconstructed using a deep learning technique (TSE-DL) with standard turbo spin-echo (TSE-SD) images of the lumbar spine regarding image quality and detection performance of common degenerative pathologies.
METHODS
This prospective, single-center study included 31 patients (15 males and 16 females; aged 51 ± 16 years (mean ± standard deviation)) who underwent lumbar spine exams with both TSE-SD and TSE-DL acquisitions for degenerative spine diseases. Images were analyzed by two radiologists and assessed for qualitative image quality using a 4-point Likert scale, quantitative signal-to-noise ratio (SNR) of anatomic landmarks, and detection of common pathologies. Paired-sample t, Wilcoxon, and McNemar tests, unweighted/linearly weighted Cohen κ statistics, and intraclass correlation coefficients were used.
RESULTS
Scan time for TSE-DL and TSE-SD protocols was 2:55 and 5:17 min:s, respectively. The overall image quality was either significantly higher for TSE-DL or not significantly different between TSE-SD and TSE-DL. TSE-DL demonstrated higher SNR and subject noise scores than TSE-SD. For pathology detection, the interreader agreement was substantial to almost perfect for TSE-DL, with κ values ranging from 0.61 to 1.00; the interprotocol agreement was almost perfect for both readers, with κ values ranging from 0.84 to 1.00. There was no significant difference in the diagnostic confidence or detection rate of common pathologies between the two sequences (p ≥ 0.081).
CONCLUSIONS
TSE-DL allowed for a 45% reduction in scan time over TSE-SD in lumbar spine MRI without compromising the overall image quality and showed comparable detection performance of common pathologies in the evaluation of degenerative lumbar spine changes.
RELEVANCE STATEMENT
Deep learning-reconstructed lumbar spine MRI protocol enabled a 45% reduction in scan time compared with conventional reconstruction, with comparable image quality and detection performance of common degenerative pathologies.
KEY POINTS
• Lumbar spine MRI with deep learning reconstruction has broad application prospects. • Deep learning reconstruction of lumbar spine MRI saved 45% scan time without compromising overall image quality. • When compared with standard sequences, deep learning reconstruction showed similar detection performance of common degenerative lumbar spine pathologies.
Topics: Humans; Male; Female; Prospective Studies; Deep Learning; Middle Aged; Magnetic Resonance Imaging; Lumbar Vertebrae; Adult; Aged; Signal-To-Noise Ratio; Spinal Diseases
PubMed: 38902467
DOI: 10.1186/s41747-024-00470-0 -
Ultrasonics Jun 2024Stiffness measurement using shear wave propagation velocity has been the most common non-invasive method for liver fibrosis assessment. The velocity is captured through...
Stiffness measurement using shear wave propagation velocity has been the most common non-invasive method for liver fibrosis assessment. The velocity is captured through a trace recorded by transient ultrasonographic elastography, with the slope indicating the velocity of the wave. However, due to various factors such as noise and shear wave attenuation, detecting shear wave trajectory on wave propagation maps is a challenging task. In this work, we made the first attempt to use deep learning methods for shear wave trajectory detection on wave propagation maps. Specifically, we adopted five deep learning models in this task and evaluated them by using a well-acknowledged metric based on EA-Angular-Score (EAA) and task-specific metric based on Young s-Score (Ys) in the line-detection field. Furthermore, we proposed an end-to-end framework based on a Transformer and Hough transform, named Transformer-enhanced Hough Transform (TEHT). It took a wave propagation map as input image and directly output the slope of the shear wave trajectory. The framework extracts multi-scale local features from wave propagation maps, employs a deformable attention mechanism for feature fusion, identifies the target line using the Hough transform's voting mechanism, and calculates the contribution of each scale through channel attention. Wave propagation maps from 68 patients were utilized in this study, with manual annotation performed by a rater who was trained as a radiologist, serving as the reference value. The evaluation revealed that the SLNet model exhibited F-measure of EA and Ys values as 40.33 % and 40.72 %, respectively, while the TEHT model showed F-measure of EA and Ys values as 80.96 % and 98.00 %, respectively. TEHT yielded significantly better performance than other deep learning models. Moreover, TEHT demonstrated strong concordance with the gold standard, yielding R values of 0.967 and 0.968 for velocity and liver stiffness, respectively. The present study therefore suggests the application of the TEHT model for assessing liver fibrosis owing to its superiority among the five deep learning models.
PubMed: 38901149
DOI: 10.1016/j.ultras.2024.107358