Polish journal of radiology最新文献

Purpose: Cervical cancer continues to be one of the leading causes of death among females worldwide, and thus early diagnosis by using more advanced diagnostic procedures is crucial. The conventional Pap-smear procedure is accurate but subject to human error; thus, computerised, standardised, and automated diagnosis becomes imperative. Herein we present a novel framework of a fuzzy distance-based ensemble of convolutional neural networks (CNNs) for efficient cervical cancer classification from Pap-smear images.

Material and methods: The proposed approach integrates 5 models of CNN - Simple CNN, InceptionV3, Xception, Xception with Attention, and Inception Attention - via attention mechanisms to advance feature learning. A fuzzy distance-based aggregator function is introduced to fuse the predictions of these models optimally as per Euclidean, Manhattan, and cosine distance measures. Four advanced pre-processing techniques - wavelet denoising, contrast-limited adaptive histogram equalisation (CLAHE), background correction, and Laplacian sharpening - are employed to construct a cleaner dataset with enhanced image sharpness and segmentation.

Results: Experimental outcomes prove that the model is significantly better than state-of-the-art approaches, with an accuracy of 94% on the original dataset and 98.3% on the pre-processed dataset.

Conclusions: The method suggested herein has better noise robustness, interpretability through fuzzy logic, and automatic adaptation to various CNN frameworks without fine-tuning. These results acknowledge the promise of fuzzy logic-based CNN ensembles to improve machine-based cervical cancer diagnosis, which could be mapped to better and scalable diagnostic instruments in medical imaging.

Purpose: This study aimed to optimise the dynamic coronary computed tomography perfusion (CTP) protocol, focusing on patient preparation, scanning parameters, and image acquisition, reconstruction, and interpretation. Future phases will evaluate the diagnostic accuracy of dynamic CTP in detecting haemodynamically significant coronary artery disease (CAD), using invasive coronary angiography (ICA) and fractional flow reserve (FFR) as reference standards.

Material and methods: Thirty-six symptomatic patients with confirmed or suspected CAD underwent dynamic CTP using a whole-heart coverage CT scanner (Revolution Apex CT, GE Healthcare). Two patients were excluded due to non-diagnostic CTP results. Of the remaining 34 patients, 24 underwent both cardiac CT angiography (CCTA) and CTP, while 19 underwent CCTA, CTP, and ICA. Preliminary data were analysed by comparing CTP findings with CCTA and ICA/FFR when available.

Results: Among 578 myocardial segments, 424 (73.3%) showed normal perfusion and 154 (26.6%) exhibited hypoperfusion. Of the 17 cases with perfusion deficits, ICA confirmed significant stenosis in 10, resulting in 100% sensitivity and 22% specificity for detecting haemodynamically significant stenosis. FFR assessment in 10 patients demonstrated 60% concordance between CTP, ICA, and FFR. Incorporating CTP into the diagnostic pathway led to a 29.4% reclassification in management strategies.

Conclusions: The low specificity observed for detecting significant CAD underscores the need for further refinement of the CTP protocol. Future research should aim to optimise myocardial blood flow thresholds to improve diagnostic specificity and clinical applicability.

Purpose: Differentiating active from non-active multiple sclerosis (MS) lesions is critical for disease management but often relies on gadolinium-enhanced magnetic resonance imaging (MRI), raising concerns about retention risks and costs. This study introduces a contrast-free, multi-sequence MRI approach using radiomics and machine learning to classify MS lesion activity.

Material and methods: A total of 187 lesions from 31 MS patients (mean age 42.5 ± 11.3 years; 64.5% female) at Amin Hospital (November 2024 - February 2025) were retrospectively analysed using a 1.5 T MRI scanner. Five sequences - T1-weighted (T1W), T2-weighted (T2W), fluid-attenuated inversion recovery (FLAIR), diffusion-weighted imaging (DWI), and susceptibility-weighted imaging (SWI) - were processed to extract 8905 radiomic features, refined to 127 via correlation and recursive feature elimination. XGBoost classified lesions as active or non-active, validated on an internal test set (n = 28 lesions), with performance assessed by area under the receiver operating characteristic curve (AUC-ROC).

Results: The XGBoost model achieved an AUC-ROC of 0.87 (95% CI: 0.82-0.92), sensitivity of 0.85, and specificity of 0.83, outperforming other classifiers (SVM AUC 0.84). FLAIR (35.4%) and T2W (28.3%) dominated feature contributions, with SWI (12.6%) enhancing accuracy (AUC dropped to 0.84 without SWI). Noise simulation (Gaussian σ = 0.1) confirmed robustness (AUC = 0.86).

Conclusions: This integration of SWI with conventional sequences in a unified radiomic model offers a promising contrast-free alternative for MS lesion classification, achieving promising accuracy comparable to radiologist performance on an internal test set (n = 28 lesions), pending external validation. External validation is needed to confirm the generalisability, but this approach could reduce gadolinium reliance in clinical practice.

Purpose: To evaluate how different artificial intelligence (AI)-powered approaches affect human performance in a demanding chest computed tomography (CT) task, such as distinguishing between viral pneumonias.

Material and methods: Three radiologists blindly evaluated 220 chest CT scans of viral pneumonia cases (n = 151 COVID-19; n = 69 other viruses), classifying them with a probabilistic scoring system (COVID-19 Reporting and Data System - CO-RADS) in 2 phases: before (S1) and after (S2) receiving AI classifier results. Two S2 scenarios were investigated: a default approach, with AI predictions available for all cases, and a selective approach, with AI limited to equivocal S1 cases (CO-RADS = 3). Inter-reader agreement (Gwet's AC2) and diagnostic performance were analysed.

Results: Radiologists demonstrated good-to-excellent agreement across all scenarios (AC2 = 0.77-0.81). Evaluation changes between S1 and S2 occurred in 18% of cases, with 29% of cases initially classified as CO-RADS = 3. In these equivocal cases, AI led to an average correct classification rate of 85%. Conversely, when radiologists were confident in their S1 diagnoses (CO-RADS ≠ 3), classification changes in S2 occurred in 7% of cases, preventing incorrect diagnoses in 45% of patients but resulting in missed correct classifications in 55%. Regarding diagnostic performance, S1 accuracy was 78%, with 15% of CO-RADS = 3 cases. In S2, under the default approach, accuracy increased to 81%, with 16% of CO-RADS = 3 cases, whereas the selective approach achieved 79% accuracy with only 10% of CO-RADS = 3 cases. Only the selective approach significantly reduced the proportion of equivocal cases (p < 0.009).

Conclusions: A selective AI approach effectively reduces diagnostic uncertainty without introducing unnecessary complexity, emphasising its potential to optimise radiological workflows in challenging diagnostic scenarios.

Purpose: The purpose of this study was to determine the effectiveness of ADC histogram analysis in diagnosing and determining the aggressiveness of peripheral zone (PZ) prostate cancer, and to reveal the relationship between Gleason and PI-RADS scores.Material and method: 61 patients who underwent standard 12-core and cognitive prostate biopsy and multiparametric prostate magnetic resonance imaging before biopsy were included in the study. According to the pathology results, patients were classified as either having clinically significant cancer with malignancy (n = 35) or as clinically insignificant - benign (n = 26). The effectiveness of ADC histogram parameters to distinguish between benign and malignant lesions was investigated. Subsequently, 35 patients in the malignant group were grouped according to their Gleason scores, and the relationship between ADC histogram parameters and Gleason scores was examined.

Results: ADC max, standard deviation, entropy, voxel count, and volume were found to be significantly different between the benign and malignant groups (p < 0.05; p < 0.05; p < 0.01; p < 0.01; p < 0.01). According to the ROC curve: entropy (AUC = 0.75; 95% CI: 0.63-0.87), voxel count (AUC = 0.83; 95% CI: 0.73-0.93), and volume values (AUC = 0.83; 95% CI: 0.73-0.93) were statistically significant in the diagnosis of benign and malignant lesions in the prostate gland (area under the ROC curves). In the logistic regression analysis models (backward), it was found that an increase in volume increased the risk of malignant tumours by 1.75 times (p = 0.04; OR = 1.75; 95% CI: 1.00-3.04).

Conclusions: ADC histogram data contribute to the diagnosis of benign-malignant differentiation in PZ prostate lesions and predict the Gleason score in malignant lesions.

Crohn's disease (CD) is an increasingly common disease in clinical practice. The progress of medicine, which has resulted in an extension of the survival time of patients, the introduction of new treatment methods, and the nature of the disease itself means that we are seeing more and more new, unusual complications of this disease. We have reviewed three cases of rare complications of CD, with a focus on possible atypical complications that may be seen on imaging studies. Complications of CD and its treatment can occur in various organs and systems, and manifest in very non-specific ways. If unnoticed, they can be even life-threatening; therefore, it is important in clinical practice to take into account the possibility of their presence when evaluating patients with CD. When assessing radiological examinations of these people, we should take into account the possibility of atypical signs and radiographic features, and consider whether they may be related to the underlying disease.

Purpose: Accurate quantification of coronary artery calcium (CAC) via computed tomography (CT) imaging is essential for effective cardiovascular risk assessment. This study investigates the impact of different iteration levels in the advanced model-based iterative reconstruction (ADMIRE) algorithm on artificial intelligence-driven CAC quantification and subsequent risk stratification, with filtered back projection (FBP) serving as the reference.

Material and methods: For 254 patients undergoing coronary CT angiography (120 kVp, automated tube current), raw data were reconstructed using FBP and ADMIRE levels 1-5 (kernel Sa36, 3.0 mm slice thickness, 1.5 mm spacing). AI-derived CAC parameters (volume, mass, Agatston score) and risk stratification were compared across reconstruction groups. Statistical analysis employed the Friedman test, one-way analysis of variance, and c² test.

Results: Compared to FBP, ADMIRE 1-5 reduced image noise by 9.70% to 49.76% (noise: 14.95 ± 2.26 HU vs. 7.55 ± 1.40 HU, F = 455.105, p < 0.001). Maximum CAC CT values progressively decreased with higher ADMIRE levels (FBP: 458.50 [306.00-645.00] HU vs. ADMIRE 5: 432.50 [281.75-620.75] HU; χ² = 455.105, p < 0.001). CAC volume, mass, and Agatston scores declined significantly (p < 0.001 for all): volume decreased by 8.56-32.55% (FBP: 47.56 ± 5.93 mm³ vs. ADMIRE 5: 21.77 ± 3.46 mm³; F = 32.310); mass decreased by 8.73-32.57% (F = 29.477); and Agatston scores decreased by 8.77-33.13% (F = 31.104). Risk stratification shifted in 24/161 patients (14.91%) with detectable CAC. The effective radiation dose was 0.61 ± 0.18 mSv.

Conclusions: ADMIRE reconstruction reduces image noise but progressively lowers CAC quantification (volume, mass, Agatston score) and maximum CT values, leading to underestimation of cardiovascular risk in a subset of patients. Caution is warranted when applying ADMIRE iterative reconstruction for CAC scoring.

Purpose: Muscle injuries are common in competitive sports. Magnetic resonance imaging (MRI) and ultrasound (US) are the most commonly used methods for evaluating muscle injuries. Several classification systems for muscle injuries have been published. Mueller-Wohlfahrt et al. introduced a new classification system in 2013, currently the most widely used, employing grading to reflect the diverse spectrum of muscle injuries observed in athletes. The differentiation between lesions classified as type 3A (minor partial muscle tear) and 3B (moderate partial muscle tear) remains to be precisely established. In relation to recovery time, we researched possible statistically significant differences.

Material and methods: We conducted a comprehensive analysis of 100 MRI studies that were performed on high-level professional athletes who exhibited clinical signs of lower limb muscle injuries. We selected individuals whose myotendinous or myofascial lesions could be classified as 3A or 3B, based on the Mueller-Wohlfarth (MW) classification. The athletes were then categorised into groups based on the presence or absence of fluid collection at the site of injury. The study's medical practitioner provided data regarding the duration of the injury and the return to sporting activities. Regarding statistical analyses, a linear regression test was conducted to examine the correlation between the variable "fluid collections" and the duration of the injury. Following this, Fisher's t-test or the Mann-Whitney test was applied.

Results: The results of the association between "blood collection" and "duration of injury" revealed a statistically significant correlation. The median value of return to play (RTP) in patients with haemorrhagic collection (median = 29) was significantly higher in comparison with patients without haemorrhagic collection (median = 19), with a difference between the 2 samples of 10 days.

Conclusions: Our study highlights how this distinction could be easily practiced by recognizing the presence of a haemorrhagic collection and how it predominates in determining a worsening of the prognosis and therefore an extension of the RTP. Hence, we can conclude that athletes who do not have blood collection, but only interstitial haemorrhage between fibres can be considered as type 3A, while athletes with interstitial haemorrhage at diagnosis can be considered as type 3B.

Diffusion tensor imaging (DTI) and tractography are powerful non-invasive techniques for studying the human brain's white matter pathways. The uncinate fasciculus (UF) is a key frontotemporal tract involved in emotion regulation, memory, and language. Despite advancements, challenges persist in accurately mapping its structure and function due to methodological limitations in data acquisition and analysis. This review aims to provide a comprehensive overview of the strengths and limitations of DTI and tractography in studying the UF, focusing on its anatomy, data acquisition techniques, and associated neurological and psychiatric disorders. A systematic review of over 30 years of literature on UF was conducted, encompassing anatomical studies, DTI methodologies, and clinical applications. Studies involving both postmortem dissections and in vivo imaging were analysed, with particular attention to different DTI acquisition parameters, fibre tracking algorithms, and their impact on imaging accuracy. DTI has significantly improved our understanding of UF anatomy and its role in neurocognitive functions. However, methodological constraints such as low spatial resolution, crossing fibres, and inter-subject variability limit its precision. Advances in higher-field magnetic resonance imaging, improved diffusion models, and artificial intelligence-enhanced tractography offer promising solutions. UF abnormalities have been linked to various disorders, including schizophrenia, depression, autism spectrum disorders, and neurodegenerative diseases. While DTI and tractography are invaluable tools for studying the UF, their limitations necessitate cautious interpretation of results. Future research should focus on refining imaging techniques to enhance accuracy and clinical applicability, paving the way for better diagnostic and therapeutic strategies.