Quantitative Imaging in Medicine and Surgery最新文献

{"title":"Correlation between cardiac and hepatic native T1 value and myocardial late gadolinium enhancement in children with Kawasaki disease.","authors":"Shengkun Peng, Lingyi Wen, Zhongqin Zhou, Shan Huang, Lei Hu, Shiganmo Azhe, Chuan Wang, Nanjun Zhang, Meining Chen, Kaiyu Zhou, Yingkun Guo","doi":"10.21037/qims-24-791","DOIUrl":"10.21037/qims-24-791","url":null,"abstract":"<p><strong>Background: </strong>Kawasaki disease (KD) is an acute febrile illness and systemic vasculitis of unknown etiology that predominantly affects young children. The objective of this study was to investigate the correlation between myocardial and hepatic native T1 value and myocardial late gadolinium enhancement (LGE) in pediatric patients with KD.</p><p><strong>Methods: </strong>In this cross-sectional retrospective study, 115 KD patients (50 in the acute phase, 65 in the chronic phase) and 40 age- and gender-matched controls underwent cardiac magnetic resonance (CMR) imaging with T1 mapping and LGE sequences. KD patients were subgrouped based on the myocardial LGE. Cardiac and hepatic T1 value as well as laboratory tests were also analyzed.</p><p><strong>Results: </strong>Both cardiac and hepatic T1 value were significantly elevated in KD patients compared to controls, with the highest values noted in the acute phase (myocardial 1,393±70, 1,345±65, 1,303±62 ms; hepatic 813±25, 787±29, 758±38 ms; P=0.001, P=0.001, respectively). KD patients with myocardial LGE had significantly higher myocardial and hepatic T1 value in both the acute (1,442±66, 1,381±67 ms; 836±47, 803±30 ms, P=0.048, P=0.013, respectively) and chronic phases (myocardial 1,393±91, 1,331±50 ms; hepatic 811±39, 780±21 ms, P=0.012, P=0.001, respectively). Multivariate analysis demonstrated a significant correlation between the disease phase, albumin, and hepatic T1 value in KD patients. The combined of myocardial and hepatic T1 value significantly enhances the diagnostic performance of myocardial LGE, increasing the area under the curve (AUC) from 0.773 to 0.881 (P=0.013).</p><p><strong>Conclusions: </strong>Elevated myocardial and hepatic T1 values correlate with myocardial LGE in KD, highlighting systemic involvement. The integration of these T1 values enhances the non-invasive diagnosis of myocardial involvement in KD, demonstrating their utility in assessing disease severity and progression.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"1990-2002"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948400/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of PET/CT parameters and a clinical variable to predict the risk of progression of disease within 24 months (POD24) in follicular lymphoma.","authors":"Qiuhui Jiang, Zhijuan Lin, Qinwei Chen, Feng Lin, Chong Jiang, Manman Deng, Jie Zha, Long Liu, Chongyang Ding, Bing Xu","doi":"10.21037/qims-24-1504","DOIUrl":"10.21037/qims-24-1504","url":null,"abstract":"<p><strong>Background: </strong>Patients with follicular lymphoma (FL) who experience progression of disease within 24 months (POD24) of receiving first-line therapy had a significantly poorer prognosis than that without early progression. Due to the established prognostic relevance of positron emission tomography/computed tomography (PET/CT) parameters in FL and their clinical accessibility, we aimed to investigate the predictive role of PET/CT metabolism and dissemination parameters in POD24 for FL.</p><p><strong>Methods: </strong>The POD24 status of 155 patients who underwent PET/CT examinations at initial diagnosis was evaluated. Various baseline characteristics were collected, along with PET/CT-derived parameters, including the maximum tumor dissemination (Dmax), maximum standardized uptake (SUVmax) value, total metabolic tumor volume (TMTV), and total lesion glycolysis (TLG). A Cox proportional regression analysis was used to identify potential risk predictors of POD24. Receiver operating characteristic (ROC) curves were used to define the optimal cut-off values.</p><p><strong>Results: </strong>In our cohort, POD24 was observed in 21 (13.5%) FL patients. The univariate and multivariate Cox regression analyses revealed that elevated lactate dehydrogenase (LDH) was a significant predictor of POD24. Additionally, survival analyses based on the cut-off values showed that the risk of POD24 was significantly increased in patients with a Dmax >64.24 cm, SUVmax >11.23, TMTV >144.16 cm², and TLG >586.79 g. Further, a Dmax >64.24 cm, a TMTV >144.16 cm², and elevated LDH were selected for inclusion in a risk model [concordance index (C-index) =0.82], and the patients were divided into three risk groups, in which the rates of POD24 were 1.69%, 10.42%, and 35.29%, respectively (P<0.001). Our model exhibited excellent performance in terms of both the C-index and ROC curve analysis, surpassing the performance of models commonly used in the field.</p><p><strong>Conclusions: </strong>PET/CT parameters have prognostic value for POD24 in FL. The risk model, which combined PET/CT parameters with clinical indicators, could improve risk stratification and help guide therapeutic decisions.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2468-2480"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Left atrioventricular coupling and left atrial abnormality in patients with acute myocardial infarction with and without hyperglycemia assessed with 3.0T cardiac magnetic resonance imaging feature tracking.","authors":"Pei-Lun Han, Kang Li, Yu Jiang, Li Jiang, Xin Tang, Ying-Kun Guo, Yuan Li, Zhi-Gang Yang","doi":"10.21037/qims-24-1757","DOIUrl":"10.21037/qims-24-1757","url":null,"abstract":"<p><strong>Background: </strong>The relationship between stress hyperglycemia and left atrial (LA) abnormality and left atrioventricular coupling in patients with acute myocardial infarction (AMI) has not been fully explored. This study aimed to assess the additive effect of hyperglycemia on LA phasic function and to investigate the atrioventricular interaction in patients with AMI via cardiac magnetic resonance imaging (MRI).</p><p><strong>Methods: </strong>This study comprised 120 patients with AMI with admission normoglycemia (aNGL), 88 patients with AMI and admission hyperglycemia (aHGL), and 70 age- and sex-matched controls. LA volume (LAV), LA ejection fraction (LAEF), and LA reservoir/conduit/contraction strain (εs/εe/εa) were measured and compared. Subgroup analysis was performed according to the presence of LA enlargement [LAE; defined as a maximum LAV index (LAVImax) >55 mL/m²]. Univariate and multivariate linear regression analyses were employed to identify the independent factors related to LA phasic strains.</p><p><strong>Results: </strong>Compared with controls, patients with AMI had increased LAVI and decreased LAEF and LA strains (all P values <0.05), and the LA reservoir [LA total ejection fraction (LATEF) and εs] and conduit [LA passive ejection fraction (LAPEF) and εe] dysfunction was also present in those without LAE (all P values <0.05). Furthermore, εs and εe were significantly reduced in the aHGL group as compared with the aNGL group (both P values <0.001). After adjustments were made for confounding clinical factors, admission blood glucose level (aBGL) was independently and significantly associated with εs (β=-0.211; P=0.002) and εe (β=-0.215; P=0.001) in patients with AMI. After the introduction of left ventricular (LV) indicators into multivariable regression models, LV global longitudinal strain (GLS) was significantly associated with εs (β=-0.467; P<0.001) and εe (β=-0.455; P<0.001).</p><p><strong>Conclusions: </strong>Hyperglycemia was found to exacerbate LA reservoir and conduit dysfunction in patients with AMI. aBGL and LV GLS were independent determinants of the εs and the εe, suggesting that attention should be paid not only to glucose monitoring but also to cardiac function indicators.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2347-2361"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948394/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multifocal Epstein-Barr virus-associated smooth muscle tumors in a pediatric patient after kidney transplantation: a case description and literature analysis.","authors":"Xiaojing Lin, Hongchang Luo, Wei Zhang","doi":"10.21037/qims-24-1942","DOIUrl":"10.21037/qims-24-1942","url":null,"abstract":"","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2642-2651"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948438/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of axillary lymph node metastasis in T1 breast cancer using diffuse optical tomography, strain elastography and molecular markers.","authors":"Cong Shang, Jing Zhang, Ying Huang","doi":"10.21037/qims-24-1664","DOIUrl":"10.21037/qims-24-1664","url":null,"abstract":"<p><strong>Background: </strong>Early-stage breast cancer (BC) presents a certain risk of axillary lymph node (ALN) metastasis (ALNM), leading to different individualized treatment. Preoperative non-invasive prediction to determine ALN status is of great significance for avoiding ineffective axillary surgery. Tumor total hemoglobin concentration (TTHC), strain ratio (SR), and Ki-67 expression are associated with ALNM in BC, but few studies have focused on T1 BC. This study aimed to explore the usefulness of these factors individually and in combination for the preoperative prediction of ALNM in T1 BC.</p><p><strong>Methods: </strong>This was a cross-sectional study. A total of 122 patients with T1 BC were enrolled. TTHC and SR were assessed preoperatively using diffuse optical tomography and strain elastography, respectively. All patients were pathologically evaluated to determine ALN status. Univariate analysis and logistic regression trend test were performed to identify independent predictors. A combined model of imaging-pathological parameters for ALNM was developed.</p><p><strong>Results: </strong>Histopathological analysis indicated that 56 patients (45.9%) exhibited ALNM. The fully adjusted model demonstrated a significant trend correlating increased TTHC (P<0.01 for trend), SR (P<0.001 for trend), and Ki-67 expression (P=0.004 for trend) with ALNM. The area under the receiver operating characteristic curves (AUCs) of TTHC, SR, and Ki-67 expression for predicting ALNM were 0.707 [95% confidence interval (CI): 0.61-0.80], 0.718 (95% CI: 0.63-0.81) and 0.642 (95% CI: 0.56-0.73), respectively. The integration of imaging parameters (TTHC and SR) and Ki-67 expression yielded superior predictive performance for ALN status compared to each parameter individually, as evidenced by an AUC of 0.837 (95% CI: 0.76-0.91). The Hosmer-Lemeshow test P value was 0.880, demonstrating good calibration. In the subgroup analysis, the model exhibited positive predictive capabilities (AUC >0.75) across various subgroups, including molecular subtype, pathological type, and grade. Notably, the predictive performance was particularly enhanced in patients with invasive lobular carcinomas and triple-negative BC, with AUC values exceeding 0.90 for both subgroups.</p><p><strong>Conclusions: </strong>The study found that TTHC ≥185.75 µmol/L, SR ≥3.93 and Ki-67 expression ≥20% were strongly associated with ALNM in patients with T1 BC. The combined imaging-pathological model might provide a convenient preoperative method for predicting ALN status, which can assist clinicians in individualizing management for patients with early-stage BC.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2162-2174"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948403/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Midterm outcomes and costs of Pipeline embolization device alone versus Atlas stent-assisted coiling for unruptured anterior circulation aneurysms: a propensity score matched comparative analysis.","authors":"Linggen Dong, Chao Wang, Xinzhi Wu, Huaying Xu, Xuefang Wu, Ying Zhang, Ming Lv","doi":"10.21037/qims-24-1581","DOIUrl":"10.21037/qims-24-1581","url":null,"abstract":"<p><strong>Background: </strong>Endovascular treatment has achieved great progress over the past few decades, providing multiple options for the treatment of intracranial aneurysms (IAs). In the present era of flow diverters (FDs), the optimum endovascular management for unruptured IAs amenable to both stent-assisted coiling (SAC) and FDs remains to be determined. Therefore, our study aimed to compare the midterm outcomes and costs of Pipeline embolization device (PED) alone versus Atlas SAC for the treatment of unruptured saccular anterior circulation aneurysms.</p><p><strong>Methods: </strong>This is a retrospective cohort study in which we studied consecutive unruptured anterior circulation aneurysms treated with PED alone or Atlas SAC at our institution. Propensity score matching (PSM) was performed to control for potential differences.</p><p><strong>Results: </strong>A total of 731 patients with 739 aneurysms were included: 299 patients with 302 aneurysms received PED treatment and 432 patients with 437 aneurysms received Atlas SAC treatment. The two groups differed at baseline. After PSM, two comparable groups of 192 aneurysms each were obtained. The PED alone group had shorter procedure times (97.65±33.53 <i>vs.</i> 125.17±30.71 min, P<0.001), and higher total hospital costs ($31,322.84±3,567.04 <i>vs.</i> $27,595.79±6,825.05, P<0.001) than the Atlas SAC group. The use of Atlas SAC reduced hospital costs by 13.5% compared to PED alone. At follow-up, the PED alone group was more prone to develop in-stent stenosis (ISS) compared to the Atlas SAC group (4.2% <i>vs.</i> 0.5%, P=0.043). The retreatment rate was higher in the Atlas group than in the PED group (4.7% <i>vs.</i> 0%, P=0.007). However, the complete aneurysm occlusion rates, favorable neurological and follow-up costs were similar in both groups.</p><p><strong>Conclusions: </strong>This study showed similar midterm outcome with PED alone and Atlas SAC for the treatment of unruptured anterior circulation aneurysms. Atlas SAC required a longer procedure time, and PED alone increased hospital costs. However, patients who underwent PED treatment were more likely to develop ISS during follow-up. In addition, the retreatment rate was higher in the Atlas group than in the PED group.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"1977-1989"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948390/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiac magnetic resonance T2 mapping and T2* mapping for myocardial iron detection in iron-water phantom models and pediatric patients with transfusion-dependent thalassemia: a comparison study.","authors":"Hang Fu, Mei Yan, Xue Yang, Ke Xu, Ting Xu, Lini Liu, Muhan Li, Jiangyao Zeng, Yunan Zhang, Yilin Zhang, Wenjie Tian, Jing Lin, Yingkun Guo, Hongding Zhang, Huayan Xu","doi":"10.21037/qims-24-1769","DOIUrl":"10.21037/qims-24-1769","url":null,"abstract":"<p><strong>Background: </strong>The cardiac magnetic resonance (CMR) T2* mapping technique is widely used to quantify myocardial iron and assess iron overload in patients with transfusion-dependent thalassemia (TDT). However, the value of T2 mapping in detecting iron overload and its consistency with T2* mapping in the myocardium of pediatric patients are unknown. Thus, this study sought to explore the utility and feasibility of using T2 mapping to assess iron overload, and to provide an alternative non-invasive method for the assessment of iron overload in clinical practice.</p><p><strong>Methods: </strong>Vitro iron-water phantom models with different iron concentrations were used to analyze the correlation between the T2 and T2* values. In total, 113 TDT pediatric patients were prospectively enrolled in the study and underwent CMR examinations using a Philips 1.5T scanner, and T2 and T2* mapping of the short-axis of the left ventricle were performed. Pearson correlation analyses, Bland-Altman plots, the Student's <i>t</i>-test or Mann-Whitney <i>U</i> test, Receiver operating characteristic (ROC) curve analyses, and intraclass correlation coefficient (ICC) were applied to analyze the data.</p><p><strong>Results: </strong>Excellent negative correlations were found between the actual iron concentration and the measured T2* (r=-0.919, P=0.003) and T2 values (r=-0.888, P=0.008) of the vitro iron-water phantom models. Additionally, the measured T2* and T2 values of the phantom models were positively correlated (r=0.997, P<0.001). Bland-Altman plots revealed that the T2* and T2 values showed good agreement at the basal, middle, and apical levels of the left ventricle short-axis. The areas under the ROC curves for the diagnosis of myocardial iron overload by T2 mapping in the basal, middle, and apical segments were 0.78, 0.95, and 0.89, respectively.</p><p><strong>Conclusions: </strong>The T2 mapping technique may serve as an alternative and complementary method to the T2* mapping technique in assessing iron overload in TDT patients, which provides a new use of routine T2 mapping.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"1938-1949"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948408/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Magnetic resonance imaging features and diagnostic value analysis of non-mass enhancement lesions of the breast.","authors":"Weiyue Li, Shaofu Hong, Yan Shi, Jinsen Zou, Jie Ma, Jingshan Gong","doi":"10.21037/qims-24-254","DOIUrl":"10.21037/qims-24-254","url":null,"abstract":"<p><strong>Background: </strong>Due to the presence of distinctive morphological features and diverse pathological types, evaluation of breast non-mass enhancement (NME) lesions on magnetic resonance imaging (MRI) is challenging, generating more false-positive results as compared to enhancing mass lesions. Our objective was to identify the MRI features capable of distinguishing between benign and malignant NME lesions in the breast.</p><p><strong>Methods: </strong>A retrospective analysis was conducted, in which the clinical data and MRI manifestations of 101 NME lesions were examined and confirmed through surgical or biopsy pathology. Statistical analyses, including <i>t</i> tests, Wilcoxon rank-sum tests, χ² tests, Fisher exact tests, and receiver operating characteristic (ROC) curve analyses, were employed to compare the MRI characteristics and clinical features of benign and malignant NME lesions.</p><p><strong>Results: </strong>The study included 101 NME lesions from 98 patients (34 benign and 67 malignant). No statistically significant differences were observed in terms of clinical characteristics between the benign and malignant groups. However, there were significant differences in lesion maximum diameter (P=0.003), morphological distribution (P=0.003), internal enhancement patterns (P<0.001), time-intensity curve (TIC) types (P<0.001), early and delayed enhancement rates (P=0.001 and P<0.001, respectively), apparent diffusion coefficient (ADC), and T2 ratio (P=0.02). Notably, the diagnostic efficacy of ADC values was highest for the minimum value within a small region of interest (small ROI), yielding an area under the curve as high as 0.884.</p><p><strong>Conclusions: </strong>A comprehensive analysis of MRI features indicated their significant value for the differential diagnosis of benign and malignant NME lesions of the breast.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2457-2467"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948379/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reproducibility of the CT radiomic features of pulmonary nodules: the effects of the CT reconstruction algorithm, radiation dose, and contrast agent.","authors":"Shou-Xin Yang, Meng Li, Li-Na Zhou, Dong-Hui Hou, Li Zhang, Ning Wu","doi":"10.21037/qims-24-2026","DOIUrl":"10.21037/qims-24-2026","url":null,"abstract":"<p><strong>Background: </strong>The reproducibility of radiomic features (RFs) is essential in lung nodule diagnosis. This study aimed to prospectively investigate the effects of computed tomography (CT) scanning parameters on the reproducibility of RFs in pulmonary nodules.</p><p><strong>Methods: </strong>Patients with pulmonary nodules who underwent chest CT scans at the Cancer Hospital of the Chinese Academy of Medical Sciences between July 2018 and March 2019 were prospectively included in the study. Six sequences with three pairs of different scanning parameters, including the reconstruction algorithm [filtered back projection (FBP) <i>vs.</i> 50% adaptive statistical iterative reconstruction-V (ASiR-V)], radiation dose (low dose <i>vs.</i> standard dose), and contrast agent [contrast-enhanced (CE) CT <i>vs.</i> non-contrast enhanced (NE) CT], were used for each patient. When one of the scanning parameters was changed, the other two remained fixed. The nodules were classified into pure ground-glass nodules (pGGNs), part-solid nodules (PSNs), and solid nodules (SNs) according to the nodule consistency. RFs with an intraclass correlation coefficient (ICC) >0.75 were considered to have good retest reliability. All the RF values of the different scanning parameters and nodule consistency were investigated and compared.</p><p><strong>Results: </strong>A total of 150 pulmonary nodules, including 50 pGGNs, 50 PSNs, and 50 SNs, in 96 patients (mean age: 52±10 years; 62 females) were included in the study. In total, 320 RFs with an ICC >0.75 were evaluated. The proportion of RFs showed significant difference between FBP and 50% ASiR-V, low dose and standard dose, and CE and NE CT scans was 38.4% (123/320), 63.1% (202/320) and 54.1% (173/320), respectively. The radiation dose and contrast agent affected more RFs than the reconstruction algorithm (both P<0.001). In the subgroup analysis of nodule consistency, regardless of changes in the reconstruction algorithms, radiation doses, or contrast agents, the RFs showed significant difference among the pGGNs, PSNs, and SNs (all P<0.001).</p><p><strong>Conclusions: </strong>The scanning parameters affected the reproducibility of the RFs, and nodules of different consistency were affected differently. The effects of these parameters should be fully considered in radiomic analysis.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2309-2318"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948441/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing bone radiology images classification through appropriate preprocessing: a deep learning and explainable artificial intelligence approach.","authors":"Yaoyang Wu, Simon Fong, Jiahui Yu","doi":"10.21037/qims-24-1745","DOIUrl":"10.21037/qims-24-1745","url":null,"abstract":"<p><strong>Background: </strong>Medical image classification has been an important application for deep learning techniques for over a decade, and since the emergence of explainable artificial intelligence (XAI), researchers have started using XAI to validate the results produced by these black box models. In the research field, it has become clear that accuracy and efficiency are not the only crucial factors for developing medical deep learning models; the authenticity of results and the accountability of the model and its creator also matter greatly. The objective of this study is to emphasize the importance of authenticity of the results and the accountability of deep learning models used for medical purposes, through proposing targeted preprocessing method for medical dataset processed by deep learning models.</p><p><strong>Methods: </strong>In this paper we conduct comparison experiments on processing two bone radiology image datasets using various deep learning neural networks, while emphasizing on the effect of appropriate preprocessing methods for the dataset towards the models' prediction performance. Comparisons are conducted both horizontally, between performance of different neural networks; and vertically, of using same models processing datasets before and after going through appropriate preprocessing procedures. Furthermore, we evaluate the experimental results not only quantitatively, but also visually by using XAI techniques, in order to determine the reasonability and reliability of the predictions from the experiments.</p><p><strong>Results: </strong>Results showed that for the bone radiology image dataset used for our experiment, among the five comparison models, DenseNet201 achieved the highest validation accuracy of 78%. Using the same models to process the abovementioned dataset after conducting appropriate preprocessing procedures, performance for all models have increased by an average of 0.06. Using XAI technique to evaluate the comparison results for before/after preprocessing experiments, we could observe that the appropriate preprocessing method effectively helped the models to concentrate on the abnormality areas on the radiology images comparing to processing raw images.</p><p><strong>Conclusions: </strong>The novelty of this paper lies in its specific application of extended preprocessing techniques-namely, the removal of background and irrelevant parts-to medical images for improving the performance of deep learning models in classification tasks. While the concept of preprocessing images has been explored by many researchers, applying such targeted preprocessing steps to medical images, combined with the use of XAI to validate and illustrate the benefits, is a novel approach. This paper highlights the unique requirements of medical image data and proposes an innovative method to enhance model accuracy and reliability in medical diagnostics by removing background and redundant features from the images.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 3","pages":"2529-2546"},"PeriodicalIF":2.9,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948367/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}