Deep Learning Reconstruction Shows Better Lung Nodule Detection for Ultra-Low-Dose Chest CT

An End-to-End CRSwNP Prediction with Multichannel ResNet on Computed Tomography

Chronic rhinosinusitis (CRS) is a global disease characterized by poor treatment outcomes and high recurrence rates, significantly affecting patients' quality of life. Due to its complex pathophysiology and diverse clinical presentations, CRS is categorized into various subtypes to facilitate more precise diagnosis, treatment, and prognosis prediction. Among these, CRS with nasal polyps (CRSwNP) is further divided into eosinophilic CRSwNP (eCRSwNP) and noneosinophilic CRSwNP (non-eCRSwNP). However, there is a lack of precise predictive diagnostic and treatment methods, making research into accurate diagnostic techniques for CRSwNP endotypes crucial for achieving precision medicine in CRSwNP. This paper proposes a method using multiangle sinus computed tomography (CT) images combined with artificial intelligence (AI) to predict CRSwNP endotypes, distinguishing between patients with eCRSwNP and non-eCRSwNP. The considered dataset comprises 22,265 CT images from 192 CRSwNP patients, including 13,203 images from non-eCRSwNP patients and 9,062 images from eCRSwNP patients. Test results from the network model demonstrate that multiangle images provide more useful information for the network, achieving an accuracy of 98.43%, precision of 98.1%, recall of 98.1%, specificity of 98.7%, and an AUC value of 0.984. Compared to the limited learning capacity of single-channel neural networks, our proposed multichannel feature adaptive fusion model captures multiscale spatial features, enhancing the model's focus on crucial sinus information within the CT images to maximize detection accuracy. This deep learning-based diagnostic model for CRSwNP endotypes offers excellent classification performance, providing a noninvasive method for accurately predicting CRSwNP endotypes before treatment and paving the way for precision medicine in the new era of CRSwNP.

Influence of Deep Learning Based Image Reconstruction on Quantitative Results of Coronary Artery Calcium Scoring

RATIONALE AND OBJECTIVES

To assess the impact of deep learning-based imaging reconstruction (DLIR) on quantitative results of coronary artery calcium scoring (CACS) and to evaluate the potential of DLIR for radiation dose reduction in CACS.

METHODS

For a retrospective cohort of 100 consecutive patients (mean age 62 ±10 years, 40% female), CACS scans were reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction (ASiR-V in 30%, 60% and 90% strength) and DLIR in low, medium and high strength. CACS was quantified semi-automatically and compared between image reconstructions. In a phantom study, a cardiac calcification insert was scanned inside an anthropomorphic thorax phantom at standard dose, 50% dose and 25% dose. FBP reconstructions at standard dose served as the reference standard.

RESULTS

In the patient study, DLIR led to a mean underestimation of Agatston score by 3.5, 6.4 and 11.6 points at low, medium and high strength, respectively. This underestimation of Agatston score was less pronounced for DLIR than for ASiR-V. In the phantom study, quantitative CACS results increased with reduced radiation dose and decreased with increasing strength of DLIR. Medium strength DLIR reconstruction at 50% dose reduction and high strength DLIR reconstruction at 75% dose reduction resulted in quantitative CACS results that were comparable to FBP reconstructions at standard dose.

CONCLUSION

Compared to FBP as the historical reference standard, DLIR leads to an underestimation of CACS but this underestimation is more moderate than with ASiR-V. DLIR can offset the increase in image noise and calcium score at reduced dose and may thus allow for substantial radiation dose reductions in CACS studies.

Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images

OBJECTIVES

This study aims to develop an innovative, deep model for thymoma risk stratification using preoperative CT images. Current algorithms predominantly focus on radiomic features or 2D deep features and require manual tumor segmentation by radiologists, limiting their practical applicability.

METHODS

The deep model was trained and tested on a dataset comprising CT images from 147 patients (82 female; mean age, 54 years ± 10) who underwent surgical resection and received subsequent pathological confirmation. The eligible participants were divided into a training cohort (117 patients) and a testing cohort (30 patients) based on the CT scan time. The model consists of two stages: 3D tumor segmentation and risk stratification. The radiomic model and deep model (2D) were constructed for comparative analysis. Model performance was evaluated through dice coefficient, area under the curve (AUC), and accuracy.

RESULTS

In both the training and testing cohorts, the deep model demonstrated better performance in differentiating thymoma risk, boasting AUCs of 0.998 and 0.893 respectively. This was compared to the radiomic model (AUCs of 0.773 and 0.769) and deep model (2D) (AUCs of 0.981 and 0.760). Notably, the deep model was capable of simultaneously identifying lesions, segmenting the region of interest (ROI), and differentiating the risk of thymoma on arterial phase CT images. Its diagnostic prowess outperformed that of the baseline model.

CONCLUSIONS

The deep model has the potential to serve as an innovative decision-making tool, assisting on clinical prognosis evaluation and the discernment of suitable treatments for different thymoma pathological subtypes.

KEY POINTS

• This study incorporated both tumor segmentation and risk stratification. • The deep model, using clinical and 3D deep features, effectively predicted thymoma risk. • The deep model improved AUCs by 16.1pt and 17.5pt compared to radiomic model and deep model (2D) respectively.

Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT

BACKGROUND

This study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable.

MATERIALS AND METHODS

A standardized CT dataset was established using an anthropomorphic chest phantom (Lungman, Kyoto Kaguku Inc., Kyoto, Japan) containing a set of 3D-printed lung nodules including six diameters (4 to 9 mm) and three morphology classes (lobular, spiculated, smooth), with an established ground truth. Images were acquired at varying radiation doses (6.04, 3.03, 1.54, 0.77, 0.41 and 0.20 mGy) and reconstructed with combinations of reconstruction kernels (soft and hard kernel) and reconstruction algorithms (ASIR-V and DLIR at low, medium and high strength). Semi-automatic volumetry measurements and subjective image quality scores recorded by five radiologists were analyzed with multiple linear regression and mixed-effect ordinal logistic regression models.

RESULTS

Volumetric errors of nodules imaged with DLIR are up to 50% lower compared to ASIR-V, especially at radiation doses below 1 mGy and when reconstructed with a hard kernel. Also, across all nodule diameters and morphologies, volumetric errors are commonly lower with DLIR. Furthermore, DLIR renders higher subjective IQ, especially at the sub-mGy doses. Radiologists were up to nine times more likely to score the highest IQ-score to these images compared to those reconstructed with ASIR-V. Lung nodules with irregular margins and small diameters also had an increased likelihood (up to five times more likely) to be ascribed the best IQ scores when reconstructed with DLIR.

CONCLUSION

We observed that DLIR performs as good as or even outperforms conventionally used reconstruction algorithms in terms of volumetric accuracy and subjective IQ of nodules in an anthropomorphic chest phantom. As such, DLIR potentially allows to lower the radiation dose to participants of lung cancer screening without compromising accurate measurement and characterization of lung nodules.

Factors Influencing Long-Term Local Recurrence, Distant Metastasis, and Survival in Patients with Soft Tissue Sarcoma of the Extremities Treated with Radiotherapy

INTRODUCTION

The prognostic factors for extremity soft-tissue sarcomas (ESTSs) treated with multimodal surgery and radiotherapy (RT) remain a subject of debate across diverse and heterogeneous studies.

METHODS

We retrospectively analyzed nonmetastatic ESTS patients treated with RT between 2007 and 2020 in Strasbourg, France. We assessed local control (LC), distant control (DC), overall survival (OS), and complications.

RESULTS

A total of 169 patients diagnosed with localized ESTS were included. The median age was 64 years (range 21-94 years). ESTS primarily occurred proximally (74.6%) and in the lower limbs (71%). Most tumors were grade 2-3 (71.1%), deep-seated (86.4%), and had R0 margins (63.9%). Most patients were treated with helical tomotherapy (79.3%). The median biologically effective dose (BED) prescribed was 75 BEDGy4 (range 45.0-109.9). The median follow-up was 5.5 years. The 5- and 10-year LC, DC, and OS rates were 91.7%, 76.8%, and 83.8% and 84.2%, 74.1%, and 77.6%, respectively. According to the univariate analysis, LC was worse for patients who received less than 75 BEDGy4 (p = 0.015). Deep tumors were associated with worse OS (p < 0.05), and grade 2-3 and undifferentiated pleomorphic sarcoma (UPS) were linked to both shorter DC and shorter OS (p < 0.05). IMRT was associated with longer LC than 3DRT (p = 0.018). Multivariate analysis revealed that patients with liposarcoma had better OS (p < 0.05) and that patients with distant relapse had shorter OS (p < 0.0001).

CONCLUSION

RT associated with surgical resection was well tolerated and was associated with excellent long-term rates of LC, DC, and OS. Compared with 3DRT, IMRT improved local control. Liposarcoma was a favorable prognostic factor for OS. Intermediate- and high-grade tumors and deep tumors were associated with lower DC and OS.

Image Quality and Lesion Detection of Multiplanar Reconstruction Images Using Deep Learning: Comparison with Hybrid Iterative Reconstruction

Background

We assessed and compared the image quality of normal and pathologic structures as well as the image noise in chest computed tomography images using "adaptive statistical iterative reconstruction-V" (ASiR-V) or deep learning reconstruction "TrueFidelity".

Methods

Forty consecutive patients with suspected lung disease were evaluated. The 1.25-mm axial images and 2.0-mm coronal multiplanar images were reconstructed under the following three conditions: (i) ASiR-V, lung kernel with 60% of ASiR-V; (ii) TF-M, standard kernel, image filter (Lung) with TrueFidelity at medium strength; and (iii) TF-H, standard kernel, image filter (Lung) with TrueFidelity at high strength. Two radiologists (readers) independently evaluated the image quality of anatomic structures using a scale ranging from 1 (best) to 5 (worst). In addition, readers ranked their image preference. Objective image noise was measured using a circular region of interest in the lung parenchyma. Subjective image quality scores, total scores for normal and abnormal structures, and lesion detection were compared using Wilcoxon's signed-rank test. Objective image quality was compared using Student's paired t-test and Wilcoxon's signed-rank test. The Bonferroni correction was applied to the P value, and significance was assumed only for values of P < 0.016.

Results

Both readers rated TF-M and TF-H images significantly better than ASiR-V images in terms of visualization of the centrilobular region in axial images. The preference score of TF-M and TF-H images for reader 1 were better than that of ASiR-V images, and the preference score of TF-H images for reader 2 were significantly better than that of ASiR-V and TF-M images. TF-M images showed significantly lower objective image noise than ASiR-V or TF-H images.

Conclusion

TrueFidelity showed better image quality, especially in the centrilobular region, than ASiR-V in subjective and objective evaluations. In addition, the image texture preference for TrueFidelity was better than that for ASiR-V.

Influence of deep learning image reconstruction algorithm for reducing radiation dose and image noise compared to iterative reconstruction and filtered back projection for head and chest computed tomography examinations: a systematic review

Background

The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations.

Methods

We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines.

Results

Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations.

Conclusions

DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy.

Low-dose liver CT: image quality and diagnostic accuracy of deep learning image reconstruction algorithm

OBJECTIVES

To perform a comprehensive within-subject image quality analysis of abdominal CT examinations reconstructed with DLIR and to evaluate diagnostic accuracy compared to the routinely applied adaptive statistical iterative reconstruction (ASiR-V) algorithm.

MATERIALS AND METHODS

Oncologic patients were prospectively enrolled and underwent contrast-enhanced CT. Images were reconstructed with DLIR with three intensity levels of reconstruction (high, medium, and low) and ASiR-V at strength levels from 10 to 100% with a 10% interval. Three radiologists characterized the lesions and two readers assessed diagnostic accuracy and calculated signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), figure of merit (FOM), and subjective image quality, the latter with a 5-point Likert scale.

RESULTS

Fifty patients (mean age: 70 ± 10 years, 23 men) were enrolled and 130 liver lesions (105 benign lesions, 25 metastases) were identified. DLIR_H achieved the highest SNR and CNR, comparable to ASiR-V 100% (p ≥ .051). DLIR_M returned the highest subjective image quality (score: 5; IQR: 4-5; p ≤ .001) and significant median increase (29%) in FOM (p < .001). Differences in detection were identified only for lesions ≤ 0.5 cm: 32/33 lesions were detected with DLIR_M and 26 lesions were detected with ASiR-V 50% (p = .031). Lesion accuracy of was 93.8% (95% CI: 88.1, 97.3; 122 of 130 lesions) for DLIR and 87.7% (95% CI: 80.8, 92.8; 114 of 130 lesions) for ASiR-V 50%.

CONCLUSIONS

DLIR yields superior image quality and provides higher diagnostic accuracy compared to ASiR-V in the assessment of hypovascular liver lesions, in particular for lesions ≤ 0.5 cm.

CLINICAL RELEVANCE STATEMENT

Deep learning image reconstruction algorithm demonstrates higher diagnostic accuracy compared to iterative reconstruction in the identification of hypovascular liver lesions, especially for lesions ≤ 0.5 cm.

KEY POINTS

• Iterative reconstruction algorithm impacts image texture, with negative effects on diagnostic capabilities. • Medium-strength deep learning image reconstruction algorithm outperforms iterative reconstruction in the diagnostic accuracy of ≤ 0.5 cm hypovascular liver lesions (93.9% vs 78.8%), also granting higher objective and subjective image quality. • Deep learning image reconstruction algorithm can be safely implemented in routine abdominal CT protocols in place of iterative reconstruction.

A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy

The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.

Exploring the Low-Dose Limit for Focal Hepatic Lesion Detection with a Deep Learning-Based CT Reconstruction Algorithm: A Simulation Study on Patient Images

This study aims to investigate the maximum achievable dose reduction for applying a new deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in computed tomography (CT) for hepatic lesion detection. A total of 40 patients with 98 clinically confirmed hepatic lesions were retrospectively included. The mean volume CT dose index was 13.66 ± 1.73 mGy in routine-dose portal venous CT examinations, where the images were originally obtained with hybrid iterative reconstruction (HIR). Low-dose simulations were performed in projection domain for 40%-, 20%-, and 10%-dose levels, followed by reconstruction using both HIR and AIIR. Two radiologists were asked to detect hepatic lesion on each set of low-dose image in separate sessions. Qualitative metrics including lesion conspicuity, diagnostic confidence, and overall image quality were evaluated using a 5-point scale. The contrast-to-noise ratio (CNR) for lesion was also calculated for quantitative assessment. The lesion CNR on AIIR at reduced doses were significantly higher than that on routine-dose HIR (all p < 0.05). Lower qualitative image quality was observed as the radiation dose reduced, while there were no significant differences between 40%-dose AIIR and routine-dose HIR images. The lesion detection rate was 100%, 98% (96/98), and 73.5% (72/98) on 40%-, 20%-, and 10%-dose AIIR, respectively, whereas it was 98% (96/98), 73.5% (72/98), and 40% (39/98) on the corresponding low-dose HIR, respectively. AIIR outperformed HIR in simulated low-dose CT examinations of the liver. The use of AIIR allows up to 60% dose reduction for lesion detection while maintaining comparable image quality to routine-dose HIR.

Decreased levels of sex hormones in females with solitary pulmonary nodules were risk factors for malignancy

OBJECTIVE

The purpose of this research was to detect the relationship between the levels of sex hormones in females with solitary pulmonary nodules (SPNs) and their potential malignancies.

METHODS

A total of 187 consecutive patients with pathologically confirmed SPNs by chest CT were enrolled in our study. They were divided into two groups based on the pathologic findings of SPNs after surgery: benign and malignant SPNs. Progesterone (P), estradiol (E2), and testosterone (T) levels in the two groups were measured. Meanwhile, we used binary logistic regression analysis to analyze the risk factors for SPNs.

RESULTS

Of these 187 patients, 73 had benign SPNs, while 114 had malignant SPNs. We found that the levels of progesterone (P), estradiol (E2), and testosterone (T) were decreased significantly in patients with malignant SPNs compared to patients with benign SPNs (all P < 0.05). Multivariate logistic regression analysis revealed that second-hand smoke, burr sign, lobulation sign, pleural traction sign, vascular convergence sign, vacuole sign, and ≥ 1 cm nodules were independent risk factors for malignant pulmonary nodules in females.

CONCLUSIONS

Decreased levels of sex hormones in females were associated with malignant pulmonary nodules, suggesting that they can contribute to the diagnosis of lung cancer.

Organ dose prediction for patients undergoing radiotherapy CBCT chest examinations using artificial intelligence

PURPOSE

To propose an artificial intelligence (AI)-based method for personalized and real-time dosimetry for chest CBCT acquisitions.

METHODS

CT images from 113 patients who underwent radiotherapy treatment were collected for simulating thorax examinations using cone-beam computed tomography (CBCT) with the Monte Carlo technique. These simulations yielded organ dose data, used to train and validate specific AI algorithms. The efficacy of these AI algorithms was evaluated by comparing dose predictions with the actual doses derived from Monte Carlo simulations, which are the ground truth, utilizing Bland-Altman plots for this comparative analysis.

RESULTS

The absolute mean discrepancies between the predicted doses and the ground truth are (0.9 ± 1.3)% for bones, (1.2 ± 1.2)% for the esophagus, (0.5 ± 1.3)% for the breast, (2.5 ± 1.4)% for the heart, (2.4 ± 2.1)% for lungs, (0.8 ± 0.6)% for the skin, and (1.7 ± 0.7)% for integral. Meanwhile, the maximum discrepancies between the predicted doses and the ground truth are (14.4 ± 1.3)% for bones, (12.9 ± 1.2)% for the esophagus, (9.4 ± 1.3)% for the breast, (14.6 ± 1.4)% for the heart, (21.2 ± 2.1)% for lungs, (10.0 ± 0.6)% for the skin, and (10.5 ± 0.7)% for integral.

CONCLUSIONS

AI models that can make real-time predictions of the organ doses for patients undergoing CBCT thorax examinations as part of radiotherapy pre-treatment positioning were developed. The results of this study clearly show that the doses predicted by analyzed AI models are in close agreement with those calculated using Monte Carlo simulations.

Improving Image Quality and Nodule Characterization in Ultra-low-dose Lung CT with Deep Learning Image Reconstruction

RATIONALE AND OBJECTIVE

To investigate the influence of the deep learning image reconstruction (DLIR) on the image quality and quantitative analysis of pulmonary nodules under ultra-low dose lung CT conditions.

MATERIALS AND METHODS

This was a prospective study with patient consent and included 56 patients with suspected pulmonary nodules. Patients were examined by both standard-dose CT (SDCT) and ultra-low-dose CT (ULDCT). SDCT images were reconstructed with adaptive statistical iterative reconstruction-V 40% (ASIR-V40%) (group A), while ULDCT images were reconstructed using ASIR-V40% (group B) and high-strength DLIR (DLIR-H) (group C). The three image sets were analyzed using a commercial computer aided diagnosis (CAD) software. Parameters such as nodule length, width, density, volume, risk, and classification were measured. The CAD quantitative data of different nodule types (solid, calcified, and subsolid nodules) and nodule image quality scores evaluated by two physicians on a 5-point scale were compared.

RESULT

The radiation dose in ULDCT was 0.25 ± 0.08mSv, 7.2% that of the 3.48 ± 1.08mSv in SDCT (P < 0.001). 104 pulmonary nodules were detected (51/53 solid, 26/24 calcified and 27/27 subsolid in Groups A and (B&C), respectively). Group B had lower density for solid, calcified nodules, and lower volume and risk for subsolid nodules than Group A, while Group C had lower density for calcified nodules (P < 0.05), There were no significant differences in other parameters among the three groups (P > 0.05). Group A and C had similar image quality for nodules and were higher than Group B (P < 0.05).

CONCLUSION

DLIR-H significantly improves image quality than ASIR-V40% and maintains similar nodule detection and characterization with CAD in ULDCT compared to SDCT.

Prospective evaluation of deep learning image reconstruction for Lung-RADS and automatic nodule volumetry on ultralow-dose chest CT

PURPOSE

To prospectively evaluate whether Lung-RADS classification and volumetric nodule assessment were feasible with ultralow-dose (ULD) chest CT scans with deep learning image reconstruction (DLIR).

METHODS

The institutional review board approved this prospective study. This study included 40 patients (mean age, 66±12 years; 21 women). Participants sequentially underwent LDCT and ULDCT (CTDIvol, 0.96±0.15 mGy and 0.12±0.01 mGy) scans reconstructed with the adaptive statistical iterative reconstruction-V 50% (ASIR-V50) and DLIR. CT image quality was compared subjectively and objectively. The pulmonary nodules were assessed visually by two readers using the Lung-RADS 1.1 and automatically using a computerized assisted tool.

RESULTS

DLIR provided a significantly higher signal-to-noise ratio for LDCT and ULDCT images than ASIR-V50 (all P < .001). In general, DLIR showed superior subjective image quality for ULDCT images (P < .001) and comparable quality for LDCT images compared to ASIR-V50 (P = .01-1). The per-nodule sensitivities of observers for Lung-RADS category 3-4 nodules were 70.6-88.2% and 64.7-82.4% for DLIR-LDCT and DLIR-ULDCT images (P = 1) and categories were mostly concordant within observers. The per-nodule sensitivities of the computer-assisted detection for nodules ≥4 mm were 72.1% and 67.4% on DLIR-LDCT and ULDCT images (P = .50). The 95% limits of agreement for nodule volume differences between DLIR-LDCT and ULDCT images (-85.6 to 78.7 mm3) was similar to the within-scan nodule volume differences between DLIR- and ASIR-V50-LDCT images (-63.9 to 78.5 mm3), with volume differences smaller than 25% in 88.5% and 92.3% of nodules, respectively (P = .65).

CONCLUSION

DLIR enabled comparable Lung-RADS and volumetric nodule assessments on ULDCT images to LDCT images.

Ultra-low dose chest CT with silver filter and deep learning reconstruction significantly reduces radiation dose and retains quantitative information in the investigation and monitoring of lymphangioleiomyomatosis (LAM)

PURPOSE

Frequent CT scans to quantify lung involvement in cystic lung disease increases radiation exposure. Beam shaping energy filters can optimize imaging properties at lower radiation dosages. The aim of this study is to investigate whether use of SilverBeam filter and deep learning reconstruction algorithm allows for reduced radiation dose chest CT scanning in patients with lymphangioleiomyomatosis (LAM).

MATERIAL AND METHODS

In a single-center prospective study, 60 consecutive patients with LAM underwent chest CT at standard and ultra-low radiation doses. Standard dose scan was performed with standard copper filter and ultra-low dose scan was performed with SilverBeam filter. Scans were reconstructed using a soft tissue kernel with deep learning reconstruction (AiCE) technique and using a soft tissue kernel with hybrid iterative reconstruction (AIDR3D). Cyst scores were quantified by semi-automated software. Signal-to-noise ratio (SNR) was calculated for each reconstruction. Data were analyzed by linear correlation, paired t-test, and Bland-Altman plots.

RESULTS

Patients averaged 49.4 years and 100% were female with mean BMI 26.6 ± 6.1 kg/m2. Cyst score measured by AiCE reconstruction with SilverBeam filter correlated well with that of AIDR3D reconstruction with standard filter, with a 1.5% difference, and allowed for an 85.5% median radiation dosage reduction (0.33 mSv vs. 2.27 mSv, respectively, p < 0.001). Compared to standard filter with AIDR3D, SNR for SilverBeam AiCE images was slightly lower (3.2 vs. 3.1, respectively, p = 0.005).

CONCLUSION

SilverBeam filter with deep learning reconstruction reduces radiation dosage of chest CT, while maintaining accuracy of cyst quantification as well as image quality in cystic lung disease.

CLINICAL RELEVANCE STATEMENT

Radiation dosage from chest CT can be significantly reduced without sacrificing image quality by using silver filter in combination with a deep learning reconstructive algorithm.

KEY POINTS

• Deep learning reconstruction in chest CT had no significant effect on cyst quantification when compared to conventional hybrid iterative reconstruction. • SilverBeam filter reduced radiation dosage by 85.5% compared to standard dose chest CT. • SilverBeam filter in coordination with deep learning reconstruction maintained image quality and diagnostic accuracy for cyst quantification when compared to standard dose CT with hybrid iterative reconstruction.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

Diagnostic CT of colorectal cancer with artificial intelligence iterative reconstruction: A clinical evaluation

OBJECTIVES

To investigate the clinical value of a novel deep-learning based CT reconstruction algorithm, artificial intelligence iterative reconstruction (AIIR), in diagnostic imaging of colorectal cancer (CRC).

METHODS

This study retrospectively enrolled 217 patients with pathologically confirmed CRC. CT images were reconstructed with the AIIR algorithm and compared with those originally obtained with hybrid iterative reconstruction (HIR). Objective image quality was evaluated in terms of the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Subjective image quality was graded on the conspicuity of tumor margin and enhancement pattern as well as the certainty in diagnosing organ invasion and regional lymphadenopathy. In patients with surgical pathology (n = 116), the performance of diagnosing visceral peritoneum invasion was characterized using receiver operating characteristic (ROC) analysis. Changes of diagnostic thinking in diagnosing hepatic metastases were assessed through lesion classification confidence.

RESULTS

The SNRs and CNRs on AIIR images were significantly higher than those on HIR images (all p < 0.001). The AIIR was scored higher for all subjective metrics (all p < 0.001) except for the certainty of diagnosing regional lymphadenopathy (p = 0.467). In diagnosing visceral peritoneum invasion, higher area under curve (AUC) of the ROC was found for AIIR than HIR (0.87 vs 0.77, p = 0.001). In assessing hepatic metastases, AIIR was found capable of correcting the misdiagnosis and improving the diagnostic confidence provided by HIR (p = 0.01).

CONCLUSIONS

Compared to HIR, AIIR offers better image quality, improves the diagnostic performance regarding CRC, and thus has the potential for application in routine abdominal CT.

Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window

OBJECTIVES

To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma.

METHODS

Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal-Wallis test with Bonferroni correction.

RESULTS

The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05).

CONCLUSION

LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR.

CLINICAL RELEVANCE STATEMENT

The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications.

KEY POINTS

• DLR enables LDCT maintaining image quality even with very low radiation doses. • Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation. • Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses.

Improved image quality in CT pulmonary angiography using deep learning-based image reconstruction

We investigated the effect of deep learning-based image reconstruction (DLIR) compared to iterative reconstruction on image quality in CT pulmonary angiography (CTPA) for suspected pulmonary embolism (PE). For 220 patients with suspected PE, CTPA studies were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction (ASiR-V 30%, 60% and 90%) and DLIR (low, medium and high strength). Contrast-to-noise ratio (CNR) served as the primary parameter of objective image quality. Subgroup analyses were performed for normal weight, overweight and obese individuals. For patients with confirmed PE (n = 40), we further measured PE-specific CNR. Subjective image quality was assessed independently by two experienced radiologists. CNR was lowest for FBP and enhanced with increasing levels of ASiR-V and, even more with increasing strength of DLIR. High strength DLIR resulted in an additional improvement in CNR by 29-67% compared to ASiR-V 90% (p < 0.05). PE-specific CNR increased by 75% compared to ASiR-V 90% (p < 0.05). Subjective image quality was significantly higher for medium and high strength DLIR compared to all other image reconstructions (p < 0.05). In CT pulmonary angiography, DLIR significantly outperforms iterative reconstruction for increasing objective and subjective image quality. This may allow for further reductions in radiation exposure in suspected PE.

Deep Learning-Based Reconstruction Improves the Image Quality of Low-Dose CT Colonography

RATIONALE AND OBJECTIVES

To evaluate the image quality of low-dose CT colonography (CTC) using deep learning-based reconstruction (DLR) compared to iterative reconstruction (IR).

MATERIALS AND METHODS

Adults included in the study were divided into four groups according to body mass index (BMI). Routine-dose (RD: 120 kVp) CTC images were reconstructed with IR (RD-IR); low-dose (LD: 100kVp) images were reconstructed with IR (LD-IR) and DLR (LD-DLR). The subjective image quality was rated on a 5-point scale by two radiologists independently. The parameters for objective image quality included noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The Friedman test was used to compare the image quality among RD-IR, LD-IR and LD-DLR. The KruskalWallis test was used to compare the results among different BMI groups.

RESULTS

A total of 270 volunteers (mean age: 47.94 years ± 11.57; 115 men) were included. The effective dose of low-dose CTC was decreased by approximately 83.18% (5.18mSv ± 0.86 vs. 0.86mSv ± 0.05, P < 0.001). The subjective image quality score of LD-DLR was superior to that of LD-IR (3.61 ± 0.56 vs. 2.70 ± 0.51, P < 0.001) and on par with the RD- IR's (3.61 ± 0.56 vs. 3.74 ± 0.52, P = 0.486). LD-DLR exhibited the lowest noise, and the maximum SNR and CNR compared to RD-IR and LD-IR (all P < 0.001). No statistical difference was found in the noise of LD-DLR images between different BMI groups (all P > 0.05).

CONCLUSION

Compared to IR, DLR provided low-dose CTC with superior image quality at an average radiation dose of 0.86mSv, which may be promising in future colorectal cancer screening.

A Novel Automatic Algorithm to Support Lung Ultrasound Non-Expert Physicians in Interstitial Pneumonia Evaluation: A Single-Center Study

INTRODUCTION

Lung ultrasound (LUS) is widely used in clinical practice for identifying interstitial lung diseases (ILDs) and assessing their progression. Although high-resolution computed tomography (HRCT) remains the gold standard for evaluating the severity of ILDs, LUS can be performed as a screening method or as a follow-up tool post-HRCT. Minimum training is needed to better identify typical lesions, and the integration of innovative artificial intelligence (AI) automatic algorithms may enhance diagnostic efficiency.

AIM

This study aims to assess the effectiveness of a novel AI algorithm in automatic ILD recognition and scoring in comparison to an expert LUS sonographer. The "SensUS Lung" device, equipped with an automatic algorithm, was employed for the automatic recognition of the typical ILD patterns and to calculate an index grading of the interstitial involvement.

METHODS

We selected 33 Caucasian patients in follow-up for ILDs exhibiting typical HRCT patterns (honeycombing, ground glass, fibrosis). An expert physician evaluated all patients with LUS on twelve segments (six per side). Next, blinded to the previous evaluation, an untrained operator, a non-expert in LUS, performed the exam with the SensUS device equipped with the automatic algorithm ("SensUS Lung") using the same protocol. Pulmonary functional tests (PFT) and DLCO were conducted for all patients, categorizing them as having reduced or preserved DLCO. The SensUS device indicated different grades of interstitial involvement named Lung Staging that were scored from 0 (absent) to 4 (peak), which was compared to the Lung Ultrasound Score (LUS score) by dividing it by the number of segments evaluated. Statistical analyses were done with Wilcoxon tests for paired values or Mann-Whitney for unpaired samples, and correlations were performed using Spearman analysis; p < 0.05 was considered significant.

RESULTS

Lung Staging was non-inferior to LUS score in identifying the risk of ILDs (median SensUS 1 [0-2] vs. LUS 0.67 [0.25-1.54]; p = 0.84). Furthermore, the grade of interstitial pulmonary involvement detected with the SensUS device is directly related to the LUS score (r = 0.607, p = 0.002). Lung Staging values were inversely correlated with forced expiratory volume at first second (FEV1%, r = -0.40, p = 0.027), forced vital capacity (FVC%, r = -0.39, p = 0.03) and forced expiratory flow (FEF) at 25th percentile (FEF25%, r = -0.39, p = 0.02) while results directly correlated with FEF25-75% (r = 0.45, p = 0.04) and FEF75% (r = 0.43, p = 0.01). Finally, in patients with reduced DLCO, the Lung Staging was significantly higher, overlapping the LUS (reduced median 1 [1-2] vs. preserved 0 [0-1], p = 0.001), and overlapping the LUS (reduced median 18 [4-20] vs. preserved 5.5 [2-9], p = 0.035).

CONCLUSIONS

Our data suggest that the considered AI automatic algorithm may assist non-expert physicians in LUS, resulting in non-inferior-to-expert LUS despite a tendency to overestimate ILD lesions. Therefore, the AI algorithm has the potential to support physicians, particularly non-expert LUS sonographers, in daily clinical practice to monitor patients with ILDs. The adopted device is user-friendly, offering a fully automatic real-time analysis. However, it needs proper training in basic skills.

Fully automated artificial intelligence-based coronary CT angiography image processing: efficiency, diagnostic capability, and risk stratification

OBJECTIVES

To prospectively investigate whether fully automated artificial intelligence (FAAI)-based coronary CT angiography (CCTA) image processing is non-inferior to semi-automated mode in efficiency, diagnostic ability, and risk stratification of coronary artery disease (CAD).

MATERIALS AND METHODS

Adults with indications for CCTA were prospectively and consecutively enrolled at two hospitals and randomly assigned to either FAAI-based or semi-automated image processing using equipment workstations. Outcome measures were workflow efficiency, diagnostic accuracy for obstructive CAD (≥ 50% stenosis), and cardiovascular events at 2-year follow-up. The endpoints included major adverse cardiovascular events, hospitalization for unstable angina, and recurrence of cardiac symptoms. The non-inferiority margin was 3 percentage difference in diagnostic accuracy and C-index.

RESULTS

In total, 1801 subjects (62.7 ± 11.1 years) were included, of whom 893 and 908 were assigned to the FAAI-based and semi-automated modes, respectively. Image processing times were 121.0 ± 18.6 and 433.5 ± 68.4 s, respectively (p <0.001). Scan-to-report release times were 6.4 ± 2.7 and 10.5 ± 3.8 h, respectively (p < 0.001). Of all subjects, 152 and 159 in the FAAI-based and semi-automated modes, respectively, subsequently underwent invasive coronary angiography. The diagnostic accuracies for obstructive CAD were 94.7% (89.9-97.7%) and 94.3% (89.5-97.4%), respectively (difference 0.4%). Of all subjects, 779 and 784 in the FAAI-based and semi-automated modes were followed for 589 ± 182 days, respectively, and the C-statistic for cardiovascular events were 0.75 (0.67 to 0.83) and 0.74 (0.66 to 0.82) (difference 1%).

CONCLUSIONS

FAAI-based CCTA image processing significantly improves workflow efficiency than semi-automated mode, and is non-inferior in diagnosing obstructive CAD and risk stratification for cardiovascular events.

CLINICAL RELEVANCE STATEMENT

Conventional coronary CT angiography image processing is semi-automated. This observation shows that fully automated artificial intelligence-based image processing greatly improves efficiency, and maintains high diagnostic accuracy and the effectiveness in stratifying patients for cardiovascular events.

KEY POINTS

• Coronary CT angiography (CCTA) relies heavily on high-quality and fast image processing. • Full-automation CCTA image processing is clinically non-inferior to the semi-automated mode. • Full automation can facilitate the application of CCTA in early detection of coronary artery disease.

Assessing the effect of scanning parameter on the size and density of pulmonary nodules: a phantom study

BACKGROUND

Lung cancer remains a leading cause of death among cancer patients. Computed tomography (CT) plays a key role in lung cancer screening. Previous studies have not adequately quantified the effect of scanning protocols on the detected tumor size. The aim of this study was to assess the effect of various CT scanning parameters on tumor size and densitometry based on a phantom study and to investigate the optimal energy and mA image quality for screening assessment.

METHODS

We proposed a new model using the LUNGMAN N1 phantom multipurpose anthropomorphic chest phantom (diameters: 8, 10, and 12 mm; CT values: - 100, - 630, and - 800 HU) to evaluate the influence of changes in tube voltage and tube current on the size and density of pulmonary nodules. In the LUNGMAN N1 model, three types of simulated lung nodules representing solid tumors of different sizes were used. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were used to evaluate the image quality of each scanning combination. The consistency between the calculated results based on segmentation from two physicists was evaluated using the interclass correlation coefficient (ICC).

RESULTS

In terms of nodule size, the longest diameters of ground-glass nodules (GGNs) were closest to the ground truth on the images measured at 100 kVp tube voltage, and the longest diameters of solid nodules were closest to the ground truth on the images measured at 80 kVp tube voltage. In respect to density, the CT values of GGNs and solid nodules were closest to the ground truth when measured at 80 kVp and 100 kVp tube voltage, respectively. The overall agreement demonstrates that the measurements were consistent between the two physicists.

CONCLUSIONS

Our proposed model demonstrated that a combination of 80 kVp and 140 mA scans was preferred for measuring the size of the solid nodules, and a combination of 100 kVp and 100 mA scans was preferred for measuring the size of the GGNs when performing lung cancer screening. The CT values at 80 kVp and 100 kVp were preferred for the measurement of GGNs and solid nodules, respectively, which were closest to the true CT values of the nodules. Therefore, the combination of scanning parameters should be selected for different types of nodules to obtain more accurate nodal data.

Overdiagnosis and overtreatment of ground-glass nodule-like lung cancer

Lung cancer has had one of the highest incidences and mortality in the world over the last few decades, which has aided in the promotion and popularization of screening for lung ground-glass nodules (GGNs). People have great psychological anxiety about GGN because of the chance that it will develop into lung cancer, which makes clinical treatment of GGN a generally excessive phenomenon. Overdiagnosis in screening has recently been mentioned in the literature. An important research emphasis of screening is how to reduce the incidence of overdiagnosis and overtreatment. This paper discusses from different aspects how to characterize the occurrence of overdiagnosis and overtreatment, how to reduce overdiagnosis and overtreatment, and future screening, follow-up, and treatment approaches.

Deep learning reconstruction CT for liver metastases: low-dose dual-energy vs standard-dose single-energy

OBJECTIVES

To assess image quality and liver metastasis detection of reduced-dose dual-energy CT (DECT) with deep learning image reconstruction (DLIR) compared to standard-dose single-energy CT (SECT) with DLIR or iterative reconstruction (IR).

METHODS

In this prospective study, two groups of 40 participants each underwent abdominal contrast-enhanced scans with full-dose SECT (120-kVp images, DLIR and IR algorithms) or reduced-dose DECT (40- to 60-keV virtual monochromatic images [VMIs], DLIR algorithm), with 122 and 106 metastases, respectively. Groups were matched by age, sex ratio, body mass index, and cross-sectional area. Noise power spectrum of liver images and task-based transfer function of metastases were calculated to assess the noise texture and low-contrast resolution. The image noise, signal-to-noise ratios (SNR) of liver and portal vein, liver-to-lesion contrast-to-noise ratio (LLR), lesion conspicuity, lesion detection rate, and the subjective image quality metrics were compared between groups on 1.25-mm reconstructed images.

RESULTS

Compared to 120-kVp images with IR, 40- and 50-keV VMIs with DLIR showed similar noise texture and LLR, similar or higher image noise and low-contrast resolution, improved SNR and lesion conspicuity, and similar or better perceptual image quality. When compared to 120-kVp images with DLIR, 50-keV VMIs with DLIR had similar low-contrast resolution, SNR, LLR, lesion conspicuity, and perceptual image quality but lower frequency noise texture and higher image noise. For the detection of hepatic metastases, reduced-dose DECT by 34% maintained observer lesion detection rates.

CONCLUSION

DECT assisted with DLIR enables a 34% dose reduction for detecting hepatic metastases while maintaining comparable perceptual image quality to full-dose SECT.

CLINICAL RELEVANCE STATEMENT

Reduced-dose dual-energy CT with deep learning image reconstruction is as accurate as standard-dose single-energy CT for the detection of liver metastases and saves more than 30% of the radiation dose.

KEY POINTS

• The 40- and 50-keV virtual monochromatic images (VMIs) with deep learning image reconstruction (DLIR) improved lesion conspicuity compared with 120-kVp images with iterative reconstruction while providing similar or better perceptual image quality. • The 50-keV VMIs with DLIR provided comparable perceptual image quality and lesion conspicuity to 120-kVp images with DLIR. • The reduction of radiation by 34% by DLIR in low-keV VMIs is clinically sufficient for detecting low-contrast hepatic metastases.

Effectiveness of deep learning reconstruction on standard to ultra-low-dose high-definition chest CT images

PURPOSE

Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT examinations of a variety of organs, and compared with other reconstruction methods. The purpose of this study was to compare the capabilities of DLR for image quality improvement and lung texture evaluation with those of hybrid-type iterative reconstruction (IR) for standard-, reduced- and ultra-low-dose CTs (SDCT, RDCT and ULDCT) obtained with high-definition CT (HDCT) and reconstructed at 0.25-mm, 0.5-mm and 1-mm section thicknesses with 512 × 512 or 1024 × 1024 matrixes for patients with various pulmonary diseases.

MATERIALS AND METHODS

Forty age-, gender- and body mass index-matched patients with various pulmonary diseases underwent SDCT (CT dose index volume : mean ± standard deviation, 9.0 ± 1.8 mGy), RDCT (CTDIvol: 1.7 ± 0.2 mGy) and ULDCT (CTDIvol: 0.8 ± 0.1 mGy) at a HDCT. All CT data set were then reconstructed with 512 × 512 or 1024 × 1024 matrixes by means of hybrid-type IR and DLR. SNR of lung parenchyma and probabilities of all lung textures were assessed for each CT data set. SNR and detection performance of each lung texture reconstructed with DLR and hybrid-type IR were then compared by means of paired t tests and ROC analyses for all CT data at each section thickness.

RESULTS

Data for each radiation dose showed DLR attained significantly higher SNR than hybrid-type IR for each of the CT data (p < 0.0001). On assessments of all findings except consolidation and nodules or masses, areas under the curve (AUCs) for ULDCT with hybrid-type IR for each section thickness (0.91 ≤ AUC ≤ 0.97) were significantly smaller than those with DLR (0.97 ≤ AUC ≤ 1, p < 0.05) and the standard protocol (0.98 ≤ AUC ≤ 1, p < 0.05).

CONCLUSION

DLR is potentially more effective for image quality improvement and lung texture evaluation than hybrid-type IR on all radiation dose CTs obtained at HDCT and reconstructed with each section thickness with both matrixes for patients with a variety of pulmonary diseases.

Artificial Intelligence and Machine Learning in Lung Cancer Screening

Recent advances in artificial intelligence and machine learning (AI/ML) hold substantial promise to address some of the current challenges in lung cancer screening and improve health equity. This article reviews the status and future directions of AI/ML tools in the lung cancer screening workflow, focusing on determining screening eligibility, radiation dose reduction and image denoising for low-dose chest computed tomography (CT), lung nodule detection, lung nodule classification, and determining optimal screening intervals. AI/ML tools can assess for chronic diseases on CT, which creates opportunities to improve population health through opportunistic screening.

Chromosome classification via deep learning and its application to patients with structural abnormalities of chromosomes

BACKGROUND AND OBJECTIVE

Karyotyping is an important technique in cytogenetic practice for the early diagnosis of genetic diseases. Clinical karyotyping is tedious, time-consuming, and error-prone. The objective of our study was to develop a single-stage deep convolutional neural networks (DCNN)-based model to automatically classify normal and abnormal chromosomes in an end-to-end manner.

METHODS

We analyzed 2,424 normal chromosomes and 544 abnormal chromosomes. A preliminary support vector machine (SVM) model was developed to evaluate the basic recognition performance on the dataset. A DCNN-based model was then proposed to process the same dataset.

RESULTS

By utilizing the SVM model, the classification accuracy of 24 normal chromosomes was 86.01 %. The 32 types of normal and abnormal chromosomes got an accuracy of 85.37 %. The accuracy of the DCNN-based model performing the 24 normal chromosomal classification was 91.75 %. The accuracy of the 32 type classification was 87.76 %. To differentiate eight common structural abnormalities, we obtained accuracies that ranged from 90.84 % to 100 %, and the values of the AUC ranged from 91.81 % to 100 %.

CONCLUSIONS

Our proposed DCNN-based model effectively performed the karyotype classification in an end-to-end manner. It had the competence to be used as a prediction tool for abnormal karyotype detection and screening in genetic diagnosis without initial feature extraction. We believe our work is meaningful for genetic triage management to lower the cost in clinical practice.

PB-LNet: a model for predicting pathological subtypes of pulmonary nodules on CT images

OBJECTIVE

To investigate the correlation between CT imaging features and pathological subtypes of pulmonary nodules and construct a prediction model using deep learning.

METHODS

We collected information of patients with pulmonary nodules treated by surgery and the reference standard for diagnosis was post-operative pathology. After using elastic distortion for data augmentation, the CT images were divided into a training set, a validation set and a test set in a ratio of 6:2:2. We used PB-LNet to analyze the nodules in pre-operative CT and predict their pathological subtypes. Accuracy was used as the model evaluation index and Class Activation Map was applied to interpreting the results. Comparative experiments with other models were carried out to achieve the best results. Finally, images from the test set without data augmentation were analyzed to judge the clinical utility.

RESULTS

Four hundred seventy-seven patients were included and the nodules were divided into six groups: benign lesions, precursor glandular lesions, minimally invasive adenocarcinoma, invasive adenocarcinoma Grade 1, Grade 2 and Grade 3. The accuracy of the test set was 0.84. Class Activation Map confirmed that PB-LNet classified the nodules mainly based on the lungs in CT images, which is in line with the actual situation in clinical practice. In comparative experiments, PB-LNet obtained the highest accuracy. Finally, 96 images from the test set without data augmentation were analyzed and the accuracy was 0.89.

CONCLUSIONS

In classifying CT images of lung nodules into six categories based on pathological subtypes, PB-LNet demonstrates satisfactory accuracy without the need of delineating nodules, while the results are interpretable. A high level of accuracy was also obtained when validating on real data, therefore demonstrates its usefulness in clinical practice.

[18F]FDG PET/MRI combined with chest HRCT in early cancer detection: a retrospective study of 3020 asymptomatic subjects

PURPOSE

PET/MRI has become an important medical imaging approach in clinical practice. In this study, we retrospectively investigated the detectability of fluorine-18 (18F)-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging ([18F]FDG PET/MRI) combined with chest computerized tomography (CT) for early cancer in a large cohort of asymptomatic subjects.

METHODS

This study included a total of 3020 asymptomatic subjects who underwent whole-body [18F]FDG PET/MRI and chest HRCT examinations. All subjects received a 2-4-year follow-up for cancer development. Cancer detection rate, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the [18F]FDG PET/MRI with or without chest HRCT were calculated and analyzed.

RESULTS

Sixty-one subjects were pathologically diagnosed with cancers, among which 59 were correctly detected by [18F]FDG PET/MRI combined with chest HRCT. Of the 59 patients (32 with lung cancer, 9 with breast cancer, 6 with thyroid cancer, 5 with colon cancer, 3 with renal cancer, 1 with prostate cancer, 1 with gastric cancer, 1 with endometrial cancer, and 1 with lymphoma), 54 (91.5%) were at stage 0 or stage I (according to the 8th edition of the tumor-node-metastasis [TNM] staging system), 33 (55.9%) were detected by PET/MRI alone (27 with non-lung cancers and 6 with lung cancer). Cancer detection rate, sensitivity, specificity, PPV, and NPV for PET/MRI combined with chest CT were 2.0%, 96.7%, 99.6%, 83.1%, and 99.9%, respectively. For PET/MRI alone, the metrics were 1.1%, 54.1%, 99.6%, 73.3%, and 99.1%, respectively, and for PET/MRI in non-lung cancers, the metrics were 0.9%, 93.1%, 99.6%, 69.2%, and 99.9%, respectively.

CONCLUSIONS

[18F]FDG PET/MRI holds great promise for the early detection of non-lung cancers, while it seems insufficient for detecting early-stage lung cancers. Chest HRCT can be complementary to whole-body PET/MRI for early cancer detection.

TRIAL REGISTRATION

ChiCTR2200060041. Registered 16 May 2022. Public site: https://www.chictr.org.cn/index.html.

Application of Deep Learning for Prediction of Alzheimer's Disease in PET/MR Imaging

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide. Positron emission tomography/magnetic resonance (PET/MR) imaging is a promising technique that combines the advantages of PET and MR to provide both functional and structural information of the brain. Deep learning (DL) is a subfield of machine learning (ML) and artificial intelligence (AI) that focuses on developing algorithms and models inspired by the structure and function of the human brain's neural networks. DL has been applied to various aspects of PET/MR imaging in AD, such as image segmentation, image reconstruction, diagnosis and prediction, and visualization of pathological features. In this review, we introduce the basic concepts and types of DL algorithms, such as feed forward neural networks, convolutional neural networks, recurrent neural networks, and autoencoders. We then summarize the current applications and challenges of DL in PET/MR imaging in AD, and discuss the future directions and opportunities for automated diagnosis, predictions of models, and personalized medicine. We conclude that DL has great potential to improve the quality and efficiency of PET/MR imaging in AD, and to provide new insights into the pathophysiology and treatment of this devastating disease.

75% radiation dose reduction using deep learning reconstruction on low-dose chest CT

OBJECTIVE

Few studies have explored the clinical feasibility of using deep-learning reconstruction to reduce the radiation dose of CT. We aimed to compare the image quality and lung nodule detectability between chest CT using a quarter of the low dose (QLD) reconstructed with vendor-agnostic deep-learning image reconstruction (DLIR) and conventional low-dose (LD) CT reconstructed with iterative reconstruction (IR).

MATERIALS AND METHODS

We retrospectively collected 100 patients (median age, 61 years [IQR, 53-70 years]) who received LDCT using a dual-source scanner, where total radiation was split into a 1:3 ratio. QLD CT was generated using a quarter dose and reconstructed with DLIR (QLD-DLIR), while LDCT images were generated using a full dose and reconstructed with IR (LD-IR). Three thoracic radiologists reviewed subjective noise, spatial resolution, and overall image quality, and image noise was measured in five areas. The radiologists were also asked to detect all Lung-RADS category 3 or 4 nodules, and their performance was evaluated using area under the jackknife free-response receiver operating characteristic curve (AUFROC).

RESULTS

The median effective dose was 0.16 (IQR, 0.14-0.18) mSv for QLD CT and 0.65 (IQR, 0.57-0.71) mSv for LDCT. The radiologists' evaluations showed no significant differences in subjective noise (QLD-DLIR vs. LD-IR, lung-window setting; 3.23 ± 0.19 vs. 3.27 ± 0.22; P = .11), spatial resolution (3.14 ± 0.28 vs. 3.16 ± 0.27; P = .12), and overall image quality (3.14 ± 0.21 vs. 3.17 ± 0.17; P = .15). QLD-DLIR demonstrated lower measured noise than LD-IR in most areas (P < .001 for all). No significant difference was found between QLD-DLIR and LD-IR for the sensitivity (76.4% vs. 72.2%; P = .35) or the AUFROCs (0.77 vs. 0.78; P = .68) in detecting Lung-RADS category 3 or 4 nodules. Under a noninferiority limit of -0.1, QLD-DLIR showed noninferior detection performance (95% CI for AUFROC difference, -0.04 to 0.06).

CONCLUSION

QLD-DLIR images showed comparable image quality and noninferior nodule detectability relative to LD-IR images.

Supervised Learning for CT Denoising and Deconvolution Without High-Resolution Reference Images

Purpose

Convolutional neural networks (CNNs) have been proposed for super-resolution in CT, but training of CNNs requires high-resolution reference data. Higher spatial resolution can also be achieved using deconvolution, but conventional deconvolution approaches amplify noise. We develop a CNN that mitigates increasing noise and that does not require higher-resolution reference images.

Methods

Our model includes a noise reduction CNN and a deconvolution CNN that are separately trained. The noise reduction CNN is a U-Net, similar to other noise reduction CNNs found in the literature. The deconvolution CNN uses an autoencoder, where the decoder is fixed and provided as a hyperparameter that represents the system point spread function. The encoder is trained to provide a deconvolution that does not amplify noise. Ringing can occur from deconvolution but is controlled with a difference of gradients loss function term. Our technique was demonstrated on a variety of patient images and on ex vivo kidney stones.

Results

The noise reduction and deconvolution CNNs produced visually sharper images at low noise. In ex vivo mixed kidney stones, better visual delineation of the kidney stone components could be seen.

Conclusions

A noise reduction and deconvolution CNN improves spatial resolution and reduces noise without requiring higher-resolution reference images.

Deep learning assisted diagnosis system: improving the diagnostic accuracy of distal radius fractures

Objectives

To explore an intelligent detection technology based on deep learning algorithms to assist the clinical diagnosis of distal radius fractures (DRFs), and further compare it with human performance to verify the feasibility of this method.

Methods

A total of 3,240 patients (fracture: n = 1,620, normal: n = 1,620) were included in this study, with a total of 3,276 wrist joint anteroposterior (AP) X-ray films (1,639 fractured, 1,637 normal) and 3,260 wrist joint lateral X-ray films (1,623 fractured, 1,637 normal). We divided the patients into training set, validation set and test set in a ratio of 7:1.5:1.5. The deep learning models were developed using the data from the training and validation sets, and then their effectiveness were evaluated using the data from the test set. Evaluate the diagnostic performance of deep learning models using receiver operating characteristic (ROC) curves and area under the curve (AUC), accuracy, sensitivity, and specificity, and compare them with medical professionals.

Results

The deep learning ensemble model had excellent accuracy (97.03%), sensitivity (95.70%), and specificity (98.37%) in detecting DRFs. Among them, the accuracy of the AP view was 97.75%, the sensitivity 97.13%, and the specificity 98.37%; the accuracy of the lateral view was 96.32%, the sensitivity 94.26%, and the specificity 98.37%. When the wrist joint is counted, the accuracy was 97.55%, the sensitivity 98.36%, and the specificity 96.73%. In terms of these variables, the performance of the ensemble model is superior to that of both the orthopedic attending physician group and the radiology attending physician group.

Conclusion

This deep learning ensemble model has excellent performance in detecting DRFs on plain X-ray films. Using this artificial intelligence model as a second expert to assist clinical diagnosis is expected to improve the accuracy of diagnosing DRFs and enhance clinical work efficiency.

Clinical and radiological characteristics of pediatric COVID-19 before and after the Omicron outbreak: a multi-center study

Introduction

The emergence of the Omicron variant has seen changes in the clinical and radiological presentations of COVID-19 in pediatric patients. We sought to compare these features between patients infected in the early phase of the pandemic and those during the Omicron outbreak.

Methods

A retrospective study was conducted on 68 pediatric COVID-19 patients, of which 31 were infected with the original SARS-CoV-2 strain (original group) and 37 with the Omicron variant (Omicron group). Clinical symptoms and chest CT scans were examined to assess clinical characteristics, and the extent and severity of lung involvement.

Results

Pediatric COVID-19 patients predominantly had normal or mild chest CT findings. The Omicron group demonstrated a significantly reduced CT severity score than the original group. Ground-glass opacities were the prevalent radiological findings in both sets. The Omicron group presented with fewer symptoms, had milder clinical manifestations, and recovered faster than the original group.

Discussion

The clinical and radiological characteristics of pediatric COVID-19 patients have evolved with the advent of the Omicron variant. For children displaying severe symptoms warranting CT examinations, it is crucial to weigh the implications of ionizing radiation and employ customized scanning protocols and protective measures. This research offers insights into the shifting disease spectrum, aiding in the effective diagnosis and treatment of pediatric COVID-19 patients.

Lung Cancer Screening with Low-Dose CT: What We Have Learned in Two Decades of ITALUNG and What Is Yet to Be Addressed

The ITALUNG trial started in 2004 and compared lung cancer (LC) and other-causes mortality in 55-69 years-aged smokers and ex-smokers who were randomized to four annual chest low-dose CT (LDCT) or usual care. ITALUNG showed a lower LC and cardiovascular mortality in the screened subjects after 13 years of follow-up, especially in women, and produced many ancillary studies. They included recruitment results of a population-based mimicking approach, development of software for computer-aided diagnosis (CAD) and lung nodules volumetry, LDCT assessment of pulmonary emphysema and coronary artery calcifications (CAC) and their relevance to long-term mortality, results of a smoking-cessation intervention, assessment of the radiations dose associated with screening LDCT, and the results of biomarkers assays. Moreover, ITALUNG data indicated that screen-detected LCs are mostly already present at baseline LDCT, can present as lung cancer associated with cystic airspaces, and can be multiple. However, several issues of LC screening are still unaddressed. They include the annual vs. biennial pace of LDCT, choice between opportunistic or population-based recruitment. and between uni or multi-centre screening, implementation of CAD-assisted reading, containment of false positive and negative LDCT results, incorporation of emphysema. and CAC quantification in models of personalized LC and mortality risk, validation of ultra-LDCT acquisitions, optimization of the smoking-cessation intervention. and prospective validation of the biomarkers.

Accuracy of Nodule Volume and Airway Wall Thickness Measurement Using Low-Dose Chest CT on a Photon-Counting Detector CT Scanner

OBJECTIVES

A comparison of high-resolution photon-counting detector computed tomography (PCD-CT) versus energy-integrating detector (EID) CT via a phantom study using low-dose chest CT to evaluate nodule volume and airway wall thickness quantification.

MATERIALS AND METHODS

Twelve solid and ground-glass lung nodule phantoms with 3 diameters (5 mm, 8 mm, and 10 mm) and 2 shapes (spherical and star-shaped) and 12 airway tube phantoms (wall thicknesses, 0.27-1.54 mm) were placed in an anthropomorphic chest phantom. The phantom was scanned with EID-CT and PCD-CT at 5 dose levels (CTDI vol = 0.1-0.8 mGy at Sn-100 kV, 7.35 mGy at 120 kV). All images were iteratively reconstructed using matched kernels for EID-CT and medium-sharp kernel (MK) PCD-CT and an ultra-sharp kernel (USK) PCD-CT kernel, and image noise at each dose level was quantified. Nodule volumes were measured using semiautomated segmentation software, and the accuracy was expressed as the percentage error between segmented and reference volumes. Airway wall thicknesses were measured, and the root-mean-square error across all tubes was evaluated.

RESULTS

MK PCD-CT images had the lowest noise. At 0.1 mGy, the mean volume accuracy for the solid and ground-glass nodules was improved in USK PCD-CT (3.1% and 3.3% error) compared with MK PCD-CT (9.9% and 10.2% error) and EID-CT images (11.4% and 9.2% error), respectively. At 0.2 mGy and 0.8 mGy, the wall thickness root-mean-square error values were 0.42 mm and 0.41 mm for EID-CT, 0.54 mm and 0.49 mm for MK PCD-CT, and 0.23 mm and 0.16 mm for USK PCD-CT.

CONCLUSIONS

USK PCD-CT provided more accurate lung nodule volume and airway wall thickness quantification at lower radiation dose compared with MK PCD-CT and EID-CT.

Ultra-low dose computed tomography protocols using spectral shaping for lung cancer screening: Comparison with low-dose for volumetric LungRADS classification

PURPOSE

To compare Low-Dose Computed Tomography (LDCT) with four different Ultra-Low-Dose Computed Tomography (ULDCT) protocols for PN classification according to the Lung Reporting and Data System (LungRADS).

METHODS

Three hundred sixty-one participants of an ongoing lung cancer screening (LCS) underwent single-breath-hold double chest Computed Tomography (CT), including LDCT (120kVp, 25mAs; CTDIvol 1,62 mGy) and one ULDCT among: fully automated exposure control ("ULDCT₁"); fixed tube-voltage and current according to patient size ("ULDCT₂"); hybrid approach with fixed tube-voltage ("ULDCT₃") and tube current automated exposure control ("ULDCT₄"). Two radiologists (R1, R2) assessed LungRADS 2022 categories on LDCT, and then after 2 weeks on ULDCT using two different kernels (R1: Qr49_{ADMIRE 4}; R2: Br49_{ADMIRE 3}). Intra-subject agreement for LungRADS categories between LDCT and ULDCT was measured by the k-Cohen Index with Fleiss-Cohen weights.

RESULTS

LDCT-dominant PNs were detected in ULDCT in 87 % of cases on Qr49_{ADMIRE 4} and 88 % on Br49_{ADMIRE 3}. The intra-subject agreement was: κULDCT₁ = 0.89 [95 %CI 0.82-0.96]; κULDCT₂ = 0.90 [0.81-0.98]; κULDCT₃ = 0.91 [0.84-0.99]; κULDCT₄ = 0.88 [0.78-0.97] on Qr49_{ADMIRE 4}, and κULDCT₁ = 0.88 [0.80-0.95]; κULDCT₂ = 0.91 [0.86-0.96]; κULDCT₃ = 0.87 [0.78-0.95]; and κULDCT₄ = 0.88 [0.82-0.94] on Br49_{ADMIRE 3}. LDCT classified as LungRADS 4B were correctly identified as LungRADS 4B at ULDCT₃, with the lowest radiation exposure among the tested protocols (median effective doses were 0.31, 0.36, 0.27 and 0.37 mSv for ULDCT₁, ULDCT₂, ULDCT₃, and ULDCT₄, respectively).

CONCLUSIONS

ULDCT by spectral shaping allows the detection and characterization of PNs with an excellent agreement with LDCT and can be proposed as a feasible approach in LCS.

Evaluation of deep-learning image reconstruction for chest CT examinations at two different dose levels

AIMS

The aims of the present study were to, for both a full-dose protocol and an ultra-low dose (ULD) protocol, compare the image quality of chest CT examinations reconstructed using TrueFidelity (Standard kernel) with corresponding examinations reconstructed using ASIR-V (Lung kernel) and to evaluate if post-processing using an edge-enhancement filter affects the noise level, spatial resolution and subjective image quality of clinical images reconstructed using TrueFidelity.

METHODS

A total of 25 patients were examined with both a full-dose protocol and an ULD protocol using a GE Revolution APEX CT system (GE Healthcare, Milwaukee, USA). Three different reconstructions were included in the study: ASIR-V 40%, DLIR-H, and DLIR-H with additional post-processing using an edge-enhancement filter (DLIR-H + E2). Five observers assessed image quality in two separate visual grading characteristics (VGC) studies. The results from the studies were statistically analyzed using VGC Analyzer. Quantitative evaluations were based on determination of two-dimensional power spectrum (PS), contrast-to-noise ratio (CNR), and spatial resolution in the reconstructed patient images.

RESULTS

For both protocols, examinations reconstructed using TrueFidelity were statistically rated equal to or significantly higher than examinations reconstructed using ASIR-V 40%, but the ULD protocol benefitted more from TrueFidelity. In general, no differences in observer ratings were found between DLIR-H and DLIR-H + E2. For the three investigated image reconstruction methods, ASIR-V 40% showed highest noise and spatial resolution and DLIR-H the lowest, while the CNR was highest in DLIR-H and lowest in ASIR-V 40%.

CONCLUSION

The use of TrueFidelity for image reconstruction resulted in higher ratings on subjective image quality than ASIR-V 40%. The benefit of using TrueFidelity was larger for the ULD protocol than for the full-dose protocol. Post-processing of the TrueFidelity images using an edge-enhancement filter resulted in higher image noise and spatial resolution but did not affect the subjective image quality.

Deep learning image reconstruction algorithm: impact on image quality in coronary computed tomography angiography

PURPOSE

To perform a comprehensive intraindividual objective and subjective image quality evaluation of coronary CT angiography (CCTA) reconstructed with deep learning image reconstruction (DLIR) and to assess correlation with routinely applied hybrid iterative reconstruction algorithm (ASiR-V).

MATERIAL AND METHODS

Fifty-one patients (29 males) undergoing clinically indicated CCTA from April to December 2021 were prospectively enrolled. Fourteen datasets were reconstructed for each patient: three DLIR strength levels (DLIR_L, DLIR_M, and DLIR_H), ASiR-V from 10% to 100% in 10%-increment, and filtered back-projection (FBP). Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) determined objective image quality. Subjective image quality was assessed with a 4-point Likert scale. Concordance between reconstruction algorithms was assessed by Pearson correlation coefficient.

RESULTS

DLIR algorithm did not impact vascular attenuation (P ≥ 0.374). DLIR_H showed the lowest noise, comparable with ASiR-V 100% (P = 1) and significantly lower than other reconstructions (P ≤ 0.021). DLIR_H achieved the highest objective quality, with SNR and CNR comparable to ASiR-V 100% (P = 0.139 and 0.075, respectively). DLIR_M obtained comparable objective image quality with ASiR-V 80% and 90% (P ≥ 0.281), while achieved the highest subjective image quality (4, IQR: 4-4; P ≤ 0.001). DLIR and ASiR-V datasets returned a very strong correlation in the assessment of CAD (r = 0.874, P = 0.001).

CONCLUSION

DLIR_M significantly improves CCTA image quality and has very strong correlation with routinely applied ASiR-V 50% dataset in the diagnosis of CAD.

Clinical Scores, Biomarkers and IT Tools in Lung Cancer Screening-Can an Integrated Approach Overcome Current Challenges?

As most lung cancer (LC) cases are still detected at advanced and incurable stages, there are increasing efforts to foster detection at earlier stages by low dose computed tomography (LDCT) based LC screening. In this scoping review, we describe current advances in candidate selection for screening (selection phase), technical aspects (screening), and probability evaluation of malignancy of CT-detected pulmonary nodules (PN management). Literature was non-systematically assessed and reviewed for suitability by the authors. For the selection phase, we describe current eligibility criteria for screening, along with their limitations and potential refinements through advanced clinical scores and biomarker assessments. For LC screening, we discuss how the accuracy of computerized tomography (CT) scan reading might be augmented by IT tools, helping radiologists to cope with increasing workloads. For PN management, we evaluate the precision of follow-up scans by semi-automatic volume measurements of CT-detected PN. Moreover, we present an integrative approach to evaluate the probability of PN malignancy to enable safe decisions on further management. As a clear limitation, additional validation studies are required for most innovative diagnostic approaches presented in this article, but the integration of clinical risk models, current imaging techniques, and advancing biomarker research has the potential to improve the LC screening performance generally.

Lung cancer screening

Randomised controlled trials, including the National Lung Screening Trial (NLST) and the NELSON trial, have shown reduced mortality with lung cancer screening with low-dose CT compared with chest radiography or no screening. Although research has provided clarity on key issues of lung cancer screening, uncertainty remains about aspects that might be critical to optimise clinical effectiveness and cost-effectiveness. This Review brings together current evidence on lung cancer screening, including an overview of clinical trials, considerations regarding the identification of individuals who benefit from lung cancer screening, management of screen-detected findings, smoking cessation interventions, cost-effectiveness, the role of artificial intelligence and biomarkers, and current challenges, solutions, and opportunities surrounding the implementation of lung cancer screening programmes from an international perspective. Further research into risk models for patient selection, personalised screening intervals, novel biomarkers, integrated cardiovascular disease and chronic obstructive pulmonary disease assessments, smoking cessation interventions, and artificial intelligence for lung nodule detection and risk stratification are key opportunities to increase the efficiency of lung cancer screening and ensure equity of access.

Ultra-low-dose CT lung screening with artificial intelligence iterative reconstruction: evaluation via automatic nodule-detection software

AIM

To test the feasibility of ultra-low-dose (ULD) computed tomography (CT) combined with an artificial intelligence iterative reconstruction (AIIR) algorithm for screening pulmonary nodules using computer-assisted diagnosis (CAD).

MATERIALS AND METHODS

A chest phantom with artificial pulmonary nodules was first scanned using the routine protocol and the ULD protocol (3.28 versus 0.18 mSv) to compare the image quality and to test the acceptability of the ULD CT protocol. Next, 147 lung-screening patients were enrolled prospectively, undergoing an additional ULD CT immediately after their routine CT examination for clinical validation. Images were reconstructed with filtered back-projection (FBP), hybrid iterative reconstruction (HIR), the AIIR, and were imported to the CAD software for preliminary nodule detection. Subjective image quality on the phantom was scored using a five-point scale and compared using the Mann-Whitney U-test. Nodule detection using CAD was evaluated for ULD HIR and AIIR images using the routine dose image as reference.

RESULTS

Higher image quality was scored for AIIR than for FBP and HIR at ULD (p<0.001). As reported by CAD, 107 patients were presented with more than five nodules on routine dose images and were chosen to represent the challenging cases at an early stage of pulmonary disease. Among such, the performance of nodule detection by CAD on ULD HIR and AIIR images was 75.2% and 92.2% of the routine dose image, respectively.

CONCLUSION

Combined with AIIR, it was feasible to use an ULD CT protocol with 95% dose reduction for CAD-based screening of pulmonary nodules.

Comparison of Chest Radiograph Captions Based on Natural Language Processing vs Completed by Radiologists

IMPORTANCE

Artificial intelligence (AI) can interpret abnormal signs in chest radiography (CXR) and generate captions, but a prospective study is needed to examine its practical value.

OBJECTIVE

To prospectively compare natural language processing (NLP)-generated CXR captions and the diagnostic findings of radiologists.

DESIGN, SETTING, AND PARTICIPANTS

A multicenter diagnostic study was conducted. The training data set included CXR images and reports retrospectively collected from February 1, 2014, to February 28, 2018. The retrospective test data set included consecutive images and reports from April 1 to July 31, 2019. The prospective test data set included consecutive images and reports from May 1 to September 30, 2021.

EXPOSURES

A bidirectional encoder representation from a transformers model was used to extract language entities and relationships from unstructured CXR reports to establish 23 labels of abnormal signs to train convolutional neural networks. The participants in the prospective test group were randomly assigned to 1 of 3 different caption generation models: a normal template, NLP-generated captions, and rule-based captions based on convolutional neural networks. For each case, a resident drafted the report based on the randomly assigned captions and an experienced radiologist finalized the report blinded to the original captions. A total of 21 residents and 19 radiologists were involved.

MAIN OUTCOMES AND MEASURES

Time to write reports based on different caption generation models.

RESULTS

The training data set consisted of 74 082 cases (39 254 [53.0%] women; mean [SD] age, 50.0 [17.1] years). In the retrospective (n = 8126; 4345 [53.5%] women; mean [SD] age, 47.9 [15.9] years) and prospective (n = 5091; 2416 [47.5%] women; mean [SD] age, 45.1 [15.6] years) test data sets, the mean (SD) area under the curve of abnormal signs was 0.87 (0.11) in the retrospective data set and 0.84 (0.09) in the prospective data set. The residents' mean (SD) reporting time using the NLP-generated model was 283 (37) seconds-significantly shorter than the normal template (347 [58] seconds; P < .001) and the rule-based model (296 [46] seconds; P < .001). The NLP-generated captions showed the highest similarity to the final reports with a mean (SD) bilingual evaluation understudy score of 0.69 (0.24)-significantly higher than the normal template (0.37 [0.09]; P < .001) and the rule-based model (0.57 [0.19]; P < .001).

CONCLUSIONS AND RELEVANCE

In this diagnostic study of NLP-generated CXR captions, prior information provided by NLP was associated with greater efficiency in the reporting process, while maintaining good consistency with the findings of radiologists.

Radiation Exposure to Low-Dose Computed Tomography for Lung Cancer Screening: Should We Be Concerned?

Lung cancer screening (LCS) programs through low-dose Computed Tomography (LDCT) are being implemented in several countries worldwide. Radiation exposure of healthy individuals due to prolonged CT screening rounds and, eventually, the additional examinations required in case of suspicious findings may represent a concern, thus eventually reducing the participation in an LCS program. Therefore, the present review aims to assess the potential radiation risk from LDCT in this setting, providing estimates of cumulative dose and radiation-related risk in LCS in order to improve awareness for an informed and complete attendance to the program. After summarizing the results of the international trials on LCS to introduce the benefits coming from the implementation of a dedicated program, the screening-related and participant-related factors determining the radiation risk will be introduced and their burden assessed. Finally, future directions for a personalized screening program as well as technical improvements to reduce the delivered dose will be presented.

Use of "Diagnostic Yield" in Imaging Research Reports: Results from Articles Published in Two General Radiology Journals

OBJECTIVE

"Diagnostic yield," also referred to as the detection rate, is a parameter positioned between diagnostic accuracy and diagnosis-related patient outcomes in research studies that assess diagnostic tests. Unfamiliarity with the term may lead to incorrect usage and delivery of information. Herein, we evaluate the level of proper use of the term "diagnostic yield" and its related parameters in articles published in Radiology and Korean Journal of Radiology (KJR).

MATERIALS AND METHODS

Potentially relevant articles published since 2012 in these journals were identified using MEDLINE and PubMed Central databases. The initial search yielded 239 articles. We evaluated whether the correct definition and study setting of "diagnostic yield" or "detection rate" were used and whether the articles also reported companion parameters for false-positive results. We calculated the proportion of articles that correctly used these parameters and evaluated whether the proportion increased with time (2012-2016 vs. 2017-2022).

RESULTS

Among 39 eligible articles (19 from Radiology and 20 from KJR), 17 (43.6%; 11 from Radiology and 6 from KJR) correctly defined "diagnostic yield" or "detection rate." The remaining 22 articles used "diagnostic yield" or "detection rate" with incorrect meanings such as "diagnostic performance" or "sensitivity." The proportion of correctly used diagnostic terms was higher in the studies published in Radiology than in those published in KJR (57.9% vs. 30.0%). The proportion improved with time in Radiology (33.3% vs. 80.0%), whereas no improvement was observed in KJR over time (33.3% vs. 27.3%). The proportion of studies reporting companion parameters was similar between journals (72.7% vs. 66.7%), and no considerable improvement was observed over time.

CONCLUSION

Overall, a minority of articles accurately used "diagnostic yield" or "detection rate." Incorrect usage of the terms was more frequent without improvement over time in KJR than in Radiology. Therefore, improvements are required in the use and reporting of these parameters.

Artificial Intelligence (AI) for Lung Nodules, From the AJR Special Series on AI Applications

Interest in artificial intelligence (AI) applications for lung nodules continues to grow among radiologists, particularly with the expanding eligibility criteria and clinical utilization of lung cancer screening CT. AI has been heavily investigated for detecting and characterizing lung nodules and for guiding prognostic assessment. AI tools have also been used for image postprocessing (e.g., rib suppression on radiography or vessel suppression on CT) and for noninterpretive aspects of reporting and workflow, including management of nodule follow-up. Despite growing interest in and rapid development of AI tools and FDA approval of AI tools for pulmonary nodule evaluation, integration into clinical practice has been limited. Challenges to clinical adoption have included concerns about generalizability, regulatory issues, technical hurdles in implementation, and human skepticism. Further validation of AI tools for clinical use and demonstration of benefit in terms of patient-oriented outcomes also are needed. This article provides an overview of potential applications of AI tools in the imaging evaluation of lung nodules and discusses the challenges faced by practices interested in clinical implementation of such tools.

Measurement Accuracy and Repeatability of RECIST-Defined Pulmonary Lesions and Lymph Nodes in Ultra-Low-Dose CT Based on Deep Learning Image Reconstruction

BACKGROUND

Deep learning image reconstruction (DLIR) improves image quality. We aimed to compare the measured diameter of pulmonary lesions and lymph nodes between DLIR-based ultra-low-dose CT (ULDCT) and contrast-enhanced CT.

METHODS

The consecutive adult patients with noncontrast chest ULDCT (0.07-0.14 mSv) and contrast-enhanced CT (2.38 mSv) were prospectively enrolled. Patients with poor image quality and body mass index ≥ 30 kg/m2 were excluded. The diameter of pulmonary target lesions and lymph nodes defined by Response Evaluation Criteria in Solid Tumors (RECIST) was measured. The measurement variability between ULDCT and enhanced CT was evaluated by Bland-Altman analysis.

RESULTS

The 141 enrolled patients (62 ± 12 years) had 89 RECIST-defined measurable pulmonary target lesions (including 30 malignant lesions, mainly adenocarcinomas) and 45 measurable mediastinal lymph nodes (12 malignant). The measurement variation of pulmonary lesions between high-strength DLIR (DLIR-H) images of ULDCT and contrast-enhanced CT was 2.2% (95% CI: 1.7% to 2.6%) and the variation of lymph nodes was 1.4% (1.0% to 1.9%).

CONCLUSIONS

The measured diameters of pulmonary lesions and lymph nodes in DLIR-H images of ULDCT are highly close to those of contrast-enhanced CT. DLIR-based ULDCT may facilitate evaluating target lesions with greatly reduced radiation exposure in tumor evaluation and lung cancer screening.

Single CT Appointment for Double Lung and Colorectal Cancer Screening: Is the Time Ripe?

Annual screening of lung cancer (LC) with chest low-dose computed tomography (CT) and screening of colorectal cancer (CRC) with CT colonography every 5 years are recommended by the United States Prevention Service Task Force. We review epidemiological and pathological data on LC and CRC, and the features of screening chest low-dose CT and CT colonography comprising execution, reading, radiation exposure and harm, and the cost effectiveness of the two CT screening interventions. The possibility of combining chest low-dose CT and CT colonography examinations for double LC and CRC screening in a single CT appointment is then addressed. We demonstrate how this approach appears feasible and is already reasonable as an opportunistic screening intervention in 50–75-year-old subjects with smoking history and average CRC risk. In addition to the crucial role Computer Assisted Diagnosis systems play in decreasing the test reading times and the need to educate radiologists in screening chest LDCT and CT colonography, in view of a single CT appointment for double screening, the following uncertainties need to be solved: (1) the schedule of the screening CT; (2) the effectiveness of iterative reconstruction and deep learning algorithms affording an ultra-low-dose CT acquisition technique and (3) management of incidental findings. Resolving these issues will imply new cost-effectiveness analyses for LC screening with chest low dose CT and for CRC screening with CT colonography and, especially, for the double LC and CRC screening with a single-appointment CT.

Applying a CT texture analysis model trained with deep-learning reconstruction images to iterative reconstruction images in pulmonary nodule diagnosis

OBJECTIVE

To investigate the feasibility and accuracy of applying a computed tomography (CT) texture analysis model trained with deep-learning reconstruction images to iterative reconstruction images for classifying pulmonary nodules.

MATERIALS AND METHODS

CT images of 102 patients, with a total of 118 pulmonary nodules (52 benign, 66 malignant) were retrospectively reconstructed with a deep-learning reconstruction (artificial intelligence iterative reconstruction [AIIR]) and a hybrid iterative reconstruction (HIR) technique. The AIIR data were divided into a training (n = 96) and a validation set (n = 22), and the HIR data were set as the test set (n = 118). Extracted texture features were compared using the Mann-Whitney U test and t-test. The diagnostic performance of the classification model was analyzed with the receiver operating characteristic curve (ROC), the area under ROC (AUC), sensitivity, specificity, and accuracy.

RESULTS

Among the obtained 68 texture features, 51 (75.0%) were not influenced by the change of reconstruction algorithm (p > 0.05). Forty-four features were significantly different between benign and malignant nodules (p < 0.05) for the AIIR dataset, which were selected to build the classification model. The accuracy and AUC of the classification model were 92.3% and 0.91 (95% confidence interval [CI], 0.74-0.90) with the validation set, which were 80.0% and 0.80 (95% CI, 0.68-0.86) with the test set.

CONCLUSION

With the CT texture analysis model trained with deep-learning reconstruction (AIIR) images showing favorable diagnostic accuracy in discriminating benign and malignant pulmonary nodules, it also has certain applicability to the iterative reconstruction (HIR) images.