The Challenge of Choosing the Best Classification Method in Radiomic Analyses: Recommendations and Applications to Lung Cancer CT Images.

Radiomics uses high-dimensional sets of imaging features to predict biological characteristics of tumors and clinical outcomes. The choice of the algorithm used to analyze radiomic features and perform predictions has a high impact on the results, thus the identification of adequate machine learning methods for radiomic applications is crucial. In this study we aim to identify suitable approaches of analysis for radiomic-based binary predictions, according to sample size, outcome balancing and the features-outcome association strength. Simulated data were obtained reproducing the correlation structure among 168 radiomic features extracted from Computed Tomography images of 270 Non-Small-Cell Lung Cancer (NSCLC) patients and the associated to lymph node status. Performances of six classifiers combined with six feature selection (FS) methods were assessed on the simulated data using AUC (Area Under the Receiver Operating Characteristics Curves), sensitivity, and specificity. For all the FS methods and regardless of the association strength, the tree-based classifiers Random Forest and Extreme Gradient Boosting obtained good performances (AUC ≥ 0.73), showing the best trade-off between sensitivity and specificity. On small samples, performances were generally lower than in large-medium samples and with larger variations. FS methods generally did not improve performances. Thus, in radiomic studies, we suggest evaluating the choice of FS and classifiers, considering specific sample size, balancing, and association strength.

Apparent Diffusion Coefficient and Other Preoperative Magnetic Resonance Imaging Features for the Prediction of Positive Surgical Margins in Prostate Cancer Patients Undergoing Radical Prostatectomy.

PURPOSE: To investigate the use of apparent diffusion coefficient (ADC) values and other MRI features for predicting positive surgical margins (PSMs) in patients undergoing radical prostatectomy. MATERIALS AND METHODS: We retrospectively identified 400 consecutive patients who underwent surgery for prostate cancer between January 2015 and June 2016. ADC values of the index lesion and other preoperative magnetic resonance imaging features, including tumor site, laterality, level, Prostate Imaging Reporting and Data System category, European Society of Urogenital Radiology extracapsular extension score, and prostate volume, were assessed. Univariate and multivariable logistic regression were performed. Performance in predicting the occurrence of PSMs was measured using the area under the curve (AUC). AUC differences were evaluated with the DeLong method. The Youden index was calculated to identify the ADC threshold to best discriminate patients with PSMs. RESULTS: Of the 400 patients, 105 (26.2%) had PSMs after radical prostatectomy. ADC values, Prostate Imaging Reporting and Data System category, extracapsular extension score, tumor site, and laterality were significantly associated with PSMs (P < .001) in univariate analysis. The AUC of the predictive model based on ADC alone was 68.2% (95% confidence interval, 62.2-74.2%) and did not significantly differ from the best multivariable predictive model which combined laterality, and site with ADC to attain an AUC of 70.0% (95% confidence interval, 64.2-75.8%; DeLong P = .318). The ADC threshold that maximized the Youden index was 960.3 µm2/s. CONCLUSION: ADC values and preoperative magnetic resonance imaging features can help estimate the risk of PSMs after radical prostatectomy.

Semi-Automated Segmentation of Bone Metastases from Whole-Body MRI: Reproducibility of Apparent Diffusion Coefficient Measurements.

Using semi-automated software simplifies quantitative analysis of the visible burden of disease on whole-body MRI diffusion-weighted images. To establish the intra- and inter-observer reproducibility of apparent diffusion coefficient (ADC) measures, we retrospectively analyzed data from 20 patients with bone metastases from breast (BCa; n = 10; aged 62.3 ± 14.8) or prostate cancer (PCa; n = 10; aged 67.4 ± 9.0) who had undergone examinations at two timepoints, before and after hormone-therapy. Four independent observers processed all images twice, first segmenting the entire skeleton on diffusion-weighted images, and then isolating bone metastases via ADC histogram thresholding (ADC: 650-1400 µm2/s). Dice Similarity, Bland-Altman method, and Intraclass Correlation Coefficient were used to assess reproducibility. Inter-observer Dice similarity was moderate (0.71) for women with BCa and poor (0.40) for men with PCa. Nonetheless, the limits of agreement of the mean ADC were just ±6% for women with BCa and ±10% for men with PCa (mean ADCs: 941 and 999 µm2/s, respectively). Inter-observer Intraclass Correlation Coefficients of the ADC histogram parameters were consistently greater in women with BCa than in men with PCa. While scope remains for improving consistency of the volume segmented, the observer-dependent variability measured in this study was appropriate to distinguish the clinically meaningful changes of ADC observed in patients responding to therapy, as changes of at least 25% are of interest.

Whole-body magnetic resonance imaging: technique, guidelines and key applications.

Whole-body magnetic resonance imaging (WB-MRI) is an imaging method without ionising radiation that can provide WB coverage with a core protocol of essential imaging contrasts in less than 40 minutes, and it can be complemented with sequences to evaluate specific body regions as needed. In many cases, WB-MRI surpasses bone scintigraphy and computed tomography in detecting and characterising lesions, evaluating their response to therapy and in screening of high-risk patients. Consequently, international guidelines now recommend the use of WB-MRI in the management of patients with multiple myeloma, prostate cancer, melanoma and individuals with certain cancer predisposition syndromes. The use of WB-MRI is also growing for metastatic breast cancer, ovarian cancer and lymphoma as well as for cancer screening amongst the general population. In light of the increasing interest from clinicians and patients in WB-MRI as a radiation-free technique for guiding the management of cancer and for cancer screening, we review its technical basis, current international guidelines for its use and key applications.

MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218).

OBJECTIVES: Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa). METHODS: This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis. RESULTS: Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94. CONCLUSIONS: MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice. KEY POINTS: • A radiomic model was used to classify PCa aggressiveness. • Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland. • The most predictive features belong to the texture (57%) and intensity (43%) domains.

7-T MRI tracking of mesenchymal stromal cells after lung injection in a rat model.

BACKGROUND: Mesenchymal stromal cells (MSCs) are able to migrate and engraft at sites of inflammation, injuries, and tumours, but little is known about their fate after local injection. The purpose of this study is to perform MSC tracking, combining in vivo 7-T magnetic resonance imaging (MRI) and histological assessment, following lung injection in a rat model. METHODS: Five lungs were injected with ferumoxide-labelled MSCs and five with perfluorocarbon-labelled MSCs and underwent 7-T MRI. MRI acquisitions were recorded immediately (T0), at 24 h (T24) and/or 48 h (T48) after injection. For each rat, labelled cells were assessed in the main organs by MRI. Target organs were harvested under sterile conditions from rats sacrificed 0, 24, or 48 h after injection and fixed for histological analysis via confocal and structured illumination microscopy. RESULTS: Ferumoxide-labelled MSCs were not detectable in the lungs, whereas they were not visible in the distant sites. Perfluorocarbon-labelled MSCs were seen in 5/5 injected lungs at T0, in 1/2 at T24, and in 1/3 at T48. The fluorine signal in the liver was seen in 3/5 at T0, in 1/2 at T24, and in 2/3 at T48. Post-mortem histology confirmed the presence of MSCs in the injected lung. CONCLUSIONS: Ferumoxide-labelled cells were not seen at distant sites; a linear decay of injected perfluorocarbon-labelled MSCs was observed at T0, T24, and T48 in the lung. In more than half of the experiments, perfluorocarbon-labelled MSCs scattering to the liver was observed, with a similar decay over time as observed in the lung.

Whole-body magnetic resonance imaging (WB-MRI) reporting with the METastasis Reporting and Data System for Prostate Cancer (MET-RADS-P): inter-observer agreement between readers of different expertise levels.

BACKGROUND: The METastasis Reporting and Data System for Prostate Cancer (MET-RADS-P) guidelines are designed to enable reproducible assessment in detecting and quantifying metastatic disease response using whole-body magnetic resonance imaging (WB-MRI) in patients with advanced prostate cancer (APC). The purpose of our study was to evaluate the inter-observer agreement of WB-MRI examination reports produced by readers of different expertise when using the MET-RADS-P guidelines. METHODS: Fifty consecutive paired WB-MRI examinations, performed from December 2016 to February 2018 on 31 patients, were retrospectively examined to compare reports by a Senior Radiologist (9 years of experience in WB-MRI) and Resident Radiologist (after a 6-months training) using MET-RADS-P guidelines, for detection and for primary/dominant and secondary response assessment categories (RAC) scores assigned to metastatic disease in 14 body regions. Inter-observer agreement regarding RAC score was evaluated for each region by using weighted-Cohen's Kappa statistics (K). RESULTS: The number of metastatic regions reported by the Senior Radiologist (249) and Resident Radiologist (251) was comparable. For the primary/dominant RAC pattern, the agreement between readers was excellent for the metastatic findings in cervical, dorsal, and lumbosacral spine, pelvis, limbs, lungs and other sites (K:0.81-1.0), substantial for thorax, retroperitoneal nodes, other nodes and liver (K:0.61-0.80), moderate for pelvic nodes (K:0.56), fair for primary soft tissue and not assessable for skull due to the absence of findings. For the secondary RAC pattern, agreement between readers was excellent for the metastatic findings in cervical spine (K:0.93) and retroperitoneal nodes (K:0.89), substantial for those in dorsal spine, pelvis, thorax, limbs and pelvic nodes (K:0.61-0.80), and moderate for lumbosacral spine (K:0.44). CONCLUSIONS: We found inter-observer agreement between two readers of different expertise levels to be excellent in bone, but mixed in other body regions. Considering the importance of bone metastases in patients with APC, our results favor the use of MET-RADS-P in response to the growing clinical need for monitoring of metastasis in these patients.

Association between baseline tumour burden and outcome in patients with cancer treated with next-generation immunoncology agents.

BACKGROUND: Baseline tumour burden is a prognostic factor for patients with melanoma and non-small-cell lung cancer treated with immunotherapy. However, no data are available on its role in other solid tumours, nor for treatment with next-generation immunoncology agents (NGIOs). METHODS: We reviewed data of patients with any solid tumour consecutively treated at our institution from August 2014 to March 2019, who received ≥1 dose of immune checkpoint inhibitor and/or NGIO within phase 1 trials. Baseline tumour burden was calculated as ∑i Response Evaluation Criteria in Solid Tumours 1.1 baseline target lesions (baseline tumour size [BTS]) or as sum of all measurable baseline lesions (total tumour burden [TTB]); the impact of both parameters on treatment outcomes was investigated. RESULTS: One hundred fifty patients were included in the analysis. Median BTS and TTB were 79 mm and 212 mm, respectively. Objective response rate was found significantly associated with BTS (p < 0.001) and TTB quartiles (p = 0.006), with response rates progressively increasing with decreasing tumour burden quartiles. Both progression-free survival (PFS) (p = 0.001) and overall survival (OS) (p < 0.001) were significantly associated with BTS quartiles, with 26% of the patients progression-free and 56% alive at 12 months in the lower BTS quartile, compared with 3% and 24%, respectively, in the upper quartile. TTB was also significantly associated with OS (P = 0.01) and borderline-significant for PFS (p = 0.07). Multivariate analysis confirmed that baseline burden, also considered as continuous variable, is independently associated with PFS and OS, when assessed with BTS (p = 0.001 and p < 0.001) and TTB (p = 0.007 and p < 0.001). CONCLUSIONS: Lower baseline tumour burden is associated with better outcomes in patients with cancer treated with novel immunotherapies.

External validation of radiomics-based predictive models in low-dose CT screening for early lung cancer diagnosis.

PURPOSE: Low-dose CT screening allows early lung cancer detection, but is affected by frequent false positive results, inter/intra observer variation and uncertain diagnoses of lung nodules. Radiomics-based models have recently been introduced to overcome these issues, but limitations in demonstrating their generalizability on independent datasets are slowing their introduction to clinic. The aim of this study is to evaluate two radiomics-based models to classify malignant pulmonary nodules in low-dose CT screening, and to externally validate them on an independent cohort. The effect of a radiomics features harmonization technique is also investigated to evaluate its impact on the classification of lung nodules from a multicenter data. METHODS: Pulmonary nodules from two independent cohorts were considered in this study; the first cohort (110 subjects, 113 nodules) was used to train prediction models, and the second cohort (72 nodules) to externally validate them. Literature-based radiomics features were extracted and, after feature selection, used as predictive variables in models for malignancy identification. An in-house prediction model based on artificial neural network (ANN) was implemented and evaluated, along with an alternative model from the literature, based on a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). External validation was performed on the second cohort to evaluate models' generalization ability. Additionally, the impact of the Combat harmonization method was investigated to compensate for multicenter datasets variabilities. A new training of the models based on harmonized features was performed on the first cohort, then tested separately on the harmonized and non-harmonized features of the second cohort. RESULTS: Preliminary results showed a good accuracy of the investigated models in distinguishing benign from malignant pulmonary nodules with both sets of radiomics features (i.e., non-harmonized and harmonized). The performance of the models, quantified in terms of Area Under the Curve (AUC), was > 0.89 in the training set and > 0.82 in the external validation set for all the investigated scenarios, outperforming the clinical standard (AUC of 0.76). Slightly higher performance was observed for the SVM-LASSO model than the ANN in the external dataset, although they did not result significantly different. For both harmonized and non-harmonized features, no statistical difference was found between Receiver operating characteristic (ROC) curves related to training and test set for both models. CONCLUSIONS: Although no significant improvements were observed when applying the Combat harmonization method, both in-house and literature-based models were able to classify lung nodules with good generalization to an independent dataset, thus showing their potential as tools for clinical decision-making in lung cancer screening.

Association of a CT-Based Clinical and Radiomics Score of Non-Small Cell Lung Cancer (NSCLC) with Lymph Node Status and Overall Survival.

BACKGROUND: To evaluate whether a model based on radiomic and clinical features may be associated with lymph node (LN) status and overall survival (OS) in lung cancer (LC) patients; to evaluate whether CT reconstruction algorithms may influence the model performance. METHODS: patients operated on for LC with a pathological stage up to T3N1 were retrospectively selected and divided into training and validation sets. For the prediction of positive LNs and OS, the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression model was used; univariable and multivariable logistic regression analysis assessed the association of clinical-radiomic variables and endpoints. All tests were repeated after dividing the groups according to the CT reconstruction algorithm. p-values < 0.05 were considered significant. RESULTS: 270 patients were included and divided into training (n = 180) and validation sets (n = 90). Transfissural extension was significantly associated with positive LNs. For OS prediction, high- and low-risk groups were different according to the radiomics score, also after dividing the two groups according to reconstruction algorithms. CONCLUSIONS: a combined clinical-radiomics model was not superior to a single clinical or single radiomics model to predict positive LNs. A radiomics model was able to separate high-risk and low-risk patients for OS; CTs reconstructed with Iterative Reconstructions (IR) algorithm showed the best model performance.

Whole-body magnetic resonance imaging (WB-MRI) for cancer screening in asymptomatic subjects of the general population: review and recommendations.

BACKGROUND: The number of studies describing the use of whole-body magnetic resonance imaging (WB-MRI) for screening of malignant tumours in asymptomatic subjects is increasing. Our aim is to review the methodologies used and the results of the published studies on per patient and per lesion analysis, and to provide recommendations on the use of WB-MRI for cancer screening. MAIN BODY: We identified 12 studies, encompassing 6214 WB-MRI examinations, which provided the rates of abnormal findings and findings suspicious for cancer in asymptomatic subjects, from the general population. Eleven of 12 studies provided imaging protocols that included T1- and T2-weighted sequences, while only five included diffusion weighted imaging (DWI) of the whole body. Different categorical systems were used for the classification and the management of abnormal findings. Of 17,961 abnormal findings reported, 91% were benign, while 9% were oncologically relevant, requiring further investigations, and 0.5% of lesions were suspicious for cancer. A per-subject analysis showed that just 5% of subjects had no abnormal findings, while 95% had abnormal findings. Findings requiring further investigation were reported in 30% of all subjects, though in only 1.8% cancer was suspected. The overall rate of histologically confirmed cancer was 1.1%. CONCLUSION: WB-MRI studies of cancer screening in the asymptomatic general population are too heterogeneous to draw impactful conclusions regarding efficacy. A 5-point lesion scale based on the oncological relevance of findings appears the most appropriate for risk-based management stratification. WB-MRI examinations should be reported by experienced oncological radiologists versed on WB-MRI reading abnormalities and on onward referral pathways.

Will traditional biopsy be substituted by radiomics and liquid biopsy for breast cancer diagnosis and characterisation?

The diagnosis of breast cancer currently relies on radiological and clinical evaluation, confirmed by histopathological examination. However, such approach has some limitations as the suboptimal sensitivity, the long turnaround time for recall tests, the invasiveness of the procedure and the risk that some features of target lesions may remain undetected, making re-biopsy a necessity. Recent technological advances in the field of artificial intelligence hold promise in addressing such medical challenges not only in cancer diagnosis, but also in treatment assessment, and monitoring of disease progression. In the perspective of a truly personalised medicine, based on the early diagnosis and individually tailored treatments, two new technologies, namely radiomics and liquid biopsy, are rising as means to obtain information from diagnosis to molecular profiling and response assessment, without the need of a biopsied tissue sample. Radiomics works through the extraction of quantitative peculiar features of cancer from radiological data, while liquid biopsy gets the whole of the malignancy's biology from something as easy as a blood sample. Both techniques hopefully will identify diagnostic and prognostic information of breast cancer potentially reducing the need for invasive (and often difficult to perform) biopsies and favouring an approach that is as personalised as possible for each patient. Nevertheless, such techniques will not substitute tissue biopsy in the near future, and even in further times they will require the aid of other parameters to be correctly interpreted and acted upon.

Low-Dose Aspirin in High-Risk Individuals With Screen-Detected Subsolid Lung Nodules: A Randomized Phase II Trial.

Lung cancer screening by helical low-dose computed tomography detects nonsolid nodules that may be lung adenocarcinoma precursors. Aspirin's anti-inflammatory properties make it an attractive target for prevention of multiple cancers, including lung cancer. Therefore, we conducted a phase IIb trial (NCT02169271) to study the efficacy of low-dose aspirin to reduce the size of subsolid lung nodules (SSNs). A total of 98 current or former smokers (67.3% current) undergoing annual low-dose computed tomography screening with persistent SSNs were randomly assigned to receive aspirin 100 mg/day or placebo for 1 year. There was no difference in change in the sum of the longest diameters of target nodules in the placebo and aspirin arm after 12 months of treatment (-0.12 mm [SD = 1.55 mm] and +0.30 mm [SD= 2.54 mm], respectively; 2-sided P = .33 primary endpoint). There were no changes observed in subgroup analyses by individual characteristics or nodule type. One year of low-dose aspirin did not show any effect on lung SSNs. SSNs regression may not be the proper target for aspirin, and/or longer duration may be needed to see SSNs modifications.

Pre-operative evaluation of epithelial ovarian cancer patients: Role of whole body diffusion weighted imaging MR and CT scans in the selection of patients suitable for primary debulking surgery. A single-centre study.

PURPOSE: to evaluate the accuracy of Whole Body MRI including Diffusion-Weighted Imaging sequences (WB DWI MR) in the assessment of sites of disease in epithelial ovarian cancer (EOC), in comparison to CT; to evaluate whether a clinical-radiological score may predict suboptimal cytoreductive surgery. METHODS: patients with suspected EOC who underwent pre-operative WB DWI MR were included; CT scans were recorded. Data recorded included: age, staging, dates of examinations and surgery; tumour markers; sites of disease at imaging scans and at surgery. For calculation of sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of WB DWI MR and CT, surgical evaluation represented the gold standard. The accuracy of WB DWI MR and CT was compared. The association between clinical and radiological criteria with sub-optimal cytoreduction was tested to identify a final model to predict sub-optimal cytoreduction. RESULTS: 92 patients were included; 77/92 (83.7 %) were optimally cytoreduced. Sixty-six CT and 92 MR examinations were evaluated. WB DWI MR showed overall higher accuracy than CT in assessing all sites, but it performed significantly better than CT specifically for involvement of mesentery, lumbo-aortic lymph nodes, pelvis, large bowel, sigmoid-rectum. The predicting score for suboptimal cytoreduction included: mesenteric carcinomatosis; mesenteric retraction; large bowel carcinomatosis. CONCLUSIONS: In pre-operative evaluation of EOC patients, WB DW MRI is accurate for assessment of multiple sites and it is significantly more accurate than CT for specific unresectable sites. In our series, significant sites of disease for suboptimal cytoreduction were mesenteric carcinomatosis, mesenteric retraction and large bowel carcinomatosis.

Do DWI and quantitative DCE perfusion MR have a prognostic value in high-grade serous ovarian cancer?

PURPOSE: To evaluate whether perfusion and diffusion parameters from staging MR in ovarian cancer (OC) patients may predict the presence of residual tumor at surgery and the progression-free survival (PFS) in 12 months. MATERIALS AND METHODS: Patients who are from a single institution, candidate for OC to cytoreductive surgery and undergoing MR for staging purposes were included in this study. Inclusion criteria were: preoperative MR including diffusion-weighted imaging (DWI) and perfusion dynamic contrast-enhanced (DCE) sequence; cytoreductive surgery performed within a month from MR; and minimum follow-up of 12 months. Patients' characteristics including the presence of residual tumor at surgery (R0 or R1) and relapse within 12 months from surgery were recorded. DWI parameters included apparent diffusion coefficient (ADC) of the largest ovarian mass (O-ADC) and normalized ovarian ADC as a ratio between ovarian ADC and muscle ADC (M-ADC). DCE quantitative parameters included were descriptors of tumor vascular properties such as forward and backward transfer constants, plasma volume and volume of extracellular space. Statistical analysis was performed, and p values < 0.05 were considered significant. RESULTS: Forty-nine patients were included. M-ADC showed a slightly significant association with the presence of residual tumor at surgery. None of the other functional parameters showed either difference between R0 and R1 patients or association with PFS in the first 12 months. CONCLUSIONS: This preliminary study demonstrated a slightly significant association between normalized ovarian ADC and the presence of residual tumor at surgery. The other perfusion and diffusion parameters were not significant for the endpoints of this study.

Inter-observer agreement on the morphology of screening-detected lung cancer: beyond pulmonary nodules and masses.

OBJECTIVES: Pulmonary nodules and masses are the typical presentations of lung cancer. However, a spectrum of focal opacities cannot be defined as either "pulmonary nodule" or "mass," despite representing cancer. We aimed to assess the morphology of screening-detected lung cancers at low-dose computed tomography LDTC and to evaluate inter-observer agreement in their classification. METHODS: Four radiologists with different experiences in thoracic imaging retrospectively reviewed 273 screening-detected lung cancers. Readers were asked to assess if morphology at the time of diagnosis was consistent with the Fleischner Society definition of pulmonary "nodule" or "mass." Cancers not consistent were defined as "non-nodular/non-mass" (NN/NM) and sub-classified as follows: associated with cystic airspaces, stripe-like, scar-like, endobronchial, or not otherwise defined (NOD). Inter-observer agreement was evaluated using Cohen's K statistic among pairs of readers and modified Fleiss' kappa statistic for overall agreement. RESULTS: Two hundred forty-one of the 273 (88%) lesions were defined as pulmonary nodule or mass by complete agreement, while 20/273 (7.3%) were defined as NN/NM. Six (2.2%) of 273 were sub-classified as lesions associated with cystic airspace, six (2.2%) as scar-like, five (1.8%) as endobronchial, and one (0.7%) as NOD by complete agreement. The concordance in defining morphology was excellent (261/273; 96%, 95%CI 92-98%; k 0.85, 95%CI 0.75-0.92) and also in the sub-classification (18/20; 90%, 95%CI 68-99%, k 0.93, 95%CI 0.86-1.00). There was incomplete agreement regarding lesion morphology in 4.4% (12/273) of cases. CONCLUSIONS: A non-negligible percentage of screening-detected lung cancers has a NN/NM appearance at LDCT. The concordance in defining lesion morphology was excellent. The awareness of various presentations can avoid missed or delayed diagnosis. KEY POINTS: • A non-negligible percentage of screening-detected lung cancers have neither nodular nor mass appearance at low-dose CT. • The awareness of various LDCT presentations of lung cancer can avoid missed or delayed diagnosis. • Optimal protocol management in CT screening should take into consideration lung nodules as well as various other focal abnormalities.

Computed Tomography-Guided Percutaneous Radiotracer Localization and Resection of Indistinct/Small Pulmonary Lesions.

BACKGROUND: Detection of small pulmonary lesions has increased, and often they are difficult to localize and resect. We present our mature experience with preoperative computer tomography-guided radiotracer localization, followed by resection of these lesions. METHODS: Patients with pulmonary nodule smaller than 1 cm or deep below the visceral pleura underwent computer tomography-guided injection of radiotracer technetium macroaggregates in or close to the lesion. A gamma probe was used to localize the marked area that was resected, and in case of primary lung cancer a lobectomy with nodal dissection was performed. RESULTS: Between November 2007 and December 2017, 262 patients (196 men; median age 63 years) underwent preoperative radiotracer injection with a successful marking in all patients. Complications included 35 asymptomatic pneumothoraxes (13.4%), 36 parenchymal hemorrhage suffusions (13.7%), and 2 mild allergic reactions to contrast medium (0.7%). In all cases, except for 3, the gamma probe revealed the pulmonary lesion. Mean distance from the pleura was 10 mm (range, 0 to 40 mm). Pulmonary resection was performed by thoracoscopy in 212 cases (80.9%), intentional thoracotomy in 42 (16.0%), and converted thoracoscopy in 8 (3.1%). Mean pathologic nodule size was 9.3 mm (range, 2.5 to 39 mm). One hundred sixty-six nodules (63.4%) were nonsolid, 64 (24.4%) were partially solid, and 32 (12.2%) had a solid morphologic characteristic. Histologic examination showed 16 benign (6.1%) and 246 malignant (93.9%) lesions (218 primary lung cancers). CONCLUSIONS: Preoperative radiotracer localization of small or indistinct pulmonary lesions is simple and feasible with a high rate of success. It may be an effective and attractive alternative in managing lung lesions.