Distinguishing Adenocarcinomas from Granulomas in the CT scan of the chest: performance degradation evaluation in the automatic segmentation framework
Ontology highlight
ABSTRACT: Objective
The most common histopathologic malignant and benign nodules are Adenocarcinoma and Granuloma, respectively, which have different standards of care. In this paper, we propose an automatic framework for the diagnosis of the Adenocarcinomas and the Granulomas in the CT scans of the chest from a private dataset. We use the radiomic features of the nodules and the attached vessel tortuosity for the diagnosis. The private dataset includes 22 CTs for each nodule type, i.e., adenocarcinoma and granuloma. The dataset contains the CTs of the non-smoker patients who are between 30 and 60 years old. To automatically segment the delineated nodule area and the attached vessels area, we apply a morphological-based approach. For distinguishing the malignancy of the segmented nodule, two texture features of the nodule, the curvature Mean and the number of the attached vessels are extracted. Results
We compare our framework with the state-of-the-art feature selection methods for differentiating Adenocarcinomas from Granulomas. These methods employ only the shape features of the nodule, the texture features of the nodule, or the torsion features of the attached vessels along with the radiomic features of the nodule. The accuracy of our framework is improved by considering the four selected features. Supplementary Information
The online version contains supplementary material available at 10.1186/s13104-021-05502-1.
SUBMITTER: Tavakoli M
PROVIDER: S-EPMC7942003 | biostudies-literature | 2021 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Adenocarcinomas and active granulomas can both have a spiculated appearance on computed tomography (CT) and both are often fluorodeoxyglucose (FDG) avid on positron emission tomography (PET) scan, making them difficult to distinguish. Consequently, patients with benign granulomas are often subjected to invasive surgical biopsies or resections. In this study, quantitative vessel tortuosity (QVT), a novel CT imaging biomarker to distinguish between benign granulomas and adenocarcinomas on routine non-contrast lung CT scans is introduced. Our study comprised of CT scans of 290 patients from two different institutions, one cohort for training (N?=?145) and the other (N?=?145) for independent validation. In conjunction with a machine learning classifier, the top informative and stable QVT features yielded an area under receiver operating characteristic curve (ROC AUC) of 0.85 in the independent validation set. On the same cohort, the corresponding AUCs for two human experts including a radiologist and a pulmonologist were found to be 0.61 and 0.60, respectively. QVT features also outperformed well known shape and textural radiomic features which had a maximum AUC of 0.73 (p-value?=?0.002), as well as features learned using a convolutional neural network AUC?=?0.76 (p-value?=?0.028). Our results suggest that QVT features could potentially serve as a non-invasive imaging biomarker to distinguish granulomas from adenocarcinomas on non-contrast CT scans.
| S-EPMC6191462 | biostudies-literature
Project description:Purpose To evaluate ability of radiomic (computer-extracted imaging) features to distinguish non-small cell lung cancer adenocarcinomas from granulomas at noncontrast CT. Materials and Methods For this retrospective study, screening or standard diagnostic noncontrast CT images were collected for 290 patients (mean age, 68 years; range, 18-92 years; 125 men [mean age, 67 years; range, 18-90 years] and 165 women [mean age, 68 years; range, 33-92 years]) from two institutions between 2007 and 2013. Histopathologic analysis was available for one nodule per patient. Corresponding nodule of interest was identified on axial CT images by a radiologist with manual annotation. Nodule shape, wavelet (Gabor), and texture-based (Haralick and Laws energy) features were extracted from intra- and perinodular regions. Features were pruned to train machine learning classifiers with 145 patients. In a test set of 145 patients, classifier results were compared against a convolutional neural network (CNN) and diagnostic readings of two radiologists. Results Support vector machine classifier with intranodular radiomic features achieved an area under the receiver operating characteristic curve (AUC) of 0.75 on the test set. Combining radiomics of intranodular with perinodular regions improved the AUC to 0.80. On the same test set, CNN resulted in an AUC of 0.76. Radiologist readers achieved AUCs of 0.61 and 0.60, respectively. Conclusion Radiomic features from intranodular and perinodular regions of nodules can distinguish non-small cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Nishino in this issue.
| S-EPMC6394783 | biostudies-literature
Project description:We examined the chest CT scans of 1,453 WTC responders using the International Classification of High-resolution CT for Occupational and Environmental Respiratory Diseases. Univariate and bivariate analyses of potential work-related pleural abnormalities were performed with pre-WTC and WTC-related occupational exposure data, spirometry, demographics and quantitative CT measurements. Logistic regression was used to evaluate occupational predictors of those abnormalities. Chest CT scans were performed first at a median of 6.8 years after 9/11/2001. Pleural abnormalities were the most frequent (21.1%) across all occupational groups In multivariable analyses, significant pre-WTC occupational asbestos exposure, and work as laborer/cleaner were predictive of pleural abnormalities, with prevalence being highest for the Polish subgroup (n = 237) of our population. Continued occupational lung disease surveillance is warranted in this cohort.
| S-EPMC6474817 | biostudies-literature
Project description:With the Coronavirus disease 2019 (COVID-19) spread, causing a world pandemic, and recently, the virus new variants continue to appear, making the situation more challenging and threatening, the visual assessment and quantification by expert radiologists have become costly and error-prone. Hence, there is a need to propose a model to predict the COVID-19 cases at the earliest possible to control the disease spread. In order to assist the medical professionals and reduce workload and the time the COVID-19 diagnosis cycle takes, this paper proposes a novel neural network architecture termed as O-Net to automatically segment chest Computerised Tomography Ct-scans infected by COVID-19 with optimised computing power and memory occupation. The O-Net consists of two convolutional autoencoders with an upsampling channel and a downsampling channel. Experimental tests show our proposal's effectiveness and potential, with a dice score of 0.86, pixel accuracy, precision, specificity of 0.99, 0.99, 0.98, respectively. Performance on the external dataset illustrates generalisation and scalability capabilities of the O-Net model to Ct-scan obtained from different scanners with different sizes. The second objective of this work is to introduce our virtual reality platform, COVIR, that visualises and manipulates 3D reconstructed lungs and segmented infected lesions caused by COVID-19. COVIR platform acts as a reading and visualisation support for medical practitioners to diagnose COVID-19 lung infection. The COVIR platform could be used for medical education professional practice and training. It was tested by Thirteen participants (medical staff, researchers, and collaborators), they conclude that the 3D VR visualisation of segmented Ct-Scan provides an aid diagnosis tool for better interpretation.
| S-EPMC8923016 | biostudies-literature
Project description:Methods for quantification of breast density on MRI using semiautomatic approaches are commonly used. In this study, the authors report on a fully automatic chest template-based method.Nonfat-suppressed breast MR images from 31 healthy women were analyzed. Among them, one case was randomly selected and used as the template, and the remaining 30 cases were used for testing. Unlike most model-based breast segmentation methods that use the breast region as the template, the chest body region on a middle slice was used as the template. Within the chest template, three body landmarks (thoracic spine and bilateral boundary of the pectoral muscle) were identified for performing the initial V-shape cut to determine the posterior lateral boundary of the breast. The chest template was mapped to each subject's image space to obtain a subject-specific chest model for exclusion. On the remaining image, the chest wall muscle was identified and excluded to obtain clean breast segmentation. The chest and muscle boundaries determined on the middle slice were used as the reference for the segmentation of adjacent slices, and the process continued superiorly and inferiorly until all 3D slices were segmented. The segmentation results were evaluated by an experienced radiologist to mark voxels that were wrongly included or excluded for error analysis.The breast volumes measured by the proposed algorithm were very close to the radiologist's corrected volumes, showing a % difference ranging from 0.01% to 3.04% in 30 tested subjects with a mean of 0.86% ± 0.72%. The total error was calculated by adding the inclusion and the exclusion errors (so they did not cancel each other out), which ranged from 0.05% to 6.75% with a mean of 3.05% ± 1.93%. The fibroglandular tissue segmented within the breast region determined by the algorithm and the radiologist were also very close, showing a % difference ranging from 0.02% to 2.52% with a mean of 1.03% ± 1.03%. The total error by adding the inclusion and exclusion errors ranged from 0.16% to 11.8%, with a mean of 2.89% ± 2.55%.The automatic chest template-based breast MRI segmentation method worked well for cases with different body and breast shapes and different density patterns. Compared to the radiologist-established truth, the mean difference in segmented breast volume was approximately 1%, and the total error by considering the additive inclusion and exclusion errors was approximately 3%. This method may provide a reliable tool for MRI-based segmentation of breast density.
| S-EPMC3843758 | biostudies-other
Project description:BackgroundIn ARDS, the extent of fibroproliferative activity on chest high-resolution CT (HRCT) scan has been reported to correlate with poorer short-term outcomes and pulmonary-associated quality of life. However, clinical factors associated with HRCT scan fibroproliferation are incompletely characterized. We questioned if lung compliance assessed at the bedside would be associated with fibroproliferation on HRCT scans obtained during the resolution phase of ARDS.MethodsWe used data from a published randomized, controlled clinical trial in ARDS. All patients were cared for using a low tidal volume strategy. Demographic data and ventilator parameters were examined in association with radiologic scores from chest HRCT scans obtained 14 days after diagnosis.ResultsData from 82 patients with ARDS were analyzed. Average static respiratory compliance over the first 14 days after diagnosis was inversely associated with chest HRCT scan reticulation (? = -0.46); this relationship persisted in multivariable analysis including APACHE (Acute Physiology and Chronic Health Evaluation) II scores, initial Pao2/Fio2, pneumonia diagnosis, and ventilator days. Average static respiratory compliance was also lower among patients with bronchiectasis at day 14 (P = .007). Initial static respiratory compliance obtained within the first day after ARDS diagnosis was correlated inversely with the presence of HRCT scan reticulation (? = -0.38) and was lower among patients who demonstrated bronchiectasis on the day 14 HRCT scan (P = .008).ConclusionsIn patients with ARDS, diminished lung compliance measured bedside was associated with radiologic fibroproliferation 14 days post diagnosis. Establishing factors that predispose to development of excessive fibroproliferation with subsequent confirmation by chest HRCT scan represents a promising strategy to identify patients with ARDS at risk for poorer clinical outcomes.
| S-EPMC4219337 | biostudies-literature
Project description:Automatic segmentation of abdominal anatomy on computed tomography (CT) images can support diagnosis, treatment planning, and treatment delivery workflows. Segmentation methods using statistical models and multi-atlas label fusion (MALF) require inter-subject image registrations, which are challenging for abdominal images, but alternative methods without registration have not yet achieved higher accuracy for most abdominal organs. We present a registration-free deep-learning-based segmentation algorithm for eight organs that are relevant for navigation in endoscopic pancreatic and biliary procedures, including the pancreas, the gastrointestinal tract (esophagus, stomach, and duodenum) and surrounding organs (liver, spleen, left kidney, and gallbladder). We directly compared the segmentation accuracy of the proposed method to the existing deep learning and MALF methods in a cross-validation on a multi-centre data set with 90 subjects. The proposed method yielded significantly higher Dice scores for all organs and lower mean absolute distances for most organs, including Dice scores of 0.78 versus 0.71, 0.74, and 0.74 for the pancreas, 0.90 versus 0.85, 0.87, and 0.83 for the stomach, and 0.76 versus 0.68, 0.69, and 0.66 for the esophagus. We conclude that the deep-learning-based segmentation represents a registration-free method for multi-organ abdominal CT segmentation whose accuracy can surpass current methods, potentially supporting image-guided navigation in gastrointestinal endoscopy procedures.
| S-EPMC6076994 | biostudies-literature
Project description:ObjectivesTo evaluate the performance of an engineered machine learning algorithm to identify kidney stones and measure stone characteristics without the need for human input.MethodsWe performed a cross-sectional study of 94 children and adults who had kidney stones identified on non-contrast CT. A previously developed deep learning algorithm was trained to segment renal anatomy and kidney stones and to measure stone features. The performance and speed of the algorithm to measure renal anatomy and kidney stone features were compared to the current gold standard of human measurement performed by 3 independent reviewers.ResultsThe algorithm was 100% sensitive and 100% specific in detecting individual kidney stones. The mean stone volume segmented by the algorithm was smaller than that of human reviewers and had moderate overlap (Dice score: 0.66). There was substantial variation between human reviewers in total segmented stone volume (Jaccard score: 0.17) and volume of the single largest stone (Jaccard score: 0.33). Stone segmentations performed by the machine learning algorithm more precisely approximated stone borders than those performed by human reviewers on qualitative assessment.ConclusionAn engineered machine learning algorithm can identify and characterize stones more accurately and reliably than humans, which has the potential to improve the precision and efficiency of assessing kidney stone burden.
| S-EPMC9936246 | biostudies-literature
Project description:The World Health Organization (WHO) has declared Coronavirus Disease 2019 (COVID-19) as one of the highly contagious diseases and considered this epidemic as a global health emergency. Therefore, medical professionals urgently need an early diagnosis method for this new type of disease as soon as possible. In this research work, a new early screening method for the investigation of COVID-19 pneumonia using chest CT scan images has been introduced. For this purpose, a new image segmentation method based on K-means clustering algorithm (KMC) and novel fast forward quantum optimization algorithm (FFQOA) is proposed. The proposed method, called FFQOAK (FFQOA+KMC), initiates by clustering gray level values with the KMC algorithm and generating an optimal segmented image with the FFQOA. The main objective of the proposed FFQOAK is to segment the chest CT scan images so that infected regions can be accurately detected. The proposed method is verified and validated with different chest CT scan images of COVID-19 patients. The segmented images obtained using FFQOAK method are compared with various benchmark image segmentation methods. The proposed method achieves mean squared error, peak signal-to-noise ratio, Jaccard similarity coefficient and correlation coefficient of 712.30, 19.61, 0.90 and 0.91 in case of four experimental sets, namely Experimental_Set_1, Experimental_Set_2, Experimental_Set_3 and Experimental_Set_4, respectively. These four performance evaluation metrics show the effectiveness of FFQOAK method over these existing methods.
| S-EPMC8316646 | biostudies-literature
Project description:ObjectivesTo develop a fully automatic multiview shape constraint framework for comprehensive coronary artery calcium scores (CACS) quantification via deep learning on nonenhanced cardiac CT images.MethodsIn this retrospective single-centre study, a multi-task deep learning framework was proposed to detect and quantify coronary artery calcification from CT images collected between October 2018 and March 2019. A total of 232 non-contrast cardiac-gated CT scans were retrieved and studied (80 % for model training and 20 % for testing). CACS results of testing datasets (n = 46), including Agatston score, calcium volume score, calcium mass score, were calculated fully automatically and manually at total and vessel-specific levels, respectively.ResultsNo significant differences were found in CACS quantification obtained using automatic or manual methods at total and vessel-specific levels (Agatston score: automatic 535.3 vs. manual 542.0, P = 0.993; calcium volume score: automatic 454.2 vs. manual 460.6, P = 0.990; calcium mass score: automatic 128.9 vs. manual 129.5, P = 0.992). Compared to the ground truth, the number of calcified vessels can be accurate recognized automatically (total: automatic 107 vs. manual 102, P = 0.125; left main artery: automatic 15 vs. manual 14, P = 1.000 ; left ascending artery: automatic 37 vs. manual 37, P = 1.000; left circumflex artery: automatic 22 vs. manual 20, P = 0.625; right coronary artery: automatic 33 vs. manual 31, P = 0.500). At the patient's level, there was no statistic difference existed in the classification of Agatston scoring (P = 0.317) and the number of calcified vessels (P = 0.102) between the automatic and manual results.ConclusionsThe proposed framework can achieve reliable and comprehensive quantification for the CACS, including the calcified extent and distribution indicators at both total and vessel-specific levels.
| S-EPMC7814341 | biostudies-literature