Search

High-grade adenocarcinoma subtypes (micropapillary and solid) treated with sublobar resection have an unfavorable prognosis compared with those treated with lobectomy. We investigated the potential of incorporating solid attenuation component masks with deep learning in the prediction of high-grade components to optimize surgical strategy preoperatively.A total of 502 patients with pathologically confirmed high-grade adenocarcinomas were retrospectively enrolled between 2016 and 2020. The SACs attention DL model was developed to apply solid-attenuation-component-like subregion masks (tumor area ≥ - 190 HU) to guide the DL model for predicting high-grade subtypes. The SACA-DL was assessed using 5-fold cross-validation and external validation in the training and testing sets, respectively. The performance, which was evaluated using the area under the curve (AUC), was compared between SACA-DL and the DL model without SACs attention (DLWe classified 313 and 189 patients into training and testing cohorts, respectively. The SACA-DL achieved an AUC of 0.91 for the cross-validation, which was significantly superior to those of the DLThe combination of solid-attenuation-component-like subregion masks with the DL model is a promising approach for the preoperative prediction of high-grade adenocarcinoma subtypes.

Longitudinal image registration of pulmonary computed tomography (PCT) images may serve as an essential tool for investigating the relationship between radiation dose distribution and the occurrence and phenotype of radiation-induced lung disease (RILD). Although numerous longitudinal registration algorithms have been developed for PCT, most similarity-based approaches are not suitable for PCT involving RILD due to the complex tissue variation between two PCT images. Moreover, conventional feature-based approaches might fail to find a sufficient number of matched pairs of feature points due to the disparate lung deformation caused by breathing and RILD. To overcome the challenges resulting from RILD, component structure coherence point drift (CSCPD) was proposed to establish a deformation model by decomposing the chest into several components and matching them with individual parameters based on coherence point drift (CPD). Moreover, a regional vascular point matching (RVPM) algorithm was proposed to generate a vascular subtree and to substantially increase the number of corresponding pairs between two images. Eventually, the components were recomposed and aligned by a thin plate spline algorithm. A performance assessment on 15 pairs of PCT images of patients with RILD yielded recall and precision values of 0.85 and 0.89 for RVPM, respectively. Moreover, the target registration error of CSCPD with RVPM (2.3 ± 1.79) was significantly better than that of conventional CPD with RVPM (2.95 ± 1.89) and conventional CPD (5.04 ± 2.87). Therefore, the proposed registration system is robust enough to address the disparate deformation of lungs with RILD, and it improves registration accuracy within the parenchyma.

Near-pure lung adenocarcinoma (ADC) subtypes demonstrate strong stratification of radiomic values, providing basic information for pathological subtyping. We sought to predict the presence of high-grade (micropapillary and solid) components in lung ADCs using quantitative image analysis with near-pure radiomic values. Overall, 103 patients with lung ADCs of various histological subtypes were enrolled for 10-repetition, 3-fold cross-validation (cohort 1); 55 were enrolled for testing (cohort 2). Histogram and textural features on computed tomography (CT) images were assessed based on the “near-pure” pathological subtype data. Patch-wise high-grade likelihood prediction was performed for each voxel within the tumour region. The presence of high-grade components was then determined based on a volume percentage threshold of the high-grade likelihood area. To compare with quantitative approaches, consolidation/tumour (C/T) ratio was evaluated on CT images; we applied radiological invasiveness (C/T ratio > 0.5) for the prediction. In cohort 1, patch-wise prediction, combined model (C/T ratio and patch-wise prediction), whole-lesion-based prediction (using only the “near-pure”-based prediction model), and radiological invasiveness achieved a sensitivity and specificity of 88.00 ± 2.33% and 75.75 ± 2.82%, 90.00 ± 0.00%, and 77.12 ± 2.67%, 66.67% and 90.41%, and 90.00% and 45.21%, respectively. The sensitivity and specificity, respectively, for cohort 2 were 100.0% and 95.35% using patch-wise prediction, 100.0% and 95.35% using combined model, 75.00% and 95.35% using whole-lesion-based prediction, and 100.0% and 69.77% using radiological invasiveness. Using near-pure radiomic features and patch-wise image analysis demonstrated high levels of sensitivity and moderate levels of specificity for high-grade ADC subtype-detecting. • The radiomic values extracted from lung adenocarcinoma with “near-pure” histological subtypes provide useful information for high-grade (micropapillary and solid) components detection. • Using near-pure radiomic features and patch-wise image analysis, high-grade components of lung adenocarcinoma can be predicted with high sensitivity and moderate specificity. • Using near-pure radiomic features and patch-wise image analysis has potential role in facilitating the prediction of the presence of high-grade components in lung adenocarcinoma prior to surgical resection.

OBJECTIVES Solitary pulmonary capillary haemangioma (SPCH) is a benign lung tumour that presents as ground-glass nodules on computed tomography (CT) images and mimics lepidic-predominant adenocarcinoma. This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from lepidic-predominant adenocarcinoma. METHODS In the adenocarcinoma group, all tumours were of the lepidic-predominant subtype with high purity (>70%). A classification model was proposed based on a two-level decision tree and 26 radiomic features extracted from each segmented lesion. For comparison, a baseline model was built with the same 26 features using a support vector machine as the classifier. Both models were assessed by the leave-one-out cross-validation method. RESULTS This study included 13 and 49 patients who underwent complete resection for SPCH and adenocarcinoma, respectively. Two sets of features were identified for discrimination between the 2 different histology types. The first set included 2 principal components corresponding to the 2 largest eigenvalues for the root node of the two-level decision tree. The second set comprised 4 selected radiomic features. The area under the receiver operating characteristic curve, accuracy, sensitivity, specificity were 0.954, 91.9%, 92.3% and 91.8% in the proposed classification model, and were 0.805, 85.5%, 61.5% and 91.8% in the baseline model, respectively. The proposed classification model significantly outperformed the baseline model (P CONCLUSIONS The proposed model could differentiate the 2 different histology types on CT images, and this may help surgeons to preoperatively discriminate SPCH from adenocarcinoma.

Background We aimed to establish a radiomic prediction model for tumor spread through air spaces (STAS) in lung adenocarcinoma using radiomic values from high-grade subtypes (solid and micropapillary). Methods We retrospectively reviewed 327 patients with lung adenocarcinoma from two institutes (Cohort 1: 227 patients; Cohort 2: 100 patients) between March 2017 and March 2019. STAS was identified in 113 (34.6%) patients. A high-grade likelihood prediction model was constructed based on a historical cohort of 82 patients with “near-pure” pathological subtype. The STAS prediction model based on the patch-wise mechanism identified the high-grade likelihood area for each voxel within the internal border of the tumor. STAS presence was indirectly predicted by a volume percentage threshold of the high-grade likelihood area. Performance was evaluated by receiver operating curve analysis with 10-repetition, 3-fold cross-validation in Cohort 1, and was individually tested in Cohort 2. Results Overall, 227 patients (STAS-positive: 77 [33.9%]) were enrolled for cross-validation (Cohort 1) while 100 (STAS-positive: 36 [36.0%]) underwent individual testing (Cohort 2). The gray level co-occurrence matrix (variance) and histogram (75th percentile) features were selected to construct the high-grade likelihood prediction model, which was used as the STAS prediction model. The proposed model achieved good performance in Cohort 1 with an area under the curve, sensitivity, and specificity, of 81.44%, 86.75%, and 62.60%, respectively, and correspondingly, in Cohort 2, they were 83.16%, 83.33%, and 63.90%, respectively. Conclusions The proposed computed tomography-based radiomic prediction model could help guide preoperative prediction of STAS in early-stage lung adenocarcinoma and relevant surgeries.

Solitary pulmonary capillary hemangioma (SPCH) is a benign lung tumor that presents as ground-glass nodules (GGN) on computed tomography (CT) images, mimicking lepidic-predominant adenocarcinoma (LPA). This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from LPA in lung GGNs. This study included 13 and 49 patients who underwent complete resection for lung SPCH and LPA, respectively. An SPCH/LPA classification model was proposed based on a two-level decision tree and 26 radiomic features extracted from each segmented lesion, including 5 and 21 features from the histogram and co-occurrence matrix, respectively. The two-level decision tree was constructed based on the training data with a support vector machine (SVM) as the classifier in each tree node. For comparison, a baseline model was built with the same 26 features using an SVM as the classifier. Both models were assessed by the leave-one-out cross-validation method. The area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity of the proposed SPCH/LPA model were 0.954, 91.9%, 92.3%, and 91.8%. The proposed SPCH/LPA model significantly outperformed the baseline model (p

Histological subtypes of lung adenocarcinomas (ADCs) classified by the International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society (IASLC/ATS/ERS) system have been investigated using radiomic approaches. However, the results have had limitations since80% of invasive lung ADCs were heterogeneous, with two or more subtypes. To reduce the influence of heterogeneity during radiomic analysis, computed tomography (CT) images of lung ADCs with near-pure ADC subtypes were analyzed to extract representative radiomic features of different subtypes.We enrolled 95 patients who underwent complete resection for lung ADC and a pathological diagnosis of a "near-pure" (≥70%) IASLC/ATS/ERS histological subtype. Conventional histogram/morphological features and complex radiomic features (grey-level-based statistical features and component variance-based features) of thin-cut CT data of tumor regions were analyzed. A prediction model based on leave-one-out cross-validation (LOOCV) and logistic regression (LR) was used to classify all five subtypes and three pathologic grades (lepidic, acinar/papillary, micropapillary/solid) of ADCs. The validation was performed using 36 near-pure ADCs in a later cohort.A total of 31 lepidic, 14 papillary, 32 acinar, 10 micropapillary, and 8 solid ADCs were analyzed. With 21 conventional and complex radiomic features, for 5 subtypes and 3 pathological grades, the prediction models achieved accuracy rates of 84.2% (80/95) and 91.6% (87/95), respectively, while accuracy was 71.6% and 85.3%, respectively, if only conventional features were used. The accuracy rate for the validation set (n = 36) was 83.3% (30/36) and 94.4% (34/36) in 5 subtypes and 3 pathological grades, respectively, using conventional and complex features, while it was 66.7% and 77.8% only using conventional features, respectively.Lung ADC with high purity pathological subtypes demonstrates strong stratification of radiomic values, which provide basic information for accurate pathological subtyping and image parcellation of tumor sub-regions.

This study explores the influence of prior information for deep learning networks to discriminate the benign and malignant of pulmonary tumors in computed tomography. In this study, because the number of nodule samples is sparse, this study proposes the concept of Multiple-Window to provide prior knowledge for Convolutional neural network (CNN). In the Multiple-Window CNN, we use the 5 windows including lung window, abdomen window, bone window, and chest window to generate the nodule sample. The sparse number of nodule samples, through the characteristics of the CT image dynamic range, make more prior information in a limited amount of data. The results show that the increase of suitably prior information (window channel) be included, CNN performance has improved. When the input is original dicom image, the accuracy of CNN is 0.82, sensitivity is 0.82, and specificity is 0.82. When the input is 4 kinds channel of window type, the accuracy is 0.9, sensitivity is 0.84, and specificity is 0.96.

Drosophila and human cardiac genes are very similar. Biological parametric studies on drosophila cardiac have improved our understanding of human cardiovascular disease. Drosophila cardiac consist of five circular chambers: a conical chamber (CC) and four ostia sections (O1–O4). Due to noise and grayscale discontinuity on optical coherence tomography (OCT) images, previous researches used manual counting or M-mode to analyze heartbeats, which are inefficient and time-consuming. An automated drosophila heartbeat counting algorithm based on the chamber segmentation is developed for OCT in this study. This algorithm has two parts: automated chamber segmentation and heartbeat counting. In addition, this study proposes a principal components analysis (PCA)-based supervised learning method for training the chamber contours to make chamber segmentation more accurate. The mean distances between the conical, second and third chambers attained by the proposed algorithm and the corresponding manually delineated boundaries defined by two experts were 1.26 ± 0.25, 1.47 ± 1.25 and 0.84 ± 0.60 (pixels), respectively. The area overlap similarities were 0.83 ± 0.09, 0.75 ± 0.11 and 0.74 ± 0.12 (pixels), respectively. The average calculated heart rates of two-week and six-week drosophila were about 4.77 beats/s and 4.73 beats/s, respectively, which was consistent with the results of manual counting.

Adenocarcinomas (ADC) is the major subtype of non-small cell lung cancers. Currently, surgery is used as the main approach for the treatment of the early-stage ADCs. However, different histological subtypes of ADC classified by the IASLC/ATS/ERS system may potentially impact on the surgical management, which subsequently influence the prognosis of the surgery. Thus, preoperative determination of ADC subtypes is essential and highly desirable. Nevertheless, the histological subtypes of ADCs may be either unknown or incompletely determined by biopsy before the surgery. Alternatively, the histological subtypes of ADCs may be predicted from the pulmonary computed tomographic (CT) images. However, previous studies showed limitations on the prediction results due to the complex composition of ADC subtypes. One possible reason is the radiomic descriptors used to differentiate different subtypes could be very different. The conventional approaches based on the same set of descriptors to distinguish all subtypes are inherently infeasible. Another possible reason is the complex composition of multiple subtypes in a lung nodule may hinder the extraction of effective radiomic descriptors to characterize each subtype. To overcome these challenges, a competing round-robin prediction model was proposed to predict the histological subtypes of ADCs, which was composed of three key ideas, namely, pair-specific radiomic descriptors for differentiation of every pair of subtypes, inter-regional descriptors for characterization of complex composition of subtypes in a nodule, and a multi-level round-robin classifier. Based on 70 ADCs patients, the proposed model achieved an accuracy of 86.3p in predicting five histological subtypes of adenocarcinomas.

Long-term comparisons of infrared image can facilitate the assessment of breast cancer tissue growth and early tumor detection, in which longitudinal infrared image registration is a necessary step. However, it is hard to keep markers attached on a body surface for weeks, and rather difficult to detect anatomic fiducial markers and match them in the infrared image during registration process. The proposed study, automatic longitudinal infrared registration algorithm, develops an automatic vascular intersection detection method and establishes feature descriptors by shape context to achieve robust matching, as well as to obtain control points for the deformation model. In addition, competitive winner-guided mechanism is developed for optimal corresponding. The proposed algorithm is evaluated in two ways. Results show that the algorithm can quickly lead to accurate image registration and that the effectiveness is superior to manual registration with a mean error being 0.91 pixels. These findings demonstrate that the proposed registration algorithm is reasonably accurate and provide a novel method of extracting a greater amount of useful data from infrared images.

Harris corner detectors, which depend on strong invariance and a local autocorrelation function, display poor detection performance for infrared (IR) images with low contrast and nonobvious edges. In addition, feature points detected by Harris corner detectors are clustered due to the numerous nonlocal maxima. This paper proposes a modified Harris corner detector that includes two unique steps for processing IR images in order to overcome the aforementioned problems. Image contrast enhancement based on a generalized form of histogram equalization (HE) combined with adjusting the intensity resolution causes false contours on IR images to acquire obvious edges. Adaptive nonmaximal suppression based on eliminating neighboring pixels avoids the clustered features. Preliminary results show that the proposed method can solve the clustering problem and successfully identify the representative feature points of IR breast images.

With the advent of depth enabled sensors and increasing needs in surveillance systems, we propose a novel framework to detect fine-grained human attributes (e.g., having backpack, talking on cell phone, wearing glasses) in the surveillance environments. Traditional detection and recognition methods generally suffer from the problems such as variations in lighting conditions, poses, and viewpoints of object instances. To tackle these problems, we propose a multi-view part-based attribute detecting system based on color-depth inputs instead of purely utilizing color images. We address several important attributes in the surveillance environments and train multiple attribute classifiers based on features inferred from 3D information to construct our discriminative model. Several state-of-the-art methods are compared and the experimental results show that our method is more robust under large variations in surveillance conditions.