Using a Convolutional Neural Network and Convolutional Long Short-term Memory to Automatically Detect Aneurysms on 2D Digital Subtraction Angiography Images: Framework Development and Validation.

BACKGROUND: It is hard to distinguish cerebral aneurysms from overlapping vessels in 2D digital subtraction angiography (DSA) images due to these images' lack of spatial information. OBJECTIVE: The aims of this study were to (1) construct a deep learning diagnostic system to improve the ability to detect posterior communicating artery aneurysms on 2D DSA images and (2) validate the efficiency of the deep learning diagnostic system in 2D DSA aneurysm detection. METHODS: We proposed a 2-stage detection system. First, we established the region localization stage to automatically locate specific detection regions of raw 2D DSA sequences. Second, in the intracranial aneurysm detection stage, we constructed a bi-input+RetinaNet+convolutional long short-term memory (C-LSTM) framework to compare its performance for aneurysm detection with that of 3 existing frameworks. Each of the frameworks had a 5-fold cross-validation scheme. The receiver operating characteristic curve, the area under the curve (AUC) value, mean average precision, sensitivity, specificity, and accuracy were used to assess the abilities of different frameworks. RESULTS: A total of 255 patients with posterior communicating artery aneurysms and 20 patients without aneurysms were included in this study. The best AUC values of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks were 0.95, 0.96, 0.92, and 0.97, respectively. The mean sensitivities of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 89% (range 67.02%-98.43%), 88% (range 65.76%-98.06%), 87% (range 64.53%-97.66%), 89% (range 67.02%-98.43%), and 90% (range 68.30%-98.77%), respectively. The mean specificities of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 80% (range 56.34%-94.27%), 89% (range 67.02%-98.43%), 86% (range 63.31%-97.24%), 93% (range 72.30%-99.56%), and 90% (range 68.30%-98.77%), respectively. The mean accuracies of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 84.50% (range 69.57%-93.97%), 88.50% (range 74.44%-96.39%), 86.50% (range 71.97%-95.22%), 91% (range 77.63%-97.72%), and 90% (range 76.34%-97.21%), respectively. CONCLUSIONS: According to our results, more spatial and temporal information can help improve the performance of the frameworks. Therefore, the bi-input+RetinaNet+C-LSTM framework had the best performance when compared to that of the other frameworks. Our study demonstrates that our system can assist physicians in detecting intracranial aneurysms on 2D DSA images.

A machine learning-based prognostic predictor for stage III colon cancer.

Limited biomarkers have been identified as prognostic predictors for stage III colon cancer. To combat this shortfall, we developed a computer-aided approach which combing convolutional neural network with machine classifier to predict the prognosis of stage III colon cancer from routinely haematoxylin and eosin (H&E) stained tissue slides. We trained the model by using 101 cancers from West China Hospital (WCH). The predictive effectivity of the model was validated by using 67 cancers from WCH and 47 cancers from The Cancer Genome Atlas Colon Adenocarcinoma database. The selected model (Gradient Boosting-Colon) provided a hazard ratio (HR) for high- vs. low-risk recurrence of 8.976 (95% confidence interval (CI), 2.824-28.528; P, 0.000), and 10.273 (95% CI, 2.177-48.472; P, 0.003) in the two test groups, from the multivariate Cox proportional hazards analysis. It gave a HR value of 10.687(95% CI, 2.908-39.272; P, 0.001) and 5.033 (95% CI,1.792-14.132; P, 0.002) for the poor vs. good prognosis groups. Gradient Boosting-Colon is an independent machine prognostic predictor which allows stratification of stage III colon cancer into high- and low-risk recurrence groups, and poor and good prognosis groups directly from the H&E tissue slides. Our findings could provide crucial information to aid treatment planning during stage III colon cancer.

A machine learning model to precisely immunohistochemically classify pituitary adenoma subtypes with radiomics based on preoperative magnetic resonance imaging.

PURPOSE: The type of pituitary adenoma (PA) cannot be clearly recognized with preoperative magnetic resonance imaging (MRI) but can be classified with immunohistochemical staining after surgery. In this study, a model to precisely immunohistochemically classify the PA subtypes by radiomic features based on preoperative MR images was developed. METHODS: Two hundred thirty-five pathologically diagnosed PAs, including t-box pituitary transcription factor (Tpit) family tumors (n = 55), pituitary transcription factor 1 (Pit-1) family tumors (n = 110), and steroidogenic factor 1 (SF-1) family tumors (n = 70), were retrospectively studied. T1-weighted, T2-weighted and contrast-enhanced T1-weighted images were obtained from all patients. Through imaging acquisition, feature extraction and radiomic data processing, 18 radiomic features were used to train support vector machine (SVM), k-nearest neighbors (KNN) and Naïve Bayes (NBs) models. Ten-fold cross-validation was applied to evaluate the performance of these models. RESULTS: The SVM model showed high performance (balanced accuracy 0.89, AUC 0.9549) whereas the KNN (balanced accuracy 0.83, AUC 0.9266) and NBs (balanced accuracy 0.80, AUC 0.9324) models displayed low performance based on the T2-weighted images. The performance of the T2-weighted images was better than that of the other two MR sequences. Additionally, significant sensitivity (P = 0.031) and specificity (P = 0.012) differences were observed when classifying the PA subtypes by T2-weighted images. CONCLUSIONS: The SVM model was superior to the KNN and NBs models and can potentially precisely immunohistochemically classify PA subtypes with an MR-based radiomic analysis. The developed model exhibited good performance using T2-weighted images and might offer potential guidance to neurosurgeons in clinical decision-making before surgery.

Automatic detection on intracranial aneurysm from digital subtraction angiography with cascade convolutional neural networks.

BACKGROUND: An intracranial aneurysm is a cerebrovascular disorder that can result in various diseases. Clinically, diagnosis of an intracranial aneurysm utilizes digital subtraction angiography (DSA) modality as gold standard. The existing automatic computer-aided diagnosis (CAD) research studies with DSA modality were based on classical digital image processing (DIP) methods. However, the classical feature extraction methods were badly hampered by complex vascular distribution, and the sliding window methods were time-consuming during searching and feature extraction. Therefore, developing an accurate and efficient CAD method to detect intracranial aneurysms on DSA images is a meaningful task. METHODS: In this study, we proposed a two-stage convolutional neural network (CNN) architecture to automatically detect intracranial aneurysms on 2D-DSA images. In region localization stage (RLS), our detection system can locate a specific region to reduce the interference of the other regions. Then, in aneurysm detection stage (ADS), the detector could combine the information of frontal and lateral angiographic view to identify intracranial aneurysms, with a false-positive suppression algorithm. RESULTS: Our study was experimented on posterior communicating artery (PCoA) region of internal carotid artery (ICA). The data set contained 241 subjects for model training, and 40 prospectively collected subjects for testing. Compared with the classical DIP method which had an accuracy of 62.5% and an area under curve (AUC) of 0.69, the proposed architecture could achieve accuracy of 93.5% and the AUC of 0.942. In addition, the detection time cost of our method was about 0.569 s, which was one hundred times faster than the classical DIP method of 62.546 s. CONCLUSION: The results illustrated that our proposed two-stage CNN-based architecture was more accurate and faster compared with the existing research studies of classical DIP methods. Overall, our study is a demonstration that it is feasible to assist physicians to detect intracranial aneurysm on DSA images using CNN.