Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers.

We aimed to develop a new artificial intelligence software that can automatically extract and measure the volume of white matter hyperintensities (WMHs) in head magnetic resonance imaging (MRI) using only thick-slice fluid-attenuated inversion recovery (FLAIR) sequences from multiple centers. We enrolled 1092 participants in Japan, comprising the thick-slice Private Dataset. Based on 207 randomly selected participants, neuroradiologists annotated WMHs using predefined guidelines. The annotated images of participants were divided into training (n = 138) and test (n = 69) datasets. The WMH segmentation model comprised a U-Net ensemble and was trained using the Private Dataset. Two other models were trained for validation using either both thin- and thick-slice MRI datasets or the thin-slice dataset alone. The voxel-wise Dice similarity coefficient (DSC) was used as the evaluation metric. The model trained using only thick-slice MRI showed a DSC of 0.820 for the test dataset, which is comparable to the accuracy of human readers. The model trained with the additional thin-slice dataset showed only a slightly improved DSC of 0.822. This automatic WMH segmentation model comprising a U-Net ensemble trained on a thick-slice FLAIR MRI dataset is a promising new method. Despite some limitations, this model may be applicable in clinical practice.

Seasonal pigment fluctuation in diploid and polyploid Arabidopsis revealed by machine learning-based phenotyping method PlantServation.

Long-term field monitoring of leaf pigment content is informative for understanding plant responses to environments distinct from regulated chambers but is impractical by conventional destructive measurements. We developed PlantServation, a method incorporating robust image-acquisition hardware and deep learning-based software that extracts leaf color by detecting plant individuals automatically. As a case study, we applied PlantServation to examine environmental and genotypic effects on the pigment anthocyanin content estimated from leaf color. We processed >4 million images of small individuals of four Arabidopsis species in the field, where the plant shape, color, and background vary over months. Past radiation, coldness, and precipitation significantly affected the anthocyanin content. The synthetic allopolyploid A. kamchatica recapitulated the fluctuations of natural polyploids by integrating diploid responses. The data support a long-standing hypothesis stating that allopolyploids can inherit and combine the traits of progenitors. PlantServation facilitates the study of plant responses to complex environments termed "in natura".

Effectiveness of tuning an artificial intelligence algorithm for cerebral aneurysm diagnosis: a study of 10,000 consecutive cases.

Diagnostic image analysis for unruptured cerebral aneurysms using artificial intelligence has a very high sensitivity. However, further improvement is needed because of a relatively high number of false positives. This study aimed to confirm the clinical utility of tuning an artificial intelligence algorithm for cerebral aneurysm diagnosis. We extracted 10,000 magnetic resonance imaging scans of participants who underwent brain screening using the "Brain Dock" system. The sensitivity and false positives/case for aneurysm detection were compared before and after tuning the algorithm. The initial diagnosis included only cases for which feedback to the algorithm was provided. In the primary analysis, the sensitivity of aneurysm diagnosis decreased from 96.5 to 90% and the false positives/case improved from 2.06 to 0.99 after tuning the algorithm (P < 0.001). In the secondary analysis, the sensitivity of aneurysm diagnosis decreased from 98.8 to 94.6% and the false positives/case improved from 1.99 to 1.03 after tuning the algorithm (P < 0.001). The false positives/case reduced without a significant decrease in sensitivity. Using large clinical datasets, we demonstrated that by tuning the algorithm, we could significantly reduce false positives with a minimal decline in sensitivity.

Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method.

We developed and validated a deep learning (DL)-based model using the segmentation method and assessed its ability to detect lung cancer on chest radiographs. Chest radiographs for use as a training dataset and a test dataset were collected separately from January 2006 to June 2018 at our hospital. The training dataset was used to train and validate the DL-based model with five-fold cross-validation. The model sensitivity and mean false positive indications per image (mFPI) were assessed with the independent test dataset. The training dataset included 629 radiographs with 652 nodules/masses and the test dataset included 151 radiographs with 159 nodules/masses. The DL-based model had a sensitivity of 0.73 with 0.13 mFPI in the test dataset. Sensitivity was lower in lung cancers that overlapped with blind spots such as pulmonary apices, pulmonary hila, chest wall, heart, and sub-diaphragmatic space (0.50-0.64) compared with those in non-overlapped locations (0.87). The dice coefficient for the 159 malignant lesions was on average 0.52. The DL-based model was able to detect lung cancers on chest radiographs, with low mFPI.

Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation.

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases.

Reducing adenoma miss rate of colonoscopy assisted by artificial intelligence: a multicenter randomized controlled trial.

BACKGROUND: We have developed the computer-aided detection (CADe) system using an original deep learning algorithm based on a convolutional neural network for assisting endoscopists in detecting colorectal lesions during colonoscopy. The aim of this study was to clarify whether adenoma miss rate (AMR) could be reduced with CADe assistance during screening and surveillance colonoscopy. METHODS: This study was a multicenter randomized controlled trial. Patients aged 40 to 80 years who were referred for colorectal screening or surveillance at four sites in Japan were randomly assigned at a 1:1 ratio to either the "standard colonoscopy (SC)-first group" or the "CADe-first group" to undergo a back-to-back tandem procedure. Tandem colonoscopies were performed on the same day for each participant by the same endoscopist in a preassigned order. All polyps detected in each pass were histopathologically diagnosed after biopsy or resection. RESULTS: A total of 358 patients were enrolled and 179 patients were assigned to the SC-first group or CADe-first group. The AMR of the CADe-first group was significantly lower than that of the SC-first group (13.8% vs. 36.7%, P < 0.0001). Similar results were observed for the polyp miss rate (14.2% vs. 40.6%, P < 0.0001) and sessile serrated lesion miss rate (13.0% vs. 38.5%, P = 0.03). The adenoma detection rate of CADe-assisted colonoscopy was 64.5%, which was significantly higher than that of standard colonoscopy (53.6%; P = 0.036). CONCLUSION: Our study results first showed a reduction in the AMR when assisting with CADe based on deep learning in a multicenter randomized controlled trial.

MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction.

BACKGROUND: Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer's disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. RESULTS: We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 [Formula: see text] loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average [Formula: see text] loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. CONCLUSIONS: Similar to physicians' way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans.

Incidental cerebral aneurysms detected by a computer-assisted detection system based on artificial intelligence: A case series.

RATIONALE: Computer-assisted detection (CAD) systems based on artificial intelligence (AI) using convolutional neural network (CNN) have been successfully used for the diagnosis of unruptured cerebral aneurysms in experimental situations. However, it is yet unclear whether CAD systems can detect cerebral aneurysms effectively in real-life clinical situations. This paper describes the diagnostic efficacy of CAD systems for cerebral aneurysms and the types of cerebral aneurysms that they can detect. PATIENT CONCERNS: From March 7, 2017 to August 26, 2018 we performed brain magnetic resonance imaging (MRI) scans for 1623 subjects, to rule out intracranial diseases. We retrospectively reviewed the medical records including the history and images for each patient. DIAGNOSES, INTERVENTIONS AND OUTCOMES: Among them, we encountered 5 cases in whom the cerebral aneurysms had been overlooked in the first and second round of imaging, and were detected for the first time by CAD. All missed aneurysms were less than 2 mm in diameter. Of the 5 aneurysms, 2 were internal carotid artery (ICA) paraclinoid aneurysms, 2 were Internal carotid-posterior communicating artery (IC-PC) aneurysms and 1 was a distal middle cerebral artery (MCA) aneurysm. LESSONS: Our CAD system can detect very small aneurysms masked by the surrounding arteries and difficult for radiologists to detect. In the future, CAD systems might pave the way to substitute the workload of diagnostic radiologists and reduce the cost of human labor.

IMACEL: A cloud-based bioimage analysis platform for morphological analysis and image classification.

Automated quantitative image analysis is essential for all fields of life science research. Although several software programs and algorithms have been developed for bioimage processing, an advanced knowledge of image processing techniques and high-performance computing resources are required to use them. Hence, we developed a cloud-based image analysis platform called IMACEL, which comprises morphological analysis and machine learning-based image classification. The unique click-based user interface of IMACEL's morphological analysis platform enables researchers with limited resources to evaluate particles rapidly and quantitatively without prior knowledge of image processing. Because all the image processing and machine learning algorithms are performed on high-performance virtual machines, users can access the same analytical environment from anywhere. A validation study of the morphological analysis and image classification of IMACEL was performed. The results indicate that this platform is an accessible and potentially powerful tool for the quantitative evaluation of bioimages that will lower the barriers to life science research.

Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms.

Purpose To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists. Materials and Methods MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated. Results The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm ± 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years ± 13) and 365 were on female patients (mean age, 64 years ± 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm ± 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years ± 12 and 67 years ± 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm ± 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years ± 12 and 68 years ± 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports. Conclusion A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports. © RSNA, 2018 See also the editorial by Flanders in this issue.