Mitsutaka Nemoto

A pilot study of architectural distortion detection in mammograms based on characteristics of line shadows

ObjectiveWe present herein a novel algorithm for architectural distortion detection that utilizes the point convergence index with the likelihood of lines (e.g., spiculations) relating to architectural distortion.Materials and methodsValidation was performed using 25 computed radiography (CR) mammograms, each of which has an architectural distortion with radiating spiculations. The proposed method comprises five steps. First, the lines were extracted on mammograms, such as spiculations of architectural distortion as well as lines in the mammary gland. Second, the likelihood of spiculation for each extracted line was calculated. In the third step, point convergence index weighted by this likelihood was evaluated at each pixel to enhance distortion only. Fourth, local maxima of the index were extracted as candidates for the distortion, then classified based on nine features in the last step.ResultsPoint convergence index without the proposed likelihood generated 84.48/image false-positives (FPs) on average. Conversely, the proposed index succeeded in decreasing this number to 12.48/image on average when sensitivity was 100%. After the classification step, number of FPs was reduced to 0.80/image with 80.0% sensitivity.ConclusionCombination of the likelihood of lines with point convergence index is effective in extracting architectural distortion with radiating spiculations.

Development of automatic visceral fat volume calculation software for CT volume data.

Objective. To develop automatic visceral fat volume calculation software for computed tomography (CT) volume data and to evaluate its feasibility. Methods. A total of 24 sets of whole-body CT volume data and anthropometric measurements were obtained, with three sets for each of four BMI categories (under 20, 20 to 25, 25 to 30, and over 30) in both sexes. True visceral fat volumes were defined on the basis of manual segmentation of the whole-body CT volume data by an experienced radiologist. Software to automatically calculate visceral fat volumes was developed using a region segmentation technique based on morphological analysis with CT value threshold. Automatically calculated visceral fat volumes were evaluated in terms of the correlation coefficient with the true volumes and the error relative to the true volume. Results. Automatic visceral fat volume calculation results of all 24 data sets were obtained successfully and the average calculation time was 252.7 seconds/case. The correlation coefficients between the true visceral fat volume and the automatically calculated visceral fat volume were over 0.999. Conclusions. The newly developed software is feasible for calculating visceral fat volumes in a reasonable time and was proved to have high accuracy.

A unified framework for concurrent detection of anatomical landmarks for medical image understanding

Anatomical landmarks are useful as the primitive anatomical knowledge for medical image understanding. In this study, we construct a unified framework for automated detection of anatomical landmarks distributed within the human body. Our framework includes the following three elements; (1) initial candidate detection based on a local appearance matching technique based on appearance models built by PCA and the generative learning, (2) false positive elimination using classifier ensembles trained by MadaBoost, and (3) final landmark set determination based on a combination optimization method by Gibbs sampling with a priori knowledge of inter-landmark distances. In evaluation of our methods with 50 data sets of body trunk CT, the average sensitivity in detecting candidates of 165 landmarks was 0.948 ± 0.084 while 55 landmarks were detected with 100 % sensitivity. Initially, the amount of false positives per landmark was 462.2 ± 865.1 per case on average, then they were reduced to 152.8 ± 363.9 per case by the MadaBoost classifier ensembles without miss-elimination of the true landmarks. Finally 89.1 % of landmarks were correctly selected by the final combination optimization. These results showed that our framework is promising for an initial step for the subsequent anatomical structure recognition.

Automated segmentation method for spinal column based on a dual elliptic column model and its application for virtual spinal straightening.

Segmentation of vertebral bones in computed tomographic data is important as a first stage of image-based radiological tasks. However, it is a challenging problem to segment an affected spine correctly. In this study, we propose a new method of segmentation of thoracic and lumbar vertebral bodies from thin-slice computed tomographic images. Especially, we focus on a deformable model-based segmentation scheme to confirm the feasibility in clinical data sets with various bone diseases, such as bone metastases and scoliosis. As an application of this algorithm, virtual straightening of the thoracolumbar spine is also performed. Results on a database of 16 patients indicate the applicability of our method to spines affected by scoliosis and multiple bone metastases.

Automatic detection of over 100 anatomical landmarks in medical CT images: A framework with independent detectors and combinatorial optimization

&NA; An automatic detection method for 197 anatomically defined landmarks in computed tomography (CT) volumes is presented. The proposed method can handle missed landmarks caused by detection failure, a limited imaging range and other problems using a novel combinatorial optimization framework with a two‐stage sampling algorithm. After a list of candidates is generated by each landmark detector, the best combination of candidates is searched for by a combinatorial optimization algorithm using a landmark point distribution model (L‐PDM) to provide prior knowledge. Optimization is performed by simulated annealing and iterative Gibbs sampling. Prior to each cycle of Gibbs sampling, another sampling algorithm is processed to estimate the spatial distribution of each target landmark, so that landmark positions without any correct detector‐derived candidates can be estimated. The proposed method was evaluated using 104 CT volumes with various imaging ranges. The overall average detection distance error was 6.6 mm, and 83.8, 93.2 and 96.5% of landmarks were detected within 10, 15 and 20 mm from the ground truth, respectively. The proposed method worked even when most of the landmarks were outside of the imaging range. The identification accuracy of the vertebral centroid was also evaluated using public datasets and the proposed method could identify 70% of vertebrae including severely diseased ones. From these results, the feasibility of our framework in detecting multiple landmarks in various CT datasets was validated. HighlightsNovel landmark detection framework for over 100 anatomical landmarks.Handling missing landmarks caused by detection failure or a limited imaging range.Estimation of the positions of missing landmarks.A stochastic model of a general landmark detector.Validation with various CT datasets, e.g. different imaging ranges. Graphical abstract Figure. Image, graphical abstract

Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography

The usefulness of computer‐assisted detection (CAD) for detecting cerebral aneurysms has been reported; therefore, the improved performance of CAD will help to detect cerebral aneurysms.

Feasibility Study of a Generalized Framework for Developing Computer-Aided Detection Systems—a New Paradigm

We propose a generalized framework for developing computer-aided detection (CADe) systems whose characteristics depend only on those of the training dataset. The purpose of this study is to show the feasibility of the framework. Two different CADe systems were experimentally developed by a prototype of the framework, but with different training datasets. The CADe systems include four components; preprocessing, candidate area extraction, candidate detection, and candidate classification. Four pretrained algorithms with dedicated optimization/setting methods corresponding to the respective components were prepared in advance. The pretrained algorithms were sequentially trained in the order of processing of the components. In this study, two different datasets, brain MRA with cerebral aneurysms and chest CT with lung nodules, were collected to develop two different types of CADe systems in the framework. The performances of the developed CADe systems were evaluated by threefold cross-validation. The CADe systems for detecting cerebral aneurysms in brain MRAs and for detecting lung nodules in chest CTs were successfully developed using the respective datasets. The framework was shown to be feasible by the successful development of the two different types of CADe systems. The feasibility of this framework shows promise for a new paradigm in the development of CADe systems: development of CADe systems without any lesion specific algorithm designing.

Study on cascade classification in abnormal shadow detection for mammograms

Classifier plays an important role in a system detecting abnormal shadows from mammograms. In this paper, we propose the novel classification system that cascades four weak classifiers and a classifier ensemble to improve both computational cost and classification accuracy. The first several weak classifiers eliminate a large number of false positives in a short time which are easy to distinguish from abnormal regions, and the final classifier ensemble focuses on the remaining candidate regions difficult to classify, which results in high accuracy. We also show the experimental results using 2,564 mammograms.

Training Strategy for Performance Improvement in Computer-Assisted Detection of Lesions: Based on Multi-institutional Study in Teleradiology Environment

The performance of computer-assisted detection (CAD) software depends on quality and quantity of the dataset used for supervised learning. If the data characteristics in development and practical use are different, the performance of CAD software will be degraded. Therefore, it is necessary to continuously collect data for supervised learning in practical use, and to improve CAD software by retraining with the collected data. For this purpose, we developed a web-based CAD software processing and evaluation platform (CIRCUS CS), which provides on-line processing of CAD software and interfaces to evaluate the results obtained from CAD software. For a multi-institutional study, we implemented CIRCUS CS into a teleradiology environment, which has been in practical use since September 2011. In this study, we investigated the performance improvement of CAD software for each institution based on retraining through a simulation-based study. According to the results, the performance of CAD software for each institution was improved by retraining.

A Multiple Anatomical Landmark Detection System for Body CT Images

Automatic detection of anatomical landmarks has wide range of application in medical image analysis. In this short paper, we present a two-stage method to detect 181 landmarks simultaneously. In the first stage, each landmark is independently searched by a dedicated detector which outputs a list of candidate positions for the target landmark. Each detector is composed of an appearance-based initial detector and a classifier ensemble to estimate the probabilities of detected candidates and to eliminate false positives. Here, the appearance shape used in each detector is optimized by a cross-validation-based variable selection algorithm in advance. Then, in the following second stage, a single combination of all landmark positions is determined from all the candidate lists. The determination is performed by maximum a posteriori (MAP) estimation in which the posterior probability is calculated from both the likelihoods of detected candidates (estimated by the classifier ensemble) and a statistical spatial distribution model of the all landmarks. This MAP estimation process can also determine whether each landmark is within the given CT volume or out of the imaging range. The proposed system was trained for 181 landmarks with 60 human torso CT datasets and evaluated with another 60 datasets. The datasets include both plain CT and contrast enhanced CT volumes with various imaging ranges. In the result, 69.0% and 87.9% of the landmarks were successfully detected within 1 and 2 cm from the ground truth point, respectively. The average detection error was 9.58 mm. From these results, applicability of the proposed system to various CT datasets was verified.