Inconsistency between Human Observation and Deep Learning Models: Assessing Validity of Postmortem Computed Tomography Diagnosis of Drowning.

Drowning diagnosis is a complicated process in the autopsy, even with the assistance of autopsy imaging and the on-site information from where the body was found. Previous studies have developed well-performed deep learning (DL) models for drowning diagnosis. However, the validity of the DL models was not assessed, raising doubts about whether the learned features accurately represented the medical findings observed by human experts. In this paper, we assessed the medical validity of DL models that had achieved high classification performance for drowning diagnosis. This retrospective study included autopsy cases aged 8-91 years who underwent postmortem computed tomography between 2012 and 2021 (153 drowning and 160 non-drowning cases). We first trained three deep learning models from a previous work and generated saliency maps that highlight important features in the input. To assess the validity of models, pixel-level annotations were created by four radiological technologists and further quantitatively compared with the saliency maps. All the three models demonstrated high classification performance with areas under the receiver operating characteristic curves of 0.94, 0.97, and 0.98, respectively. On the other hand, the assessment results revealed unexpected inconsistency between annotations and models' saliency maps. In fact, each model had, respectively, around 30%, 40%, and 80% of irrelevant areas in the saliency maps, suggesting the predictions of the DL models might be unreliable. The result alerts us in the careful assessment of DL tools, even those with high classification performance.

How intra-source imbalanced datasets impact the performance of deep learning for COVID-19 diagnosis using chest X-ray images.

Over the past decade, the use of deep learning has been widely increasing in the medical image diagnosis field. Deep learning-based methods' (DLMs) performance strongly relies on training data. Therefore, researchers often focus on collecting as much data as possible from different medical facilities or developing approaches to avoid the impact of inter-category imbalance (ICI), which means a difference in data quantity among categories. However, due to the ICI within each medical facility, medical data are often isolated and acquired in different settings among medical facilities, known as the issue of intra-source imbalance (ISI) characteristic. This imbalance also impacts the performance of DLMs but receives negligible attention. In this study, we study the impact of the ISI on DLMs by comparison of the version of a deep learning model that was trained separately by an intra-source imbalanced chest X-ray (CXR) dataset and an intra-source balanced CXR dataset for COVID-19 diagnosis. The finding is that using the intra-source imbalanced dataset causes a serious training bias, although the dataset has a good inter-category balance. In contrast, the deep learning model performed a reliable diagnosis when trained on the intra-source balanced dataset. Therefore, our study reports clear evidence that the intra-source balance is vital for training data to minimize the risk of poor performance of DLMs.

Risk Analysis of Breast Cancer by Using Bilateral Mammographic Density Differences: A Case-Control Study.

The identification of risk factors helps radiologists assess the risk of breast cancer. Quantitative factors such as age and mammographic density are established risk factors for breast cancer. Asymmetric breast findings are frequently encountered during diagnostic mammography. The asymmetric area may indicate a developing mass in the early stage, causing a difference in mammographic density between the left and right sides. Therefore, this paper aims to propose a quantitative parameter named bilateral mammographic density difference (BMDD) for the quantification of breast asymmetry and to verify BMDD as a risk factor for breast cancer. To quantitatively evaluate breast asymmetry, we developed a semi-automatic method to estimate mammographic densities and calculate BMDD as the absolute difference between the left and right mammographic densities. And then, a retrospective case-control study, covering the period from July 2006 to October 2014, was conducted to analyse breast cancer risk in association with BMDD. The study included 364 women diagnosed with breast cancer and 364 matched control patients. As a result, a significant difference in BMDD was found between cases and controls (P < 0.001) and the case-control study demonstrated that women with BMDD > 10% had a 2.4-fold higher risk of breast cancer (odds ratio, 2.4; 95% confidence interval, 1.3-4.5) than women with BMDD ≤ 10%. In addition, we also demonstrated the positive association between BMDD and breast cancer risk among the subgroups with different ages and the Breast Imaging Reporting and Data System (BI-RADS) mammographic density categories. This study demonstrated that BMDD could be a potential risk factor for breast cancer.

Comprehensive evaluation of machine learning algorithms for predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability.

Introduction: Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV). Methods: Nine HRV indicators (features) and sleep-wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep-wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated-shallow sleep, deep sleep, and the two types of wake conditions-was also tested. Results and Discussion: In the test for predicting three types of sleep-wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82-0.88) and accuracy (0.78-0.81). The test using four types of sleep-wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep-wake conditions. Among the seven features, "the number of interval differences of successive RR intervals greater than 50 ms (NN50)" and "the proportion dividing NN50 by the total number of RR intervals (pNN50)" were useful to predict sleep-wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.

Deep Learning-Based Diagnosis of Fatal Hypothermia Using Post-Mortem Computed Tomography.

In forensic medicine, fatal hypothermia diagnosis is not always easy because findings are not specific, especially if traumatized. Post-mortem computed tomography (PMCT) is a useful adjunct to the cause-of-death diagnosis and some qualitative image character analysis, such as diffuse hyperaeration with decreased vascularity or pulmonary emphysema, have also been utilized for fatal hypothermia. However, it is challenging for inexperienced forensic pathologists to recognize the subtle differences of fatal hypothermia in PMCT images. In this study, we developed a deep learning-based diagnosis system for fatal hypothermia and explored the possibility of being an alternative diagnostic for forensic pathologists. An in-house dataset of forensic autopsy proven samples was used for the development and performance evaluation of the deep learning system. We used the area under the receiver operating characteristic curve (AUC) of the system for evaluation, and a human-expert comparable AUC value of 0.905, sensitivity of 0.948, and specificity of 0.741 were achieved. The experimental results clearly demonstrated the usefulness and feasibility of the deep learning system for fatal hypothermia diagnosis.

Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures With Gradient Learnings.

This letter summarizes and proves the concept of bounded-input bounded-state (BIBS) stability for weight convergence of a broad family of in-parameter-linear nonlinear neural architectures (IPLNAs) as it generally applies to a broad family of incremental gradient learning algorithms. A practical BIBS convergence condition results from the derived proofs for every individual learning point or batches for real-time applications.

A 2.5D Deep Learning-Based Method for Drowning Diagnosis Using Post-Mortem Computed Tomography.

It is challenging to diagnose drowning in autopsy even with the help of post-mortem multi-slice computed tomography (MSCT) due to the complex pathophysiology and the shortage of forensic specialists equipped with radiology knowledge. Therefore, a computer-aided diagnosis (CAD) system was developed to help with diagnosis. Most deep learning-based CAD systems only utilize 2D information, which is proper for 2D data such as chest X-ray images. However, 3D information should also be considered for 3D data like CT. Conventional 3D methods require a huge amount of data and computational cost when using 3D methods. In this article, we proposed a 2.5D method that converts 3D data into 2D images to train 2D deep learning models for drowning diagnosis. The key point of this 2.5D method is that it uses a subset to represent the whole case, covering this case as much as possible while avoiding other repetitive information. To evaluate the effectiveness of the proposed method, conventional 2D, previous 2.5D, and 3D deep learning-based methods were tested using an MSCT dataset obtained from Tohoku university. Then, to provide explainable diagnosis results, a visualization method called Gradient-weighted Class Activation Mapping was employed to visualize features relevant to drowning in CT images. Results on drowning diagnosis showed that our proposed method achieved the best performance compared to other 2D, 2.5D, and 3D methods. The visual assessment also demonstrated that our method could find the saliency regions corresponding to drowning.

Assessment of a computed tomography-based radiomics approach for assessing lung function in lung cancer patients.

PURPOSE: We aimed to assess radiomics approaches for estimating three pulmonary function test (PFT) results (forced expiratory volume in one second [FEV1], forced vital capacity [FVC], and the ratio of FEV1 to FVC [FEV1/FVC]) using data extracted from chest computed tomography (CT) images. METHODS: This retrospective study included 85 lung cancer patients (mean age, 75 years ±8; 69 men) who underwent stereotactic body radiotherapy between 2012 and 2020. Their pretreatment chest breath-hold CT and PFT data before radiotherapy were obtained. A total of 107 radiomics features (Shape: 14, Intensity: 18, Texture: 75) were extracted using two methods: extraction of the lung tissue (<-250 HU) (APPROACH 1), and extraction of small blood vessels and lung tissue (APPROACH 2). The PFT results were estimated using the least absolute shrinkage and selection operator regression. Pearson's correlation coefficients (r) were determined for all PFT results, and the area under the curve (AUC) was calculated for FEV1/FVC (<70 %). Finally, we compared our approaches with the conventional formula (Conventional). RESULTS: For the estimated FEV1/FVC, the Pearson's r were 0.21 (P =.06), 0.69 (P <.01), and 0.73 (P <.01) for Conventional, APPROACH 1, and APPROACH 2, respectively; the AUCs for FEV1/FVC (<70 %) were 0.67 (95 % confidence interval [CI]: 0.55, 0.79), 0.82 (CI: 0.72, 0.91; P =.047) and 0.86 (CI: 0.78, 0.94; P =.01), respectively. CONCLUSIONS: The radiomics approach performed better than the conventional equation and may be useful for assessing lung function based on CT images.

Heart Rate Information-Based Machine Learning Prediction of Emotions Among Pregnant Women.

In this study, the extent to which different emotions of pregnant women can be predicted based on heart rate-relevant information as indicators of autonomic nervous system functioning was explored using various machine learning algorithms. Nine heart rate-relevant autonomic system indicators, including the coefficient of variation R-R interval (CVRR), standard deviation of all NN intervals (SDNN), and square root of the mean squared differences of successive NN intervals (RMSSD), were measured using a heart rate monitor (MyBeat) and four different emotions including "happy," as a positive emotion and "anxiety," "sad," "frustrated," as negative emotions were self-recorded on a smartphone application, during 1 week starting from 23rd to 32nd weeks of pregnancy from 85 pregnant women. The k-nearest neighbor (k-NN), support vector machine (SVM), logistic regression (LR), random forest (RF), naïve bayes (NB), decision tree (DT), gradient boosting trees (GBT), stochastic gradient descent (SGD), extreme gradient boosting (XGBoost), and artificial neural network (ANN) machine learning methods were applied to predict the four different emotions based on the heart rate-relevant information. To predict four different emotions, RF also showed a modest area under the receiver operating characteristic curve (AUC-ROC) of 0.70. CVRR, RMSSD, SDNN, high frequency (HF), and low frequency (LF) mostly contributed to the predictions. GBT displayed the second highest AUC (0.69). Comprehensive analyses revealed the benefits of the prediction accuracy of the RF and GBT methods and were beneficial to establish models to predict emotions based on autonomic nervous system indicators. The results implicated SDNN, RMSSD, CVRR, LF, and HF as important parameters for the predictions.

A Deep Learning Aided Drowning Diagnosis for Forensic Investigations using Post-Mortem Lung CT Images.

Feasibility of computer-aided diagnosis (CAD) systems has been demonstrated in the field of medical image diagnosis. Especially, deep learning based CAD systems showed high performance thanks to its capability of image recognition. However, there is no CAD system developed for post-mortem imaging diagnosis and thus it is still unclear if the CAD system is effective for this purpose. Particulally, the drowning diagnosis is one of the most difficult tasks in the field of forensic medicine because findings of the post-mortem image diagnosis are not specific. To address this issue, we develop a CAD system consisting of a deep convolution neural network (DCNN) to classify post-mortem lung computed tomography (CT) images into two categories of drowning and non-drowning cases. The DCNN was trained by means of transfer learning and performance evaluation was conducted by 10-fold cross validation using 140 drowning cases and 140 non-drowning cases of the CT images. The area under the receiver operating characteristic curve (AUC-ROC) for the DCNN was achieved 0.88 in average. This high performance clearly demonstrated that the proposed DCNN based CAD system has a potential for post-mortem image diagnosis of drowning.

Comparison of Visible and Infrared Video Plethysmography Captured from Different Regions of the Human Face.

Recently, video plethysmography (VPG) - a heart rate estimation technique using a video camera - has gained significant attention. Most studies of VPG have used a visible RGB camera; only a limited number of studies investigating near-infrared light (wavelength 750-2500 nm), which can be used even in a dark environment, have been performed. The purpose of this study was to investigate the differences between VPG data collected using visible light (VPGVIS) or near-infrared light (VPGNIR) from four facial areas (forehead, right cheek, left cheek, and nose). An experiment was conducted to obtain both VPGVIS and VPGNIR simultaneously by alternately irradiating the face with NIR and VIS lights. Experimental results showed that the root mean squared error of heart rate estimated using VPGNIR was 1 bpm higher than that of VPGVIS. However, contrary to our expectations, the power of the heartbeat-related component included in VPGNIR was not reduced despite the absorbance of hemoglobin in the NIR light range being 1/100 of that in the VIS light range. This result supports the hypothesis that a main factor in the generation of VPG waves was change in the optical properties caused by blood vessels compressing the subcutaneous tissue and the venous bed. Additionally, the accuracy of the heart rate estimation using VPG tended to be high when the nose was set as the ROI. This result was likely associated with the anatomical structure of the nose.

Estimation of Absolute Blood Pressure Using Video Images Captured at Different Heights from the Heart.

The risk of cardiovascular diseases is related to the absolute level of blood pressure as well as its fluctuation while sleeping or during daily activities. To assess the risk, a simpler method to monitor daily blood pressure is desirable. In recent years, there has been a focus on developing a method to obtain pulse waves from video images of the human body. This is a promising technique to acquire biometric information without contact. In this study, we propose a new method to estimate the absolute level of blood pressure by using two video images of human hands captured at different heights from the heart. We focus on the amplitude difference of pulse waves obtained from the video images and derive an equation to estimate blood pressure based on the relationship between the internal pressure and the cross-sectional area of the blood vessel. The accuracy of the estimation was evaluated using data obtained from 5 healthy subjects performing cycling exercises that change their blood pressure. The average value of the root mean square error between the real value and the estimated value was 25.7 mmHg, while that of correlation coefficient was 0.66. There were large individual differences, particularly in the estimation of the absolute value of blood pressure. This result suggests the need for individual correction of the compliance curve, which represents the relationship between the internal pressure and the cross-sectional area of the blood vessel.

Potential improvements of lung and prostate MLC tracking investigated by treatment simulations.

PURPOSE/OBJECTIVES: Intrafraction tumor motion during external radiotherapy is a challenge for the treatment accuracy. A novel technique to mitigate the impact of tumor motion is real-time adaptation of the multileaf collimator (MLC) aperture to the motion, also known as MLC tracking. Although MLC tracking improves the dosimetric accuracy, there are still residual errors. Here, we investigate and rank the performance of five prediction algorithms and seven improvements of an MLC tracking system by extensive tracking treatment simulations. MATERIALS AND METHODS: An in-house-developed MLC tracking simulator that has been experimentally validated against an electromagnetic-guided MLC tracking system was used to test the prediction algorithms and tracking system improvements. The simulator requires a Dicom treatment plan and a motion trajectory as input and outputs all motion of the accelerator during MLC tracking treatment delivery. For lung tumors, MLC tracking treatments were simulated with a low and a high modulation VMAT plan using 99 patient-measured lung tumor trajectories. For prostate, tracking was also simulated with a low and a high modulation VMAT plan, but with 695 prostate trajectories. For each simulated treatment, the tracking error was quantified as the mean MLC exposure error, which is the sum of the overexposed area (irradiated area that should have been shielded according to the treatment plan) and the underexposed area (shielded area that should have been irradiated). First, MLC tracking was simulated with the current MLC tracking system without prediction, with perfect prediction (Perfect), and with the following five prediction algorithms: linear Kalman filter (Kalman), kernel density estimation (KDE), linear adaptive filtering (LAF), wavelet-based multiscale autoregression (wLMS), and time variant seasonal autoregression (TVSAR). Next, MLC tracking was simulated using the best prediction algorithm and seven different tracking system improvements: no localization signal latency (a), doubled maximum MLC leaf speed (b), halved MLC leaf width (c), use of Y backup jaws to track motion perpendicular to the MLC leaves (d), dynamic collimator rotation for alignment of the MLC leaves with the dominant target motion direction (e), improvements 4 and 5 combined (f), and all improvements combined (g). RESULTS: All results are presented as the mean residual MLC exposure error compared to no tracking. In the prediction study, the residual MLC exposure error was 47.0% (no prediction), 45.1% (Kalman), 43.8% (KDE), 43.7% (LAF), 42.1% (wLMS), 40.1% (TVSAR), and 36.5% (Perfect) for lung MLC tracking. For prostate MLC tracking, it was 66.0% (no prediction), 66.9% (Kalman), and 63.4% (Perfect). For lung with TVSAR prediction, the residual MLC exposure error for the seven tracking system improvements was 37.2%(1), 38.3%(2), 37.4%(3), 34.2%(4), 30.6%(5), 27.7%(6), and 20.7%(7). For prostate with no prediction, the residual MLC exposure error was 61.7%(1), 61.4%(2), 55.4%(3), 57.2%(4), 47.5%(5), 43.7%(6), and 38.7%(7). CONCLUSION: For prostate, MLC tracking was slightly better without prediction than with linear Kalman filter prediction. For lung, the TVSAR prediction algorithm performed best. Dynamic alignment of the collimator with the dominant motion axis was the most efficient MLC tracking improvement except for lung tracking with the low modulation VMAT plan, where jaw tracking was slightly better.

Dosimetric evaluation of MLC-based dynamic tumor tracking radiotherapy using digital phantom: Desired setup margin for tracking radiotherapy.

The purpose of this study is to evaluate the dosimetric impact of the margin on the multileaf collimator-based dynamic tumor tracking plan. Furthermore, an equivalent setup margin (EM) of the tracking plan was determined according to the gated plan. A 4-dimensional extended cardiac-torso was used to create 9 digital phantom datasets of different tumor diameters (TDs) of 1, 3, and 5 cm and motion ranges (MRs) of 1, 2, and 3 cm. For each dataset, respiratory gating (30% to 70% phase) and tumor tracking treatment plans were prepared using 8-field 3-dimensional conformal radiation therapy by 4-dimensional dose calculation. The total lung V20 was calculated to evaluate the dosimetric impact for each case and to estimate the EM with the same impact on lung V20 obtained with the gating plan with a setup margin of 5 mm. The EMs for {TD = 1 cm, MR = 1 cm}, {TD = 1 cm, MR = 2 cm}, and {TD = 1 cm, MR = 3 cm} were estimated as 5.00, 4.16, and 4.24 mm, respectively. The EMs for {TD = 5 cm, MR = 1 cm}, {TD = 5 cm, MR = 2 cm}, and {TD = 5 cm, MR = 3 cm} were estimated as 4.24 mm, 6.35 mm, and 7.49 mm, respectively. This result showed that with a larger MR, the EM was found to be increased. In addition, with a larger TD, the EM became smaller. Our result showing the EMs provided the desired accuracy for multileaf collimator-based dynamic tumor tracking radiotherapy.

Tracking tumor boundary in MV-EPID images without implanted markers: A feasibility study.

PURPOSE: To develop a markerless tracking algorithm to track the tumor boundary in megavoltage (MV)-electronic portal imaging device (EPID) images for image-guided radiation therapy. METHODS: A level set method (LSM)-based algorithm is developed to track tumor boundary in EPID image sequences. Given an EPID image sequence, an initial curve is manually specified in the first frame. Driven by a region-scalable energy fitting function, the initial curve automatically evolves toward the tumor boundary and stops on the desired boundary while the energy function reaches its minimum. For the subsequent frames, the tracking algorithm updates the initial curve by using the tracking result in the previous frame and reuses the LSM to detect the tumor boundary in the subsequent frame so that the tracking processing can be continued without user intervention. The tracking algorithm is tested on three image datasets, including a 4-D phantom EPID image sequence, four digitally deformable phantom image sequences with different noise levels, and four clinical EPID image sequences acquired in lung cancer treatment. The tracking accuracy is evaluated based on two metrics: centroid localization error (CLE) and volume overlap index (VOI) between the tracking result and the ground truth. RESULTS: For the 4-D phantom image sequence, the CLE is 0.23 ± 0.20 mm, and VOI is 95.6% ± 0.2%. For the digital phantom image sequences, the total CLE and VOI are 0.11 ± 0.08 mm and 96.7% ± 0.7%, respectively. In addition, for the clinical EPID image sequences, the proposed algorithm achieves 0.32 ± 0.77 mm in the CLE and 72.1% ± 5.5% in the VOI. These results demonstrate the effectiveness of the authors' proposed method both in tumor localization and boundary tracking in EPID images. In addition, compared with two existing tracking algorithms, the proposed method achieves a higher accuracy in tumor localization. CONCLUSIONS: In this paper, the authors presented a feasibility study of tracking tumor boundary in EPID images by using a LSM-based algorithm. Experimental results conducted on phantom and clinical EPID images demonstrated the effectiveness of the tracking algorithm for visible tumor target. Compared with previous tracking methods, the authors' algorithm has the potential to improve the tracking accuracy in radiation therapy. In addition, real-time tumor boundary information within the irradiation field will be potentially useful for further applications, such as adaptive beam delivery, dose evaluation.

A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications.

During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time.

A kernel-based method for markerless tumor tracking in kV fluoroscopic images.

Markerless tracking of respiration-induced tumor motion in kilo-voltage (kV) fluoroscopic image sequence is still a challenging task in real time image-guided radiation therapy (IGRT). Most of existing markerless tracking methods are based on a template matching technique or its extensions that are frequently sensitive to non-rigid tumor deformation and involve expensive computation. This paper presents a kernel-based method that is capable of tracking tumor motion in kV fluoroscopic image sequence with robust performance and low computational cost. The proposed tracking system consists of the following three steps. To enhance the contrast of kV fluoroscopic image, we firstly utilize a histogram equalization to transform the intensities of original images to a wider dynamical intensity range. A tumor target in the first frame is then represented by using a histogram-based feature vector. Subsequently, the target tracking is then formulated by maximizing a Bhattacharyya coefficient that measures the similarity between the tumor target and its candidates in the subsequent frames. The numerical solution for maximizing the Bhattacharyya coefficient is performed by a mean-shift algorithm. The proposed method was evaluated by using four clinical kV fluoroscopic image sequences. For comparison, we also implement four conventional template matching-based methods and compare their performance with our proposed method in terms of the tracking accuracy and computational cost. Experimental results demonstrated that the proposed method is superior to conventional template matching-based methods.

A time-varying seasonal autoregressive model-based prediction of respiratory motion for tumor following radiotherapy.

To achieve a better therapeutic effect and suppress side effects for lung cancer treatments, latency involved in current radiotherapy devices is aimed to be compensated for improving accuracy of continuous (not gating) irradiation to a respiratory moving tumor. A novel prediction method of lung tumor motion is developed for compensating the latency. An essential core of the method is to extract information valuable for the prediction, that is, the periodic nature inherent in respiratory motion. A seasonal autoregressive model useful to represent periodic motion has been extended to take into account the fluctuation of periodic nature in respiratory motion. The extended model estimates the fluctuation by using a correlation-based analysis for adaptation. The prediction performance of the proposed method was evaluated by using data sets of actual tumor motion and compared with those of the state-of-the-art methods. The proposed method demonstrated a high performance within submillimeter accuracy. That is, the average error of 1.0 s ahead predictions was 0.931 ± 0.055 mm. The accuracy achieved by the proposed method was the best among those by the others. The results suggest that the method can compensate the latency with sufficient accuracy for clinical use and contribute to improve the irradiation accuracy to the moving tumor.

Markerless Lung Tumor Motion Tracking by Dynamic Decomposition of X-Ray Image Intensity.

We propose a new markerless tracking technique of lung tumor motion by using an X-ray fluoroscopic image sequence for real-time image-guided radiation therapy (IGRT). A core innovation of the new technique is to extract a moving tumor intensity component from the fluoroscopic image intensity. The fluoroscopic intensity is the superimposition of intensity components of all the structures passed through by the X-ray. The tumor can then be extracted by decomposing the fluoroscopic intensity into the tumor intensity component and the others. The decomposition problem for more than two structures is ill posed, but it can be transformed into a well-posed one by temporally accumulating constraints that must be satisfied by the decomposed moving tumor component and the rest of the intensity components. The extracted tumor image can then be used to achieve accurate tumor motion tracking without implanted markers that are widely used in the current tracking techniques. The performance evaluation showed that the extraction error was sufficiently small and the extracted tumor tracking achieved a high and sufficient accuracy less than 1 mm for clinical datasets. These results clearly demonstrate the usefulness of the proposed method for markerless tumor motion tracking.

Respiratory motion prediction for tumor following radiotherapy by using time-variant seasonal autoregressive techniques.

We develop a new prediction method of respiratory motion for accurate dynamic radiotherapy, called tumor following radiotherapy. The method is based on a time-variant seasonal autoregressive (TVSAR) model and extended to further capture time-variant and complex nature of various respiratory patterns. The extended TVSAR can represent not only the conventional quasi-periodical nature, but also the residual components, which cannot be expressed by the quasi-periodical model. Then, the residuals are adaptively predicted by using another autoregressive model. The proposed method was tested on 105 clinical data sets of tumor motion. The average errors were 1.28 ± 0.87 mm and 1.75 ± 1.13 mm for 0.5 s and 1.0 s ahead prediction, respectively. The results demonstrate that the proposed method can outperform the state-of-the-art prediction methods.