Image-based computer-aided diagnosis (CAD) algorithms by the use of convolutional neural network (CNN) which do not require the image-feature extractor are powerful compared with conventional ...feature-based CAD algorithms which require the image-feature extractor for classification of lung abnormalities. Moreover, computer-aided detection and segmentation algorithms by the use of CNN are useful for analysis of lung abnormalities. Deep learning will improve the performance of CAD systems dramatically. Therefore, they will change the roles of radiologists in the near future. In this article, we introduce development and evaluation of such image-based CAD algorithms for various kinds of lung abnormalities such as lung nodules and diffuse lung diseases.
Biologics are essential for treating inflammatory bowel disease (IBD); however, only a few studies have validated cost-effective treatment options and patient factors for biologic use using ...real-world data from Japanese patients with IBD. Here, we aimed to provide pharmacoeconomic evidence to support clinical decisions for IBD treatment using biologics. We assessed 183 cases (127 patients) of IBD treated with biologics between November 2004 and September 2021. Data on patient background, treatment other than biologics, treatment-related medical costs, and effectiveness index (ratio of the C-reactive protein-negative period to drug survival time) were analyzed using univariate and multivariate logistic regression analyses. Drug survival was determined using Kaplan–Meier survival curve analysis. The outcomes were to validate a novel assessment index and elucidate the following aspects using this index: the effectiveness–cost relationship of long-term biologic use in IBD and cost-effectiveness-associated patient factors. Body mass index ≥25 kg/m2 and duration of hypoalbuminemia during drug survival correlated significantly with the therapeutic effectiveness of biologics. There were no significant differences in surgical, granulocyte apheresis, or adverse-event costs per drug survival time. Biologic costs were significantly higher in the group showing lower effectiveness than in the group showing higher effectiveness. These findings hold major pharmacoeconomic implications for not only improving therapeutic outcomes through the amelioration of low albumin levels and obesity but also potentially reducing healthcare expenditure related to the use of biotherapeutics. To our knowledge, this is the first pharmacoeconomic study based on real-world data from Japanese patients with IBD receiving long-term biologic therapy.
Research on Computer-Aided Diagnosis (CAD) of medical images has been actively conducted to support decisions of radiologists. Since deep learning has shown distinguished abilities in classification, ...detection, segmentation, etc. in various problems, many studies on CAD have been using deep learning. One of the reasons behind the success of deep learning is the availability of large application-specific annotated datasets. However, it is quite tough work for radiologists to annotate hundreds or thousands of medical images for deep learning, and thus it is difficult to obtain large scale annotated datasets for various organs and diseases. Therefore, many techniques that effectively train deep neural networks have been proposed, and one of the techniques is transfer learning. This paper focuses on transfer learning and especially conducts a case study on ROI-based opacity classification of diffuse lung diseases in chest CT images. The aim of this paper is to clarify what characteristics of the datasets for pre-training and what kinds of structures of deep neural networks for fine-tuning contribute to enhance the effectiveness of transfer learning. In addition, the numbers of training data are set at various values and the effectiveness of transfer learning is evaluated. In the experiments, nine conditions of transfer learning and a method without transfer learning are compared to analyze the appropriate conditions. From the experimental results, it is clarified that the pre-training dataset with more (various) classes and the compact structure for fine-tuning show the best accuracy in this work.
In computer-aided diagnosis systems for lung cancer, segmentation of lung nodules is important for analyzing image features of lung nodules on computed tomography (CT) images and distinguishing ...malignant nodules from benign ones. However, it is difficult to accurately and robustly segment lung nodules attached to the chest wall or with ground-glass opacities using conventional image processing methods. Therefore, this study aimed to develop a method for robust and accurate three-dimensional (3D) segmentation of lung nodule regions using deep learning. In this study, a nested 3D fully connected convolutional network with residual unit structures was proposed, and designed a new loss function. Compared with annotated images obtained under the guidance of a radiologist, the Dice similarity coefficient (DS) and intersection over union (IoU) were 0.845 ± 0.008 and 0.738 ± 0.011, respectively, for 332 lung nodules (lung adenocarcinoma) obtained from 332 patients. On the other hand, for 3D U-Net and 3D SegNet, the DS was 0.822 ± 0.009 and 0.786 ± 0.011, respectively, and the IoU was 0.711 ± 0.011 and 0.660 ± 0.012, respectively. These results indicate that the proposed method is significantly superior to well-known deep learning models. Moreover, we compared the results obtained from the proposed method with those obtained from conventional image processing methods, watersheds, and graph cuts. The DS and IoU results for the watershed method were 0.628 ± 0.027 and 0.494 ± 0.025, respectively, and those for the graph cut method were 0.566 ± 0.025 and 0.414 ± 0.021, respectively. These results indicate that the proposed method is significantly superior to conventional image processing methods. The proposed method may be useful for accurate and robust segmentation of lung nodules to assist radiologists in the diagnosis of lung nodules such as lung adenocarcinoma on CT images.
The efficacy of biologics in psoriasis treatment is clinically proven; however, biologics are expensive. In this study, we assessed the real‐world cost‐effectiveness of biologics for psoriasis ...treatment by evaluating the relationship between biologic drug survival (DS) and total medical‐treatment costs from a pharmacoeconomic viewpoint. Furthermore, the effects of patient factors on cost‐effectiveness were investigated. We retrospectively reviewed the medical records of 135 cases who received either a tumor necrosis factor‐alpha (TNF‐α) monoclonal antibody (TNF‐mab), interleukin (IL)‐17 mab, or IL23p19‐mab for psoriasis from January 2010 to June 2020 at Yamaguchi University Hospital. We compared the monthly medical‐treatment costs according to biologic classification and found that costs of medical services, tests, and external preparations required for the treatment process were significantly higher in the TNF‐mab group than in the other groups, and the total medical costs associated with TNF‐mab treatment were significantly higher than those of IL17‐mab treatment. The total monthly cost of medical care was lower in the long‐term DS group than in the short‐term group. The number of prescriptions for external preparations, comprising Vitamin D3 and corticosteroid, was significantly higher in the long‐term DS group than in the short‐term group; in the TNF‐mab group, the proportion of patients without smoking habits was significantly higher in the long‐term group as well. Our study indicated that when costly biologics are used for psoriasis treatment, the maintenance of long‐term DS and appropriate patient guidance might improve the quality of medical care, thus allowing cost‐effective medical care.
An isometric virus was isolated from a cultivated
Adonis
plant (
A. ramosa
). The purified virus particle is 28 nm in diameter and is composed of a single coat protein and a single RNA genome of ...3,991 nucleotides. Sequence analysis showed that the virus is closely related to carnation mottle virus. The virus was used to mechanically infect healthy
A. ramosa
plants, resulting in mosaic and leaf curl symptoms; however, attempts to inoculate carnation plants did not result in infection. We propose the virus as a new carmovirus and have named it adonis mosaic virus (AdMV).
Visual inspection of diffuse lung disease (DLD) patterns on high-resolution computed tomography (HRCT) is difficult because of their high complexity. We proposed a bag of words based method on the ...classification of these textural patters in order to improve the detection and diagnosis of DLD for radiologists. Six kinds of typical pulmonary patterns were considered in this work. They were consolidation, ground-glass opacity, honeycombing, emphysema, nodular and normal tissue. Because they were characterized by both CT values and shapes, we proposed a set of statistical measure based local features calculated from both CT values and the eigen-values of Hessian matrices. The proposed method could achieve the recognition rate of 95.85%, which was higher comparing with one global feature based method and two other CT values based bag of words methods.
Purpose
For realizing computer-aided diagnosis (CAD) of computed tomography (CT) images, many pattern recognition methods have been applied to automatic classification of normal and abnormal ...opacities; however, for the learning of accurate classifier, a large number of images with correct labels are necessary. It is a very time-consuming and impractical task for radiologists to give correct labels for a large number of CT images. In this paper, to solve the above problem and realize an unsupervised class labeling mechanism without using correct labels, a new clustering algorithm for diffuse lung diseases using frequent attribute patterns is proposed.
Methods
A large number of frequently appeared patterns of opacities are extracted by a data mining algorithm named genetic network programming (GNP), and the extracted patterns are automatically distributed to several clusters using genetic algorithm (GA). In this paper, lung CT images are used to make clusters of normal and diffuse lung diseases.
Results
After executing the pattern extraction by GNP, 1,148 frequent attribute patterns were extracted; then, GA was executed to make clusters. This paper deals with making clusters of normal and five kinds of abnormal opacities (i.e., six-class problem), and then, the proposed method without using correct class labels in the training showed 47.7 % clustering accuracy.
Conclusion
It is clarified that the proposed method can make clusters without using correct labels and has the potential to apply to CAD, reducing the time cost for labeling CT images.
We applied and optimized the sparse representation (SR) approaches in the computer-aided diagnosis (CAD) to classify normal tissues and five kinds of diffuse lung disease (DLD) patterns: ...consolidation, ground-glass opacity, honeycombing, emphysema, and nodule. By using the K-SVD which is based on the singular value decomposition (SVD) and orthogonal matching pursuit (OMP), it can achieve a satisfied recognition rate, but too much time was spent in the experiment. To reduce the runtime of the method, the K-Means algorithm was substituted for the K-SVD, and the OMP was simplified by searching the desired atoms at one time (OMP1). We proposed three SR based methods for evaluation: SR1 (K-SVD+OMP), SR2 (K-Means+OMP), and SR3 (K-Means+OMP1). 1161 volumes of interest (VOIs) were used to optimize the parameters and train each method, and 1049 VOIs were adopted to evaluate the performances of the methods. The SR based methods were powerful to recognize the DLD patterns (SR1: 96.1%, SR2: 95.6%, SR3: 96.4%) and significantly better than the baseline methods. Furthermore, when the K-Means and OMP1 were applied, the runtime of the SR based methods can be reduced by 98.2% and 55.2%, respectively. Therefore, we thought that the method using the K-Means and OMP1 (SR3) was efficient for the CAD of the DLDs.
The pathogenic type (form and race) of Fusarium oxysporum, which generates wilt symptoms on tomato, was rapidly identified with a polymerase chain reaction (PCR)-based technique. We compared the ...partial nucleotide sequences of endo polygalacturonase (pg1) and exo polygalacturonase (pgx4) genes from isolates of F. oxysporum ff. sp. lycopersici (FOL) and radicis-lycopersici (FORL) from Japan and designed specific primer sets (uni, sp13, sp23, and sprl) based on the nucleotide differences that appeared among the pathogenic types. PCR with the uni primer set amplified a 670~672-bp fragment from all isolates of FOL and FORL. With the sp13 primer set, an amplicon of 445 bp was obtained only from isolates of FOL race 1 and 3. With the sp23 primer set, a 518-bp fragment was obtained from isolates of FOL race 2 and 3. The sprl primer set yielded a 947-bp fragment from isolates of FORL, but not from FOL. A combination of amplifications with these primer sets effectively differentiated the pathogenic types of F. oxysporum in tomato. PUBLICATION ABSTRACT