Content-based image-retrieval system in chest computed tomography for a solitary pulmonary nodule: method and preliminary experiments

Abstract

Purpose The aim of this study was to develop a new diagnostic support system using content-based image-retrieval technology. In this article, we describe the mechanism and preliminary evaluation of this system for use with CT images of solitary pulmonary nodules. Materials and methods With the approval of the institutional review board of Shizuoka Cancer Center, we built a database that included CT images of 461 solitary pulmonary nodules. With this database, we developed a system that automatically extracts the pulmonary nodule when the nodule area is clicked, retrieves previous cases based on an image analysis of the extracted lesion, and generates reports of the pulmonary nodule semi-automatically. We compared the percentage of correct diagnoses with and without the system using 30 solitary pulmonary nodules, which were not included in the database, with one radiologist and two residents. As a per-user evaluation, the number of clicks required to extract the nodule region and the extracted regions was compared, and presented candidate cases were evaluated. As an evaluation of the retrieval results, the presented candidate cases were evaluated by comparing the number of diagnostic matches (benign/malignant) between the queries and four presented cases. Additionally, to evaluate the validity of the retrieval technology, the radiologist selected the most similar cases presented by the system and evaluated the visual similarity on a five-point scale.Results With this system, the percentage of correct diagnoses for the radiologist improved from 80 to 93%. For the two residents, the diagnostic accuracy improved from 66.7 to 80% and from 76.7 to 90%, respectively. The evaluation of the number of clicks required indicated that for 19 cases with the radiologist and 12 and 11 cases with the two residents, respectively, only one click was required to extract the region. When the extracted regions were compared between the radiologist and the residents, 22 and 19 cases had a Dice's Coefficient of 0.85 or higher, respectively. For the radiologist, the number of cases that matched the diagnosis (benign/malignant) averaged 3.7 ± 0.5 among 23 malignant cases and 1.7 ± 1.4 among 7 benign cases, while for the residents, these values were 3.6 ± 0.5 and 1.1 ± 0.9, and 3.4 ± 0.8 and 1.1 ± 1.3, respectively. With regard to visual evaluations by the radiologist, there were 15 similar cases and 11 somewhat similar cases. Conclusion These results suggest that, despite some differences in the search results among the users, this system has been confirmed that it can improve the accuracy of diagnosis as it displays similar cases at high probability. In addition, with the use of this system, past cases 123 332 Int J CARS (2012) 7:331-338 and their reports can be effectively referred to. Therefore, this diagnostic-assistant system has the potential to improve the efficiency of the CT image-reading workflow.

Evaluation of the Effectiveness of Artificial Neural Network Based on Correcting Scoliosis and Improving Spinal Health in University Students

“…The anterior and posterior flexion and extension of the cervical spine improved significantly, with an increase in flexion and extension of 9.25° and 8.00°, respectively; the anterior and posterior flexion and extension of the thoracic spine improved significantly, with an increase in flexion and extension of 8.90° and 11.35°, respectively; the anterior flexion and extension of the lumbar spine improved significantly, with an increase in anterior flexion of 6.45° (all P values <0.05), and the posterior extension of the lumbar spine did not change significantly relative to the pretest but did change significantly relative to the control group. There was no significant change in lumbar posterior extension compared to before the experiment, but there was a significant change compared to the control group [ 25 ]. The rotational capacity of the spine was improved by the tactician intervention, with an increase of 5.40° and 8.70° in the left and right rotation of the cervical spine, respectively, and an increase of 5.60° in the left rotation of the thoracic spine (all P values <0.05); there was no significant change in the right rotation of the thoracic spine, but there was a significant change in the right rotation of the thoracic spine compared to the control group.…”

A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases

“…Such as the extreme case, the similarity method [12] computed the similarity based on the only semantic information, where the weight of semantic similarity is 1 and the others are zeros in our framework. Another extreme case, the similarity method [11], used only visual similarity, where the weight of visual similarity equals 1 and the others are zeros in our framework. Moreover, the method [39] is a special instance of our method where the attribute weight is zero.…”

“…The shorter distances corresponded to higher similarity. To obtain a good performance, they chose the favorable metric according to the descriptors, like the city-block distance [7], the Mahalanobis distance [8], Manhattan distance [9], cosine distance [10], and Euclidian distance [11]. The other methods measured the semantic-level similarity based on the classification information.…”

A systematic review on the evaluation and characteristics of computer-aided diagnosis systems

“…It is seen, that if A seg = A man , then the relative area difference is 0. A metric applied to evaluate segmentation results, reported in three systems (Endo et al, 2012;Li et al, 2012;Liu et al, 2012), is Dice's coefficient. This metric calculates overlapping areas between an automatically segmented region and the correct expected region …”