Yukitaka Nimura

Multi-organ Segmentation Based on Spatially-Divided Probabilistic Atlas from 3D Abdominal CT Images

This paper presents an automated multi-organ segmentation method for 3D abdominal CT images based on a spatially-divided probabilistic atlases. Most previous abdominal organ segmentation methods are ineffective to deal with the large differences among patients in organ shape and position in local areas. In this paper, we propose an automated multi-organ segmentation method based on a spatially-divided probabilistic atlas, and solve this problem by introducing a scale hierarchical probabilistic atlas. The algorithm consists of image-space division and a multi-scale weighting scheme. The generated spatial-divided probabilistic atlas efficiently reduces the inter-subject variance in organ shape and position either in global or local regions. Our proposed method was evaluated using 100 abdominal CT volumes with manually traced ground truth data. Experimental results showed that it can segment the liver, spleen, pancreas, and kidneys with Dice similarity indices of 95.1%, 91.4%, 69.1%, and 90.1%, respectively.

Characterization of Colorectal Lesions Using a Computer-Aided Diagnostic System for Narrow-Band Imaging Endocytoscopy

Figure 1. Output image. (1) Computer diagnosis. (2) Input endocytoscopy with narrow band imaging. (3) Extracted vessel image, in which the green area denotes the extracted vessels. The light-green vessel has the maximum diameter. (4) Probability of computer diagnosis. 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 REndoscopy established the Preservation and Incorporation of Valuable Endoscopic Innovations for diminutive colorectal polyps. Preservation and Incorporation of Valuable Endoscopic Innovations suggests that, if an endoscopist diagnoses an agreement of >90% in determining postpolypectomy surveillance intervals and a negative predictive value of >90% with adenomatous histology, pathologic diagnosis might not be necessary. Although magnifying chromoendoscopy, narrow-band imaging (NBI), endocytoscopy (EC), and confocal laser endomicroscopy are highly accurate, interpretation of these modalities is difficult for novices. Furthermore, achieving a negative predictive value of >90% for adenoma is not easy using these modalities and requires comprehensive experiments. To achieve a breakthrough on this issue, we developed a computer-aided diagnosis (CAD) system for EC. This system automatically provides highly accurate diagnosis as expert endoscopists concurrently take EC images (Video Clip 1). Our previous system, based on glandular structural and cellular atypia, required endoscopists to use dye for staining. In contrast, the endocytoscopic vascular pattern can effectively evaluate microvessel findings using EC with NBI (EC-NBI) without using any dye. We reported that EC-NBI has a highly accurate diagnostic ability, similar to other modalities. Because dye staining complicates the procedure, our CAD system for EC-NBI represents a powerful tool for novices and experts who do not use dyes on a routine basis. Therefore, we developed a tentative CAD system model for EC-NBI image. Abbreviations used in this paper: CAD, computer-aided diagnosis; EC, endocytoscopy; EC-NBI, endocytoscopy with narrow-band imaging; NBI, narrow-band imaging; SSA/P, sessile serrated adenoma/polyp.

Regression Forest-Based Atlas Localization and Direction Specific Atlas Generation for Pancreas Segmentation

This paper proposes a fully automated atlas-based pancreas segmentation method from CT volumes utilizing atlas localization by regression forest and atlas generation using blood vessel information. Previous probabilistic atlas-based pancreas segmentation methods cannot deal with spatial variations that are commonly found in the pancreas well. Also, shape variations are not represented by an averaged atlas. We propose a fully automated pancreas segmentation method that deals with two types of variations mentioned above. The position and size of the pancreas is estimated using a regression forest technique. After localization, a patient-specific probabilistic atlas is generated based on a new image similarity that reflects the blood vessel position and direction information around the pancreas. We segment it using the EM algorithm with the atlas as prior followed by the graph-cut. In evaluation results using 147 CT volumes, the Jaccard index and the Dice overlap of the proposed method were 62.1 % and 75.1 %, respectively. Although we automated all of the segmentation processes, segmentation results were superior to the other state-of-the-art methods in the Dice overlap.

Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts

PurposeReal-time characterization of colorectal lesions during colonoscopy is important for reducing medical costs, given that the need for a pathological diagnosis can be omitted if the accuracy of the diagnostic modality is sufficiently high. However, it is sometimes difficult for community-based gastroenterologists to achieve the required level of diagnostic accuracy. In this regard, we developed a computer-aided diagnosis (CAD) system based on endocytoscopy (EC) to evaluate cellular, glandular, and vessel structure atypia in vivo. The purpose of this study was to compare the diagnostic ability and efficacy of this CAD system with the performances of human expert and trainee endoscopists.MethodsWe developed a CAD system based on EC with narrow-band imaging that allowed microvascular evaluation without dye (ECV-CAD). The CAD algorithm was programmed based on texture analysis and provided a two-class diagnosis of neoplastic or non-neoplastic, with probabilities. We validated the diagnostic ability of the ECV-CAD system using 173 randomly selected EC images (49 non-neoplasms, 124 neoplasms). The images were evaluated by the CAD and by four expert endoscopists and three trainees. The diagnostic accuracies for distinguishing between neoplasms and non-neoplasms were calculated.ResultsECV-CAD had higher overall diagnostic accuracy than trainees (87.8 vs 63.4%;

Anatomical annotation on vascular structure in volume rendered images

P=0.01

Automatic abdominal lymph node detection method based on local intensity structure analysis from 3D x-ray CT images

P=0.01), but similar to experts (87.8 vs 84.2%;

Pneumoperitoneum simulation based on mass-spring-damper models for laparoscopic surgical planning

P=0.76