Differentiation between solitary fibrous tumors and schwannomas of the head and neck: an apparent diffusion coefficient histogram analysis.

METHODS:: Our study included 5 patients with SFT and 18 patients with schwannoma in the head and neck region for whom pre-operative ADC images were obtained using either 1.5 or 3.0 T MRI system with two b-values. An ADC image that showed the tumor at the largest major diameter was selected for each patient, and a region of interest was set circumscribing the tumor. The histogram distributions of ADC values within the region of interest were compared between SFTs and schwannomas with respect to the mean, standard deviation, median, skewness, kurtosis, and percentile. RESULTS:: The mean and the median ADC values were significantly higher for schwannomas than in SFTs (p = 0.007 in both). Skewness and kurtosis of ADC histograms were significantly lower for schwannomas than for SFTs (p = 0.002 and 0.005, respectively). ADC values differed greatest between the two tumor groups at the 90th percentile, and were significantly higher for schwannomas than for SFTs (p = 0.005). On receiver operating characteristic curve analysis, the area under the curve for kurtosis, skewness, and the 90th percentile ADC values was 0.92, 0.90, and 0.90, respectively. CONCLUSIONS:: Our study suggests that skewness on ADC histograms may be the most useful diagnostic factor, followed by kurtosis and the 90th percentile ADC values, for differentiation between SFTs and schwannomas.

Fast approximation for joint optimization of segmentation, shape, and location priors, and its application in gallbladder segmentation.

PURPOSE: This paper addresses joint optimization for segmentation and shape priors, including translation, to overcome inter-subject variability in the location of an organ. Because a simple extension of the previous exact optimization method is too computationally complex, we propose a fast approximation for optimization. The effectiveness of the proposed approximation is validated in the context of gallbladder segmentation from a non-contrast computed tomography (CT) volume. METHODS: After spatial standardization and estimation of the posterior probability of the target organ, simultaneous optimization of the segmentation, shape, and location priors is performed using a branch-and-bound method. Fast approximation is achieved by combining sampling in the eigenshape space to reduce the number of shape priors and an efficient computational technique for evaluating the lower bound. RESULTS: Performance was evaluated using threefold cross-validation of 27 CT volumes. Optimization in terms of translation of the shape prior significantly improved segmentation performance. The proposed method achieved a result of 0.623 on the Jaccard index in gallbladder segmentation, which is comparable to that of state-of-the-art methods. The computational efficiency of the algorithm is confirmed to be good enough to allow execution on a personal computer. CONCLUSIONS: Joint optimization of the segmentation, shape, and location priors was proposed, and it proved to be effective in gallbladder segmentation with high computational efficiency.

Automated liver segmentation from a postmortem CT scan based on a statistical shape model.

PURPOSE: Automated liver segmentation from a postmortem computed tomography (PMCT) volume is a challenging problem owing to the large deformation and intensity changes caused by severe pathology and/or postmortem changes. This paper addresses this problem by a novel segmentation algorithm using a statistical shape model (SSM) for a postmortem liver. METHODS: The location and shape parameters of a liver are directly estimated from a given volume by the proposed SSM-guided expectation-maximization (EM) algorithm without any spatial standardization that might fail owing to the large deformation and intensity changes. The estimated location and shape parameters are then used as a constraint of the subsequent fine segmentation process based on graph cuts. Algorithms with eight different SSMs were trained using 144 in vivo and 32 postmortem livers, and the segmentation algorithm was tested on 32 postmortem livers in a twofold cross validation manner. The segmentation performance is measured by the Jaccard index (JI) between the segmentation result and the true liver label. RESULTS: The average JI of the segmentation result with the best SSM was 0.8501, which was better compared with the results obtained using conventional SSMs and the results of the previous postmortem liver segmentation with statistically significant difference. CONCLUSIONS: We proposed an algorithm for automated liver segmentation from a PMCT volume, in which an SSM-guided EM algorithm estimated the location and shape parameters of a liver in a given volume accurately. We demonstrated the effectiveness of the proposed algorithm using actual postmortem CT volumes.

Japanese phase II study of rituximab maintenance for untreated indolent B-cell non-Hodgkin lymphoma with high tumor burden.

Recent large-scale randomized clinical trials in Europe and the US demonstrated that maintenance therapy with rituximab significantly improved the progression-free survival (PFS) in indolent B-cell non-Hodgkin lymphoma (B-NHL) patients, especially those with follicular lymphoma (FL). However, rituximab maintenance has not been approved in Japan, because there are no clinical data supporting the benefit of rituximab maintenance in Japanese patients. Therefore, we conducted a single-arm, multicenter bridging study in previously untreated indolent B-NHL patients with high tumor burden. The primary endpoint was 4-year PFS and was expected to be 70 % based on previous studies. Sixty-two patients, including 55 FL patients, were enrolled and received induction therapy with CHOP combined with rituximab (R-CHOP). Fifty-eight patients responding to R-CHOP induction received rituximab at 375 mg/m2 every 8 weeks for 2 years as for the rituximab maintenance arm in the PRIMA study. A 4-year PFS of 69.8 % was obtained (95 % confidence interval 55.9-80.0 %). Rituximab maintenance was well tolerated and common adverse events were infections, neutropenia, and/or leukopenia that were manageable with conventional supportive care. No patients died. These data were compatible with the PRIMA data. R-CHOP induction followed by rituximab is useful in Japanese patients with untreated indolent B-NHL having high tumor burden. Clinical trial number UMIN000001191.

Joint optimization of segmentation and shape prior from level-set-based statistical shape model, and its application to the automated segmentation of abdominal organs.

The goal of this study is to provide a theoretical framework for accurately optimizing the segmentation energy considering all of the possible shapes generated from the level-set-based statistical shape model (SSM). The proposed algorithm solves the well-known open problem, in which a shape prior may not be optimal in terms of an objective functional that needs to be minimized during segmentation. The algorithm allows the selection of an optimal shape prior from among all possible shapes generated from an SSM by conducting a branch-and-bound search over an eigenshape space. The proposed algorithm does not require predefined shape templates or the construction of a hierarchical clustering tree before graph-cut segmentation. It jointly optimizes an objective functional in terms of both the shape prior and segmentation labeling, and finds an optimal solution by considering all possible shapes generated from an SSM. We apply the proposed algorithm to both pancreas and spleen segmentation using multiphase computed tomography volumes, and we compare the results obtained with those produced by a conventional algorithm employing a branch-and-bound search over a search tree of predefined shapes, which were sampled discretely from an SSM. The proposed algorithm significantly improves the segmentation performance in terms of the Jaccard index and Dice similarity index. In addition, we compare the results with the state-of-the-art multiple abdominal organs segmentation algorithm, and confirmed that the performances of both algorithms are comparable to each other. We discuss the high computational efficiency of the proposed algorithm, which was determined experimentally using a normalized number of traversed nodes in a search tree, and the extensibility of the proposed algorithm to other SSMs or energy functionals.

A conditional statistical shape model with integrated error estimation of the conditions; application to liver segmentation in non-contrast CT images.

This paper presents a novel conditional statistical shape model in which the condition can be relaxed instead of being treated as a hard constraint. The major contribution of this paper is the integration of an error model that estimates the reliability of the observed conditional features and subsequently relaxes the conditional statistical shape model accordingly. A three-step pipeline consisting of (1) conditional feature extraction from a maximum a posteriori estimation, (2) shape prior estimation through the novel level set based conditional statistical shape model with integrated error model and (3) subsequent graph cuts segmentation based on the estimated shape prior is applied to automatic liver segmentation from non-contrast abdominal CT volumes. Comparison with three other state of the art methods shows the superior performance of the proposed algorithm.

Statistical shape model of a liver for autopsy imaging.

PURPOSE: Modeling the postmortem liver for autopsy imaging is a challenging problem owing to the variation in organ deformation found in cadavers and limited availability of postmortem liver CT scans. An algorithm was developed to construct a statistical shape model (SSM) for the adult postmortem liver in autopsy imaging. METHODS: First, we investigated the relationship between SSMs obtained from in vivo liver CT scans and those from postmortem cases. Liver shapes were embedded in level set functions and statistically modeled using a spatially weighted principal components analysis. The performance of the SSMs was evaluated in terms of generalization and specificity. Several algorithms for the transformation from in vivo livers to postmortem livers were proposed to enhance the performance of an SSM for a postmortem liver, followed by a comparative study on SSMs. Specifically, five SSMs for a postmortem liver were constructed and evaluated using 32 postmortem liver labels, and postmortem liver labels synthesized from 144 in vivo liver labels were constructed using the proposed transformation algorithms. We also compared the proposed SSMs with three conventional SSMs trained from postmortem liver labels and/or in vivo liver labels. RESULTS: The investigation showed that the performance of an SSM constructed using in vivo liver labels suffered when describing postmortem liver shapes. Two of the five proposed SSMs trained using synthesized postmortem livers showed the best performance with no significant differences between them, and they statistically outperformed all conventional SSMs tested. CONCLUSIONS: The performance of conventional SSMs can be improved by using both postmortem liver shape labels and artificial shape labels synthesized from in vivo liver shape labels.

Semi-automated virtual unfolded view generation method of stomach from CT volumes.

CT image-based diagnosis of the stomach is developed as a new way of diagnostic method. A virtual unfolded (VU) view is suitable for displaying its wall. In this paper, we propose a semi-automated method for generating VU views of the stomach. Our method requires minimum manual operations. The determination of the unfolding forces and the termination of the unfolding process are automated. The unfolded shape of the stomach is estimated based on its radius. The unfolding forces are determined so that the stomach wall is deformed to the expected shape. The iterative deformation process is terminated if the difference of the shapes between the deformed shape and expected shape is small. Our experiments using 67 CT volumes showed that our proposed method can generate good VU views for 76.1% cases.

Phase II/III study of R-CHOP-21 versus R-CHOP-14 for untreated indolent B-cell non-Hodgkin's lymphoma: JCOG 0203 trial.

PURPOSE: Rituximab with cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) is one of the most effective front-line therapies to treat indolent B-cell lymphoma. Granulocyte colony-stimulating factor (G-CSF), which potentiates antibody-dependent rituximab cytotoxicity, is used to shorten CHOP intervals. To improve progression-free survival (PFS) in patients treated with R-CHOP as the primary end point, we conducted a phase III study. PATIENTS AND METHODS: Patients with untreated stages III to IV indolent B-cell lymphoma were randomly assigned to six cycles of R-CHOP every 3 weeks (R-CHOP-21) or every 2 weeks (R-CHOP-14) with G-CSF. Maintenance rituximab was not allowed. RESULTS: Three hundred patients were enrolled. At the median follow-up time of 5.2 years, there was no significant difference in PFS between arms for the 299 eligible patients; the median was 3.7 (R-CHOP-21) v 4.7 (R-CHOP-14) years, 57% v 58% at 3 years, and 41% v 43% at 6 years, respectively (hazard ratio [HR], 0.92; 95% CI, 0.68 to 1.25; one-sided P = .30). The median overall survival (OS) time was not reached in either arm, and there was no significant difference (6-year OS: 87% [R-CHOP-21] v 88% [R-CHOP-14]; HR, 1.15; 95% CI, 0.57 to 2.30; one-sided P = .65). Although grade 4 neutropenia and grade 3 infections were more frequent in the R-CHOP-21 group, R-CHOP was feasible in both arms. CONCLUSION: The R-CHOP dose-dense strategy failed to improve PFS of patients with untreated indolent B-cell lymphoma. Further improvement of first-line treatment or investigations on postremission therapy following R-CHOP should be explored.

Rituximab monotherapy with eight weekly infusions for relapsed or refractory patients with indolent B cell non-Hodgkin lymphoma mostly pretreated with rituximab: a multicenter phase II study.

Information regarding rituximab monotherapy with eight weekly infusions for relapsed or refractory indolent B cell non-Hodgkin lymphoma (B-NHL), in particular for patients pretreated with rituximab, is limited. To evaluate the efficacy and safety of eight doses of rituximab monotherapy, 52 patients with relapsed or refractory indolent B-NHL were enrolled in the present study. Forty of 45 eligible patients (89%) had follicular lymphoma and 24 (53%) were at intermediate or high risk group according to the Follicular Lymphoma International Prognostic Index. The median number of prior chemotherapy regimens was 1 (range 1-7). At the median follow-up of 12.2 months, the overall response rate (ORR), complete response rate (%CR), and median progression-free survival (PFS) were 69% (95% confidence interval [CI] 53%-82%), 47% (95% CI 32%-62%), and 15.6 months (95% CI 10.6- months), respectively. In the 33 patients pretreated with rituximab, the ORR, %CR, and median PFS were inferior compared with values for the 12 patients who had not received rituximab previously (64%vs 83% for ORR; 39%vs 67% for %CR; and 13.8 vs 17.5 months for median PFS, respectively). All mild-to-moderate infusion-related toxicities were reversible. Grade 3/4 non-hematologic adverse events occurred in six of the 52 patients. Two patients developed Grade 4 late-onset neutropenia and a decrease (>50%) in serum immunoglobulin was observed in six patients. In conclusion, rituximab monotherapy with eight weekly infusions is effective in relapsed patients with indolent B-NHL, with acceptable toxicities, including in patients pretreated with rituximab; however, careful monitoring is recommended for infections associated with late-onset neutropenia and hypogammaglobulinemia. (University Hospital Medical Information Network no. UMIN000002974.)

Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography.

PURPOSE: We propose an automated pancreas segmentation algorithm from contrast-enhanced multiphase computed tomography (CT) and verify its effectiveness in segmentation. METHODS: The algorithm is characterized by three unique ideas. First, a two-stage segmentation strategy with spatial standardization of pancreas was employed to reduce variations in the pancreas shape and location. Second, patient- specific probabilistic atlas guided segmentation was developed to cope with the remaining variability in shape and location. Finally, a classifier ensemble was incorporated to refine the rough segmentation results. RESULTS: The effectiveness of the proposed algorithm was validated with 20 unknown CT volumes, as well as three on-site CT volumes distributed in a competition of pancreas segmentation algorithms. The experimental results indicated that the segmentation performance was enhanced by the proposed algorithm, and the Jaccard index between an extracted pancreas and a true one was 57.9%. CONCLUSIONS: This study verified the effectiveness of two-stage segmentation with spatial standardization of pancreas in delineating the pancreas region, patient-specific probabilistic atlas guided segmentation in reducing false negatives, and a classifier ensemble in boosting segmentation performance.

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

OBJECTIVE: We 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 METHODS: Validation 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. RESULTS: Point 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. CONCLUSION: Combination of the likelihood of lines with point convergence index is effective in extracting architectural distortion with radiating spiculations.

Phase I/II study of concurrent chemoradiotherapy for localized nasal natural killer/T-cell lymphoma: Japan Clinical Oncology Group Study JCOG0211.

PURPOSE: To explore a more effective treatment for localized nasal natural killer (NK)/T-cell lymphoma, we conducted a phase I/II study of concurrent chemoradiotherapy. PATIENTS AND METHODS: Treatments comprised concurrent radiotherapy (50 Gy) and 3 courses of dexamethasone, etoposide, ifosfamide, and carboplatin (DeVIC). Patients with a newly diagnosed stage IE or contiguous IIE disease with cervical node involvement and a performance status (PS) of 0 to 2 were eligible for enrollment. The primary end point of the phase II portion was a 2-year overall survival in patients treated with the recommended dose. RESULTS: Of the 33 patients enrolled, 10 patients were enrolled in the phase I portion and a two thirds dose of DeVIC was established as the recommended dose. Twenty-seven patients (range, 21 to 68; median, 56 years) treated with the recommended dose showed the following clinical features: male:female, 17:10; stage IE, 18; stage IIE, 9; B symptoms present, 10; elevated serum lactate dehydrogenase, 5; and PS 2, 2. With a median follow-up of 32 months, the 2-year overall survival was 78% (95% CI, 57% to 89%). This compared favorably with the historical control of radiotherapy alone (45%). Of the 26 patients assessable for a response, 20 (77%) achieved a complete response, with one partial response. The overall response rate was 81%. The most common grade 3 nonhematologic toxicity was mucositis related to radiation (30%). No treatment-related deaths were observed. CONCLUSION: Concurrent chemoradiotherapy using multidrug resistance-nonrelated agents and etoposide is a safe and effective treatment for localized nasal NK/T-cell lymphoma and warrants further investigation.

Phase II study of oral fludarabine in combination with rituximab for relapsed indolent B-cell non-Hodgkin lymphoma.

Oral fludarabine is more convenient than intravenous fludarabine in an outpatient setting. To assess the efficacy and toxicity of oral fludarabine in combination with rituximab in patients with relapsed indolent B-cell non-Hodgkin lymphoma (B-NHL), we conducted a multicenter phase II study. Patients with relapsed indolent B-NHL with two or fewer prior regimens and up to 16 doses of rituximab were eligible. Patients received 375 mg/m(2) rituximab on day 1, and 40 mg/m(2) oral fludarabine once daily on days 1 through 5 every 28 days for up to six cycles. The primary endpoint was the overall response rate. Forty-one patients were enrolled, including 38 (93%) with follicular lymphoma. Thirty-four patients (83%) had received rituximab as prior therapy. Twenty-seven patients (66%) completed the planned six cycles. Dose reduction of oral fludarabine was required in 17 patients (41%). The overall response rate was 76% (31 of 41 patients; 95% confidence interval, 60-88%) with a complete response rate of 68% (28 of 41 patients; 95% confidence interval, 52-82%). Median progression-free survival for the 41 patients was 19.7 months (95% confidence interval, 12.3-26.5 months). Hematological toxicities, including grade 4 neutropenia (68%), were the most frequent toxicities. Non-hematological toxicities were mild, except for one patient who died of Pneumocystis jiroveci pneumonia 4 months after the protocol treatment. In conclusion, oral fludarabine in combination with rituximab is a highly effective and convenient therapy for patients with relapsed indolent B-NHL who have mostly been pretreated with rituximab.

Comparison of diffusion-weighted images using short inversion time inversion recovery or chemical shift selective pulse as fat suppression in patients with breast cancer.

PURPOSE: Fat suppression is essential for diffusion-weighted imaging (DWI) in the body. However, the chemical shift selective (CHESS) pulse often fails to suppress fat signals in the breast. The purpose of this study was to compare DWI using CHESS and DWI using short inversion time inversion recovery (STIR) in terms of fat suppression and the apparent diffusion coefficient (ADC) value. MATERIALS AND METHODS: DWI using STIR, DWI using CHESS, and contrast-enhanced T1-weighted images were obtained in 32 patients with breast carcinoma. Uniformity of fat suppression, ADC, signal intensity, and visualization of the breast tumors were evaluated. RESULTS: In 44% (14/32) of patients there was insufficient fat suppression in the breasts on DWI using CHESS, whereas 0% was observed on DWI using STIR (P < 0.0001). The ADCs obtained for DWI using STIR were 4.3% lower than those obtained for DWI using CHESS (P < 0.02); there was a strong correlation of the ADC measurement (r = 0.93, P < 0.001). CONCLUSION: DWI using STIR may be excellent for fat suppression; and the ADC obtained in this sequence was well correlated with that obtained with DWI using CHESS. DWI using STIR may be useful when the fat suppression technique in DWI using CHESS does not work well.

Phase I/II and pharmacokinetic study of cladribine with 2-h infusion in Japanese patients with relapsed indolent B-cell lymphoma mostly pretreated with rituximab.

We conducted a phase I/II study to investigate the toxicity, pharmacokinetics, and efficacy profiles of cladribine with 2-h intravenous infusion for five consecutive days every four weeks in Japanese patients with relapsed indolent B-cell lymphoma. This was a dose-escalation study to confirm the safety of the doses which have been recommended for Caucasian patients (phase I), and to further evaluate the efficacy and safety (phase II). In the phase I portion for nine patients, no dose-limiting toxicities were observed at levels 1 (0.09 mg/kg/day, n = 3) and 2 (0.12 mg/kg/day, n = 6). No appreciable accumulation of plasma cladribine concentration was suggested. We enrolled a total of 20 patients, and an additional 14 patients in the phase II portion at level 2 (0.12 mg/kg/day). Eighteen patients, including 13 with follicular lymphoma, were eligible for efficacy evaluation, and 15 (83%) were pretreated with rituximab. The overall response rate was 50% (9/18; 80% confidence interval, 35-65%), with 11% (2/18) complete response. With a median follow-up of 296 days, the estimated median time to progression for 18 eligible patients was 382 days. The most frequent adverse events were hematologic toxicities, including grade 4 neutropenia. Non-hematologic toxicities were mild. In conclusion, cladribine with 2-h intravenous infusion for five consecutive days every four weeks is effective with acceptable toxicities for Japanese patients with relapsed indolent B-cell lymphoma, including those pretreated with rituximab.

Digital bowel cleansing free colonic polyp detection method for fecal tagging CT colonography.

RATIONALE AND OBJECTIVES: Fecal tagging computed tomographic colonography (ftCTC) reduces the discomfort and the inconvenience of patients associated with bowel cleansing procedures before CT scanning. In conventional colonic polyp detection techniques for ftCTC, a digital bowel cleansing (DBC) technique is applied to detect polyps in tagged fecal materials (TFM). However, DBC removes the surface of soft tissues and hampers polyp detection. We developed a colonic polyp detection method for CT colonographic examination that enables the detection of polyps surrounded by air and polyps surrounded by TFM without DBC. MATERIALS AND METHODS: CT values inside the polyps surrounded by air and polyps surrounded by TFM tend to gradually increase (blob structure) and decrease (inverse-blob structure) from outward to inward, respectively. We developed blob and inverse-blob structure enhancement filters based on the eigenvalues of a Hessian matrix to detect polyps using their intensity characteristic. False-positive elimination is performed using three feature values: volume, maximum value of filter outputs, and standard deviation of CT values inside the polyp candidates. RESULTS: The proposed method is applied to 104 cases of ftCTC images that include 57 polyps larger than 6 mm in diameter. The sensitivity of the method was 91.2% (52/57) with 11.4 false positives per case. CONCLUSIONS: The proposed method detects polyps with high sensitivity and 11.4 false positives per case without adverse effects on the DBC.

Japanese phase II study of 90Y-ibritumomab tiuxetan in patients with relapsed or refractory indolent B-cell lymphoma.

There is no data about the efficacy and safety of radioimmunotherapy with 90Y-ibritumomab tiuxetan in patients with relapsed or refractory indolent B-cell lymphoma pretreated with rituximab-containing chemotherapy. We focused on this in a Japanese phase II study. Radioimmunotherapy with 90Y-ibritumomab tiuxetan (11.1 and 14.8 MBq) was evaluated in patients with 100-149x10(9) and >150x10(9) platelets/L, respectively. The primary endpoint was the overall response rate. Forty patients were treated with 90Y-ibritumomab tiuxetan (18 with 11.1 MBq/kg and 22 with 14.8 MBq/kg). Thirty-five patients (88%) had been pretreated with rituximab, including 27 (68%) pretreated with rituximab-containing chemotherapy. The overall response rate was 83% (33/40; 95% confidence interval, 67-93%), and the complete response rate was 68% (27/40; 95% confidence interval, 51-81%). The overall response rates in patients pretreated with rituximab-containing chemotherapy and rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) were 83% (19/23) and 94% (17/18), respectively. The median progression-free survival time of the 40 patients who received 90Y-ibritumomab tiuxetan was 9.6 months. Toxicity was primarily hematological and mostly transient. No grade 4 non-hematological toxicity was observed. In conclusion, radioimmunotherapy with 90Y-ibritumomab tiuxetan is safe and highly effective in patients with relapsed or refractory indolent B-cell lymphoma, including those pretreated with rituximab-containing chemotherapy. (ClinicalTrials.gov number NCT00220285).

Medical image analysis of 3D CT images based on extension of Haralick texture features.

PURPOSE: A new approach to the segmentation of 3D CT images is proposed in an attempt to provide texture-based segmentation of organs or disease diagnosis. 3D extension of Haralick texture features was studied calculating co-occurrences of all voxels in a small cubic region around the voxel. RESULTS: For verification, the proposed method was tested on a set of abdominal 3D volumes of patients. Statistically, the improvement in segmentation was significant for most of the organs considered herein. CONCLUSIONS: The proposed method has potential application in medical image segmentation, including diagnosis of diseases.