AI-Based Automated Lipomatous Tumor Segmentation in MR Images: Ensemble Solution to Heterogeneous Data

Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 \(\pm\) 0.16, 0.73 \(\pm\) 0.168, and 0.99 \(\pm\) 0.012, respectively, while for SL predictions were 0.80 \(\pm\) 0.184, 0.78 \(\pm\) 0.193, and 1.00 \(\pm\) 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.

     

An Artificial Immune System-Based Support Vector Machine Approach for Classifying Ultrasound Breast Tumor Images

A rapid and highly accurate diagnostic tool for distinguishing benign tumors from malignant ones is required owing to the high incidence of breast cancer. Although various computer-aided diagnosis (CAD) systems have been developed to interpret ultrasound images of breast tumors, feature selection and the setting of parameters are still essential to classification accuracy and the minimization of computational complexity. This work develops a highly accurate CAD system that is based on a support vector machine (SVM) and the artificial immune system (AIS) algorithm for evaluating breast tumors. Experiments demonstrate that the accuracy of the proposed CAD system for classifying breast tumors is 96.67 %. The sensitivity, specificity, PPV, and NPV of the proposed CAD system are 96.67, 96.67, 95.60, and 97.48 %, respectively. The receiver operator characteristic (ROC) area index A_z is 0.9827. Hence, the proposed CAD system can reduce the number of biopsies and yield useful results that assist physicians in diagnosing breast tumors.     

Semantic Instance Segmentation of Kidney Cysts in MR Images: A Fully Automated 3D Approach Developed Through Active Learning

Journal of Digital Imaging - Total kidney volume (TKV) is the main imaging biomarker used to monitor disease progression and to classify patients affected by autosomal dominant polycystic kidney...     

An Automated System for Heart Contour Delineation in Photofluorographic Images

An automated system for heart contour delineation in photofluorographic images is described. This system allows the heart contour to be isolated without distortion. The heart contour in photofluorographic image is isolated using a decomposition method for empirical modes. The isolation algorithm, which is based on textural segmentation, is promising for various applications.     

An Intelligent System to Enhance the Performance of Brain Tumor Diagnosis from MR Images

Journal of Digital Imaging - In the human body, cancer is caused by aberrant cell proliferation. Brain tumors are created when cells in the human brain proliferate out of control. Brain tumors...     

An Experimentalist's Approach to Accurate Localization of Phase Singularities during Reentry

A phase variable that uniquely represents the time course of the action potential has been used to study the mechanisms of cardiac fibrillation. A spatial phase singularity (PS) occurs during reentrant wave propagation and represents the organizing center of the rotating wave. Here, we present an error analysis to investigate how well PSs can be localized. Computer simulations of rotating spiral waves scaled appropriately for cardiac tissue were studied with various levels of noise added. The accuracy in identifying and localizing singularities depended on three factors: (i) the point chosen as the origin in state space used to calculate the phase variable; (ii) signal to noise ratio; and (iii) discretization (number of levels used to represent data). We found that for both simulation as well as experimental data, there existed a wide range for the choice of origin for which PSs could be identified. Discretization coupled with noise affected this range adversely. However, there always existed a range for choice of the origin that was 20% or more of the action potential amplitude within which the accuracy of localizing PSs was better than 2 mm. Thus, a precise determination of origin was not necessary for accurately identifying PSs. © 2001 Biomedical Engineering Society. PAC01: 8719Nn, 8710+e, 8719Hh     

一种二维电泳凝胶图像蛋白点数据量化和质量控制的新方法

利用计算机图像处理技术对二维电泳生成簟凝胶图像进行自动分析,是近年图像处理理论在生命科学中的一个重要应用方向,其目的是快速而准确的为病理、药理等生命学科的深入研究提供量化依据。本研究基于数据处理有关理论,提出一整套蛋白点数据量化和质量控制的新算法。实验证明,该算法计算结果准确、可靠,运算速度快,具有一定的抗噪能力。     

序列二维医学图像的三维显示法

详细综述了对序列二维医学图像进行三维显示的各种方法，进一步展示了该领域的最新发展方向。在比较各种显示技术的基础上，针对不同应用场合：计算机辅助手术实时导航系统和术前高精度诊疗系统，提出了不同的三维显示法。     

An Efficient Approach for Automated Mass Segmentation and Classification in Mammograms

Breast cancer is becoming a leading death of women all over the world; clinical experiments demonstrate that early detection and accurate diagnosis can increase the potential of treatment. In order to improve the breast cancer diagnosis precision, this paper presents a novel automated segmentation and classification method for mammograms. We conduct the experiment on both DDSM database and MIAS database, firstly extract the region of interests (ROIs) with chain codes and using the rough set (RS) method to enhance the ROIs, secondly segment the mass region from the location ROIs with an improved vector field convolution (VFC) snake and following extract features from the mass region and its surroundings, and then establish features database with 32 dimensions; finally, these features are used as input to several classification techniques. In our work, the random forest is used and compared with support vector machine (SVM), genetic algorithm support vector machine (GA-SVM), particle swarm optimization support vector machine (PSO-SVM), and decision tree. The effectiveness of our method is evaluated by a comprehensive and objective evaluation system; also, Matthew’s correlation coefficient (MCC) indicator is used. Among the state-of-the-art classifiers, our method achieves the best performance with best accuracy of 97.73 %, and the MCC value reaches 0.8668 and 0.8652 in unique DDSM database and both two databases, respectively. Experimental results prove that the proposed method outperforms the other methods; it could consider applying in CAD systems to assist the physicians for breast cancer diagnosis.     

Multi-Resolution Level Sets with Shape Priors: A Validation Report for 2D Segmentation of Prostate Gland in T2W MR Images

The level set approach to segmentation of medical images has received considerable attention in recent years. Evolving an initial contour to converge to anatomical boundaries of an organ or tumor is a very appealing method, especially when it is based on a well-defined mathematical foundation. However, one drawback of such evolving method is its high computation time. It is desirable to design and implement algorithms that are not only accurate and robust but also fast in execution. Bresson et al. have proposed a variational model using both boundary and region information as well as shape priors. The latter can be a significant factor in medical image analysis. In this work, we combine the variational model of level set with a multi-resolution approach to accelerate the processing. The question is whether a multi-resolution context can make the segmentation faster without affecting the accuracy. As well, we investigate the question whether a premature convergence, which happens in a much shorter time, would reduce accuracy. We examine multiple semiautomated configurations to segment the prostate gland in T2W MR images. Comprehensive experimentation is conducted using a data set of a 100 patients (1,235 images) to verify the effectiveness of the multi-resolution level set with shape priors. The results show that the convergence speed can be increased by a factor of ≈?2.5 without affecting the segmentation accuracy. Furthermore, a premature convergence approach drastically increases the segmentation speed by a factor of ≈?17.9.     

Computer Automated Approach to the Extraction of Epiphyseal Regions in Hand Radiographs

Epiphyseal region is the most sensitive region to developmental changes of the skeletal system. Extraction of this area is the very first step in any computerized image analysis. In this report a fully automated analysis of a hand radiograph resulting in extraction of distal and middle regions of the II, III, and IV phalanx is presented. The processing is performed in 3 stages. First, the trend of background is removed from radiograph to obtain a binary hand mask. At this stage a labeling procedure is necessary to eliminate artifacts (markers). Then, II, III, and IV phalanges are identified in the binary image, and the phalangeal axes are drawn. Finally, the intensity profile along each phalangeal axis is analyzed, and, on its basis, distal and middle regions are located. The presented procedure is designed as a part of currently developed system for automatic bone age assessment; however, it also can be as a preprocessing step in other diseases the diagnoses of which may require a computer assistance.     

An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer

Lung cancer nodules, particularly adenocarcinoma, contain a complex intermixing of cellular tissue types: incorporating cancer cells, fibroblastic stromal tissue, and inactive fibrosis. Quantitative proportions and distributions of the various tissue types may be insightful for understanding lung cancer growth, classification, and prognostic factors. However, current methods of histological assessment are qualitative and provide limited opportunity to systematically evaluate the relevance of lung nodule cellular heterogeneity. In this study we present both a manual and an automatic method for segmentation of tissue types in histological sections of resected human lung cancer nodules. A specialized staining approach incorporating immunohistochemistry with a modified Masson’s Trichrome counterstain was employed to maximize color contrast in the tissue samples for automated segmentation. The developed, clustering-based, fully automated segmentation approach segments complete lung nodule cross-sectional histology slides in less than 1 min, compared to manual segmentation which requires multiple hours to complete. We found the accuracy of the automated approach to be comparable to that of the manual segmentation with the added advantages of improved time efficiency, removal of susceptibility to human error, and 100% repeatability.     

Malignant Spindle Cell Tumor of the Pericardium

A case of malignant spindle cell tumor occurring in the pericardium in presented. The tumor arose from the pericardium of a 51-year-old Japanese woman with no history of exposure to asbestos. The tumor extended into the pericardial and left pleural cavities. The primary and metastatic tumors consisted of fusiform cells with frequent mitoses. Ultrastructurally, the tumor cells possessed a discontinuous external lamina, cytoplasmic processes, microfilaments and desmosomal intercellular junctions. Immunohistochemical examination showed that most tumor cells were positive for Leu 7, and several for S 100 and glial fibrillary acidic protein. Unexpectedly, most of the tumor cells also expressed keratin. These findings favor a diagnosis of sarcomatous mesothelioma with aberrant antigenic expression or heterogeneous differentiation of neoplastic cells. Acta Pathol Jpn 39: 750-754, 1989.     

Automated Classification of Leukocytes in Blood Smear Images

Leukocyte formula counting is an important step of clinical blood analysis. A classification system is presented for problems of classification and count of leukocytes on blood smears images. The classification is based on a variant of the AdaBoost algorithm. The results of implementation of the algorithm are presented.     

Malignant Mixed Mullerian Tumor of the Ovary

A case of malignant mixed mullerian tumor of the ovary in a 57 year old woman is reported along with the results of an immunohistochemical study. The tumor, measuring 16·10·9cm, was composed predominantly of adenocarcinoma with a smaller amount of anaplastic carcinoma as an epithelial component and chondrosarcoma, liposarcoma, fibrosarcoma and rhabdomyoblasts as mesenchymal elements. Immunohistochemistry using paraffin sections demonstrated cytokeratin (CK) and epithelial membrane antigen (EMA), generally regarded as epithelial markers, not only in the epithelial component but also in chondrosarcoma cells. Vimentin and desmin, generally regarded as mesenchymal markers, were exhibited partly in carcinoma cells as well as in mesenchymal elements. Positive staining for S 100 protein was obtained not only in chondrosarcoma and liposarcoma cells, but also partly in adenocarcinoma cells. This intricate immunohistochemical picture reflected the histologic findings. It is noteworthy that both carcinoma cells and chondrosarcoma cells demonstrated simultaneous expression of CK, EMA, vimentin, desmin and S 100 protein. This somewhat unusual antigen expression by tumor cells may indicate a change in the nature of tumor cells due to microenvironmental factors. Acta Pathol Jpn 40: 845 850, 1990.     

Gland and Zonal Segmentation of Prostate on T2W MR Images

For many years, prostate segmentation on MR images concerned only the extraction of the entire gland. Currently, in the focal treatment era, there is a continuously increasing need for the separation of the different parts of the organ. In this paper, we propose an automatic segmentation method based on the use of T2W images and atlas images to segment the prostate and to isolate the peripheral and transition zones. The algorithm consists of two stages. First, the target image is registered with each zonal atlas image then the segmentation is obtained by the application of an evidential C-Means clustering. The method was evaluated on a representative and multi-centric image base and yielded mean Dice accuracy values of 0.81, 0.70, and 0.62 for the prostate, the transition zone, and peripheral zone, respectively.     

A Heuristic Approach to Automated Nipple Detection in Digital Mammograms

In this paper, a heuristic approach to automated nipple detection in digital mammograms is presented. A multithresholding algorithm is first applied to segment the mammogram and separate the breast region from the background region. Next, the problem is considered separately for craniocaudal (CC) and mediolateral-oblique (MLO) views. In the simplified algorithm, a search is performed on the segmented image along a band around the centroid and in a direction perpendicular to the pectoral muscle edge in the MLO view image. The direction defaults to the horizontal (perpendicular to the thoracic wall) in case of CC view images. The farthest pixel from the base found in this direction can be approximated as the nipple point. Further, an improved version of the simplified algorithm is proposed which can be considered as a subclass of the Branch and Bound algorithms. The mean Euclidean distance between the ground truth and calculated nipple position for 500 mammograms from the Digital Database for Screening Mammography (DDSM) database was found to be 11.03 mm and the average total time taken by the algorithm was 0.79 s. Results of the proposed algorithm demonstrate that even simple heuristics can achieve the desired result in nipple detection thus reducing the time and computational complexity.     

An Unsupervised Approach for Extraction of Blood Vessels from Fundus Images

Pathological disorders may happen due to small changes in retinal blood vessels which may later turn into blindness. Hence, the accurate segmentation of blood vessels is becoming a challenging task for pathological analysis. This paper offers an unsupervised recursive method for extraction of blood vessels from ophthalmoscope images. First, a vessel-enhanced image is generated with the help of gamma correction and contrast-limited adaptive histogram equalization (CLAHE). Next, the vessels are extracted iteratively by applying an adaptive thresholding technique. At last, a final vessel segmented image is produced by applying a morphological cleaning operation. Evaluations are accompanied on the publicly available digital retinal images for vessel extraction (DRIVE) and Child Heart And Health Study in England (CHASE_DB1) databases using nine different measurements. The proposed method achieves average accuracies of 0.957 and 0.952 on DRIVE and CHASE_DB1 databases respectively.