scholarly journals Validation of Liver Tumor Segmentation in CT Scans by Relating Manual and Algorithmic Performance - A Preliminary Study

2010 ◽  
Author(s):  
Jan hendrik Moltz ◽  
Jan Rühaak ◽  
Christiane Engel ◽  
Ulrike Kayser ◽  
Heinz-Otto Peitgen
Keyword(s):  
Liver Tumors ◽  
Ground Truth ◽  
Ct Scans ◽  
Tumor Segmentation ◽  
Validation Framework ◽  
Segmentation Quality ◽  
Segmentation Algorithms ◽  
Preliminary Study ◽  
Traditional Approaches

The development of segmentation algorithms for liver tumors in CT scans has found growing attention in recent years. The validation of these methods, however, is often treated as a subordinate task. In this article, we review existing approaches and present rst steps towards a new methodology that evaluates the quality of an algorithm in relation to the variability of manual delineations. We obtained three manual segmentations for 50 liver lesions and computed the results of a segmentation algorithm. We compared all four masks with each other and with different ground truth estimates and calculated scores according to the validation framework from the MICCAI challenge 2008. Our results show some cases where this more elaborate evaluation reflects the segmentation quality in a more adequate way than traditional approaches. The concepts can also be extended to other similar segmentation problems.

scholarly journals Patient-Specific Simulation of Pneumoperitoneum for Laparoscopic Surgical Planning

2019 ◽  
Vol 43 (10) ◽  
Author(s):  
Shivali Dawda ◽  
Mafalda Camara ◽  
Philip Pratt ◽  
Justin Vale ◽  
Ara Darzi ◽  
...  
Keyword(s):  
Model Simulation ◽  
Ground Truth ◽  
Ct Scans ◽  
Patient Specific ◽  
Average Error ◽  
Interactive Simulation ◽  
Realistic Representation ◽  
Preoperative Ct ◽  
Simulation Parameters

Abstract Gas insufflation in laparoscopy deforms the abdomen and stretches the overlying skin. This limits the use of surgical image-guidance technologies and challenges the appropriate placement of trocars, which influences the operative ease and potential quality of laparoscopic surgery. This work describes the development of a platform that simulates pneumoperitoneum in a patient-specific manner, using preoperative CT scans as input data. This aims to provide a more realistic representation of the intraoperative scenario and guide trocar positioning to optimize the ergonomics of laparoscopic instrumentation. The simulation was developed by generating 3D reconstructions of insufflated and deflated porcine CT scans and simulating an artificial pneumoperitoneum on the deflated model. Simulation parameters were optimized by minimizing the discrepancy between the simulated pneumoperitoneum and the ground truth model extracted from insufflated porcine scans. Insufflation modeling in humans was investigated by correlating the simulation’s output to real post-insufflation measurements obtained from patients in theatre. The simulation returned an average error of 7.26 mm and 10.5 mm in the most and least accurate datasets respectively. In context of the initial discrepancy without simulation (23.8 mm and 19.6 mm), the methods proposed here provide a significantly improved picture of the intraoperative scenario. The framework was also demonstrated capable of simulating pneumoperitoneum in humans. This study proposes a method for realistically simulating pneumoperitoneum to achieve optimal ergonomics during laparoscopy. Although further studies to validate the simulation in humans are needed, there is the opportunity to provide a more realistic, interactive simulation platform for future image-guided minimally invasive surgery.

scholarly journals LIVER TUMOR SEGMENTATION CT DATA BASED ON ALEXNET-LIKE CONVOLUTION NEURAL NETS

2016 ◽  
Author(s):  
Alexandr N. Korabelnikov ◽  
◽  
Alexandr V. Kolsanov ◽  
Sergey S. Chaplygin ◽  
Pavel M. Zelter ◽  
...  
Keyword(s):  
Liver Tumors ◽  
Automatic Segmentation ◽  
A Priori ◽  
Ground Truth ◽  
Neural Nets ◽  
Average Error ◽  
Tumor Segmentation ◽  
Ct Data ◽  
And Performance ◽  
Anatomical Information

Anatomical structure segmentation on computed tomography (CT) is the key stage in medical visualization and computer diagnosis. Tumors are one of types of internal structures, for which the problem of automatic segmentation today has no solution fully satisfying by quality. The reason is high variance of tumor’s density and inability of using a priori anatomical information about shape. In this paper we propose automatic method of liver tumors segmentation based on convolution neural nets (CNN). Studying and validation have been performed on set of CT with liver and tumors segmentation ground truth. Average error (VOE) by cross-validation is 17.3%. Also there were considered algorithms of pre- and post-processing which increase accuracy and performance of segmentation procedure. Particularly the acceleration of the segmentation procedure with negligible decrease of quality has been reached 6 times.

scholarly journals HOSUR: A Novel Measure for Evaluation of Image Segmentation Quality

2017 ◽  
Vol 1 (1) ◽  
pp. 10-14
Author(s):  
Macmillan Simfukwe ◽  
Bo Peng ◽  
Tianrui Li ◽  
Douglas Kunda
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Ground Truth ◽  
Segmentation Evaluation ◽  
Local Shape ◽  
Evaluation Measures ◽  
Segmentation Quality ◽  
Segmentation Algorithms ◽  
Surf Features ◽  
Evaluation Measure

Image segmentation is one of the vital tasks in image processing. Nevertheless, no universally accepted quality measure for evaluating the performance of various segmentation algorithms or even different parameterizations of the same algorithm exists. In this paper, we propose a new segmentation evaluation measure, based on the fusion of HOG and SURF features. We call it the HOSUR. HOSUR exploits the local shape and corner information to evaluate the similarity between a given segmentation and its respective ground truth. It thus belongs to the category of supervised evaluation measures. Experimental results show accuracy of up to 85%

scholarly journals Semi-automatic Segmentation of Liver Tumors from CT Scans Using Bayesian Rule-based 3D Region Growing

2008 ◽  
Author(s):  
Yingyi Qi ◽  
Wei Xiong ◽  
Wee Keng Leow ◽  
Qi Tian ◽  
Jiayin Zhou ◽  
...  
Keyword(s):  
Liver Tumors ◽  
Automatic Segmentation ◽  
Three Dimensional ◽  
Region Growing ◽  
Ct Scans ◽  
Tumor Segmentation ◽  
Morphological Operations ◽  
Model Matching ◽  
Bayesian Decision ◽  
Seeded Region Growing

Automatic segmentation of liver tumorous regions often fails due to high noise and large variance of tumors. In this work, a semi-automatic algorithm is proposed to segment liver tumors from computed tomography (CT) images. To cope with the variance of tumors, their intensity probability density functions (PDF) are modeled as a bag of Gaussians unlike the previous works where the tumor is modeled as a single Gaussian, and employ a three-dimensional seeded region growing (SRG) method. The bag of Gaussians are initialized at manually selected seeds and updated during growing process iteratively. There are two criteria to be fulfilled for growing: one is the Bayesian decision rule, and the other is a model matching measure. Once the growing is terminated, morphological operations are performed to refine the result. This method, showing promising performance, has been evaluated using ten CT scans of livers with twenty tumors provided by the organizer of the 3D Liver Tumor Segmentation Challenge 2008.

Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentation

2020 ◽  
Vol 64 (4) ◽  
pp. 40412-1-40412-11
Author(s):  
Kexin Bai ◽  
Qiang Li ◽  
Ching-Hsin Wang
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
A Priori ◽  
Class Imbalance ◽  
Maximum Flow ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Similarity Coefficients ◽  
Segmentation Algorithms ◽  
Flow Algorithm

Abstract To address the issues of the relatively small size of brain tumor image datasets, severe class imbalance, and low precision in existing segmentation algorithms for brain tumor images, this study proposes a two-stage segmentation algorithm integrating convolutional neural networks (CNNs) and conventional methods. Four modalities of the original magnetic resonance images were first preprocessed separately. Next, preliminary segmentation was performed using an improved U-Net CNN containing deep monitoring, residual structures, dense connection structures, and dense skip connections. The authors adopted a multiclass Dice loss function to deal with class imbalance and successfully prevented overfitting using data augmentation. The preliminary segmentation results subsequently served as the a priori knowledge for a continuous maximum flow algorithm for fine segmentation of target edges. Experiments revealed that the mean Dice similarity coefficients of the proposed algorithm in whole tumor, tumor core, and enhancing tumor segmentation were 0.9072, 0.8578, and 0.7837, respectively. The proposed algorithm presents higher accuracy and better stability in comparison with some of the more advanced segmentation algorithms for brain tumor images.

Model and Method for Contributor’s Quality Assessment in Community Image Tagging Systems

2018 ◽  
pp. 45-51
Author(s):  
A. V. Ponomarev
Keyword(s):  
Large Scale ◽  
Wide Spectrum ◽  
Preference Relation ◽  
Pairwise Comparison ◽  
Ground Truth ◽  
Comparison Method ◽  
Characteristic Matrix ◽  
Image Tagging ◽  
Proposed Model

Introduction: Large-scale human-computer systems involving people of various skills and motivation into the information processing process are currently used in a wide spectrum of applications. An acute problem in such systems is assessing the expected quality of each contributor; for example, in order to penalize incompetent or inaccurate ones and to promote diligent ones.Purpose: To develop a method of assessing the expected contributor’s quality in community tagging systems. This method should only use generally unreliable and incomplete information provided by contributors (with ground truth tags unknown).Results:A mathematical model is proposed for community image tagging (including the model of a contributor), along with a method of assessing the expected contributor’s quality. The method is based on comparing tag sets provided by different contributors for the same images, being a modification of pairwise comparison method with preference relation replaced by a special domination characteristic. Expected contributors’ quality is evaluated as a positive eigenvector of a pairwise domination characteristic matrix. Community tagging simulation has confirmed that the proposed method allows you to adequately estimate the expected quality of community tagging system contributors (provided that the contributors' behavior fits the proposed model).Practical relevance: The obtained results can be used in the development of systems based on coordinated efforts of community (primarily, community tagging systems). 

scholarly journals Productivity and Nutritional Trait Improvements of Different Tomatoes Cultivated with Effective Microorganisms Technology

Agriculture ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 112
Author(s):  
Giuseppina Tommonaro ◽  
Gennaro Roberto Abbamondi ◽  
Barbara Nicolaus ◽  
Annarita Poli ◽  
Costantino D’Angelo ◽  
...  
Keyword(s):  
Plant Growth Promoting Bacteria ◽  
Effective Microorganisms ◽  
Microbial Inoculation ◽  
Yield And Quality ◽  
Promising Strategy ◽  
Plant Growth Promoting ◽  
Growth Promoting ◽  
Traditional Approaches ◽  
Nutritional Aspect

The use of ecofriendly strategies, such as the use of Plant Growth Promoting Bacteria, to improve the yield and quality of crops has become necessary to satisfy the growing demand of food and to avoid the use of chemical fertilizers and pesticides. In this study, we report the effects of an innovative microbial inoculation technique, namely Effective Microorganisms (EM), compared with traditional approaches, on productivity and nutritional aspect of four tomato varieties: Brandywine, Corbarino Giallo, S. Marzano Cirio 3, S. Marzano Antico. Results showed an increase of plant productivity as well as an enhanced antioxidant activity mainly in San Marzano Antico and Brandywine varieties treated with EM technology. Moreover, the polyphenol and carotenoid contents also changed, in response to the plant treatments. In conclusion, the application of EM® technology in agriculture could represent a very promising strategy in agricultural sustainability.

scholarly journals Systematic Review of the Integrative Medicine Recommendations for Patients with Pancreatic Cancer

Surgeries ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 216-230
Author(s):  
Andrew A. Gumbs ◽  
Manana Gogol ◽  
Gaya Spolverato ◽  
Hebatallah Taher ◽  
Elie K. Chouillard
Keyword(s):  
Systematic Review ◽  
Pancreatic Cancer ◽  
Integrative Medicine ◽  
Lifestyle Changes ◽  
Randomized Controlled ◽  
Nutrition Supplementation ◽  
Traditional Therapies ◽  
Traditional Approaches

Introduction: Integrative medicine (IM) is a relatively new field where non-traditional therapies with peer-reviewed evidence are incorporated or integrated with more traditional approaches. Methods: A systematic review of the literature from the last 10 years was done by searching clinical trials and randomized-controlled trials on Pubmed that discuss nutrition, supplementation, and lifestyle changes associated with “Pancreatic Cancer.” Results: Only 50 articles ultimately met the inclusion criteria for this review. A total of 15 articles discussed the role of obesity and 10 discussed the influence of stress in increasing the risk of pancreatic cancer. Six discussed the potential beneficial role of Vitamins, 5 of cannabinoids, 4 an anti-inflammatory diet, 3 of nut consumption, 2 of green tea consumption, 2 of curcumin supplementation, 1 role of melatonin, and 1 of probiotics. One article each was found on the theoretical benefits of adhering to either a Mediterranean or ketogenic diet. Discussion: As more surgeons become interested in IM, it is hoped that more diseases where the curative treatment is mainly surgical can benefit from the all-encompassing principles of IM in an effort to improve quality of life and survival in patients with pancreatic cancer.

scholarly journals IMG-22. A DEEP LEARNING MODEL FOR AUTOMATIC POSTERIOR FOSSA PEDIATRIC BRAIN TUMOR SEGMENTATION: A MULTI-INSTITUTIONAL STUDY

2020 ◽  
Vol 22 (Supplement_3) ◽  
pp. iii359-iii359
Author(s):  
Lydia Tam ◽  
Edward Lee ◽  
Michelle Han ◽  
Jason Wright ◽  
Leo Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Posterior Fossa ◽  
Ground Truth ◽  
Learning Model ◽  
Tumor Segmentation ◽  
Dice Similarity Coefficient ◽  
Study Cohort ◽  
Navigation Systems ◽  
Tumor Types ◽  
Deep Learning Model

Abstract BACKGROUND Brain tumors are the most common solid malignancies in childhood, many of which develop in the posterior fossa (PF). Manual tumor measurements are frequently required to optimize registration into surgical navigation systems or for surveillance of nonresectable tumors after therapy. With recent advances in artificial intelligence (AI), automated MRI-based tumor segmentation is now feasible without requiring manual measurements. Our goal was to create a deep learning model for automated PF tumor segmentation that can register into navigation systems and provide volume output. METHODS 720 pre-surgical MRI scans from five pediatric centers were divided into training, validation, and testing datasets. The study cohort comprised of four PF tumor types: medulloblastoma, diffuse midline glioma, ependymoma, and brainstem or cerebellar pilocytic astrocytoma. Manual segmentation of the tumors by an attending neuroradiologist served as “ground truth” labels for model training and evaluation. We used 2D Unet, an encoder-decoder convolutional neural network architecture, with a pre-trained ResNet50 encoder. We assessed ventricle segmentation accuracy on a held-out test set using Dice similarity coefficient (0–1) and compared ventricular volume calculation between manual and model-derived segmentations using linear regression. RESULTS Compared to the ground truth expert human segmentation, overall Dice score for model performance accuracy was 0.83 for automatic delineation of the 4 tumor types. CONCLUSIONS In this multi-institutional study, we present a deep learning algorithm that automatically delineates PF tumors and outputs volumetric information. Our results demonstrate applied AI that is clinically applicable, potentially augmenting radiologists, neuro-oncologists, and neurosurgeons for tumor evaluation, surveillance, and surgical planning.

Sign in / Sign up

Export Citation Format

Share Document