Residual Set Up Errors of the Surrogate-guided Registration Using Four-dimensional CT Images and Breath Holding Ones in Respiratory Gated Radiotherapy for Liver Cancer

BACKGROUND The Covid-19 pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a public health challenge being faced by the world currently. International and national responses to combat the Covid-19 pandemic have been very prompt with the setting up of dedicated Covid-19 hospitals. In the state of Odisha, situated in the eastern part of India, Kalinga Institute of Medical Sciences (KIMS), set up the first dedicated Covid hospital of the state. This study intends to chronicle the clinical profile, radiological presentations, laboratory findings, and clinical outcome of patients admitted to the KIMS Covid hospital. METHODS A retrospective analysis of the clinical and laboratory data of patients admitted with Covid-19 diagnosis at the dedicated Covid-19 hospital from 5th April 2020 to 4th June 2020 was done. RESULTS A total number of 272 Covid-19 cases were included in this study. Majority of the patients were males (83.57 %) and most of the patients (79.04 %) were asymptomatic. The mortality rate was 1.9 %. Fever (18.38 %), cough (17.27 %), dyspnoea (16.91 %) and myalgia (14.7 %) were the major symptoms observed. Severity was mild in 78.94 % cases. Delayed viral clearance was seen in 13 % cases. The typical features of novel SARS-CoV-2 infection was seen in 12 - 13 % cases in computed tomography (CT) images of thorax. c-reactive protein (CRP) was raised as a biomarker of inflammation. Of the 5 deaths encountered, 2 had diabetes mellitus, 2 were hypertensive and 1 had chronic obstructive pulmonary disease (COPD). CONCLUSIONS Covid-19 may have a delayed viral clearance beyond two weeks. A discordance between CT images and the clinical condition may also be observed. Diabetes, hypertension, and high blood CRP levels were significantly associated with mortality. KEYWORDS Covid-19, SARS-CoV-2, Clinical Profile, Radiological Findings, Comorbidities, Fatality

Download Full-text

Non-Rigid Liver Registration in Liver Computed Tomography Images Using Elastic Method with Global and Local Deformations

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3355 ◽

2021 ◽

Vol 11 (3) ◽

pp. 810-816

Author(s):

Taeyong Park ◽

Jeongjin Lee ◽

Juneseuk Shin ◽

Kyoung Won Kim ◽

Ho Chul Kang

Keyword(s):

Computed Tomography ◽

Liver Cancer ◽

Ct Images ◽

Local Deformation ◽

Rigid Registration ◽

Liver Ct ◽

Liver Surface ◽

Global And Local ◽

Local Deformations

The study of follow-up liver computed tomography (CT) images is required for the early diagnosis and treatment evaluation of liver cancer. Although this requirement has been manually performed by doctors, the demands on computer-aided diagnosis are dramatically growing according to the increased amount of medical image data by the recent development of CT. However, conventional image segmentation, registration, and skeletonization methods cannot be directly applied to clinical data due to the characteristics of liver CT images varying largely by patients and contrast agents. In this paper, we propose non-rigid liver segmentation using elastic method with global and local deformation for follow-up liver CT images. To manage intensity differences between two scans, we extract the liver vessel and parenchyma in each scan. And our method binarizes the segmented liver parenchyma and vessel, and performs the registration to minimize the intensity difference between these binarized images of follow-up CT images. The global movements between follow-up CT images are corrected by rigid registration based on liver surface. The local deformations between follow-up CT images are modeled by non-rigid registration, which aligns images using non-rigid transformation, based on locally deformable model. Our method can model the global and local deformation between follow-up liver CT scans by considering the deformation of both the liver surface and vessel. In experimental results using twenty clinical datasets, our method matches the liver effectively between follow-up portal phase CT images, enabling the accurate assessment of the volume change of the liver cancer. The proposed registration method can be applied to the follow-up study of various organ diseases, including cardiovascular diseases and lung cancer.

Download Full-text

Company News

Asia-Pacific Biotech News ◽

10.1142/s0219030303000326 ◽

2003 ◽

Vol 07 (04) ◽

pp. 140-149

Keyword(s):

Liver Cancer ◽

Human Liver ◽

Research Collaboration ◽

Asia Pacific ◽

Tropical Diseases ◽

Cancer Trial ◽

Human Trial ◽

Knowledge Industry ◽

Human Liver Cancer ◽

Set Up

Progen Begins Human Liver Cancer Trial with PI-166. Melanotan Phase IIb Human Trial Begins. Bionomics Develops Model to Accelerate Angiogenesis Drug Discovery. Chemeq Develops Non Absorbable Sunscreen and Skin Emollient. China Worldbest Group Acquires Subsidiaries. China Business In Brief. Ranbaxy to Launch Branded Generics in US. IPCA Labs Plans to Invest in New Plant in US. Eisai to Collaborate with Mitsui Knowledge Industry. Takeda and Beth Israel Sign Research Agreement on Endocrinology. Bionet Co. APBioNet Received Grant Injection from Pan Pacific Networking Program. DenX Sets Up First Asia Pacific Subsidiary in Singapore. MerLion Pharmaceuticals and KuDOS Pharmaceuticals Launch Research Collaboration. Novartis Institute of Tropical Diseases to be Set Up in Singapore.

Download Full-text

Survival prediction of liver cancer patients from CT images using deep learning and radiomic feature-based regression

Medical Imaging 2020: Computer-Aided Diagnosis ◽

10.1117/12.2551349 ◽

2020 ◽

Author(s):

Hansang Lee ◽

Helen Hong ◽

Jinsil Seong ◽

Jin Sung Kim ◽

Junmo Kim

Keyword(s):

Deep Learning ◽

Liver Cancer ◽

Cancer Patients ◽

Ct Images ◽

Survival Prediction ◽

Feature Based

Download Full-text

SU-FF-J-82: Improving Soft Tissue Contrast in 4D CT Images of Liver Cancer Patients Using Deformable Image Registration Method

Medical Physics ◽

10.1118/1.2240859 ◽

2006 ◽

Vol 33 (6Part6) ◽

pp. 2039-2039

Author(s):

H Wang ◽

S Krishnan ◽

X Wang ◽

A Beddar ◽

T Briere ◽

...

Keyword(s):

Soft Tissue ◽

Image Registration ◽

Liver Cancer ◽

Cancer Patients ◽

Deformable Image Registration ◽

Ct Images ◽

Registration Method ◽

4D Ct ◽

Soft Tissue Contrast ◽

Tissue Contrast

Download Full-text

SU-E-J-140: Availability of Using Diaphragm Matching in Stereotactic Body Radiotherapy (SBRT) at the Time in Breath-Holding SBRT for Liver Cancer

Medical Physics ◽

10.1118/1.4888193 ◽

2014 ◽

Vol 41 (6Part8) ◽

pp. 188-188

Author(s):

D Kawahara ◽

S Ozawa ◽

T. Nakashima ◽

M. Aita ◽

S. Tsuda ◽

...

Keyword(s):

Liver Cancer ◽

Stereotactic Body Radiotherapy ◽

Breath Holding

Download Full-text

Application of deep learning for clinical predictive modeling: An artificial intelligence recognition in spinal metastases.

Journal of Clinical Oncology ◽

10.1200/jco.2019.37.15_suppl.e18050 ◽

2019 ◽

Vol 37 (15_suppl) ◽

pp. e18050-e18050 ◽

Cited By ~ 1

Author(s):

Hui Zhao ◽

Guangyu Yao ◽

Yiyi Zhou ◽

Zhiyu Wang

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Data Augmentation ◽

Malignant Tumors ◽

Spinal Metastases ◽

Ct Images ◽

Spinal Ct ◽

Metastatic Lesions ◽

Set Up ◽

Vertebrae Segmentation

e18050 Background: Spinal metastases are very common outcomes within solid malignant tumors, which could lead to various skeletal related events (SREs). The accurate and timely diagnosis is the key to improve prognosis. Recently, artificial intelligence(AI) has assisted doctors in many ways by different AI technologies. In this study, we applicated a deep learning model to classify and locate the metastatic lesions on spinal CT images. Methods: We set up a dataset consisting of 800 patients’ spinal CT images, which contained over 300,000 CT slices. And we built a multi-label classification and vertebrae segmentation model to recognize the metastatic lesions on spinal CT images. Then we trained and tested this model within our dataset, using a data augmentation by random flips and random rotations. Sensitivity and specificity were used to evaluate the performance of the model. Results: Our model showed that the diagnostic utilities of normal lesions were: sensitivity 81.7% and specificity 92%; while the diagnostic utilities of metastatic lesions were: sensitivity 84.7% and specificity 84.5%. Conclusions: Our model can effectively and accurately discriminate spinal metastases on spinal CT images. [Table: see text]

Download Full-text