Automated segmentation of osteoblastic vertebral metastasis: a radiomics approach

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.

Download Full-text

Effectiveness of Antalgic Therapies in Patients with Vertebral Bone Metastasis: A Protocol for a Systematic Review and Meta-Analysis

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18083991 ◽

2021 ◽

Vol 18 (8) ◽

pp. 3991

Author(s):

Antonio Jose Martin-Perez ◽

María Fernández-González ◽

Paula Postigo-Martin ◽

Marc Sampedro Pilegaard ◽

Carolina Fernández-Lao ◽

...

Keyword(s):

Systematic Review ◽

Bone Metastasis ◽

Data Extraction ◽

Meta Analysis ◽

Risk Of Bias ◽

Cochrane Library ◽

Pharmacological Intervention ◽

Vertebral Metastasis ◽

Randomized Controlled Clinical Trials

There is no systematic review that has identified existing studies evaluating the pharmacological and non-pharmacological intervention for pain management in patients with bone metastasis. To fill this gap in the literature, this systematic review with meta-analysis aims to evaluate the effectiveness of different antalgic therapies (pharmacological and non-pharmacological) in the improvement of pain of these patients. To this end, this protocol has been written according to the Preferred Reporting Items for Systematic review and Meta-Analysis Protocols (PRISMA-P) and registered in PROSPERO (CRD42020135762). A systematic search will be carried out in four international databases: Medline (Via PubMed), Web of Science, Cochrane Library and SCOPUS, to select the randomized controlled clinical trials. The Risk of Bias Tool developed by Cochrane will be used to assess the risk of bias and the quality of the identified studies. A narrative synthesis will be used to describe and compare the studies, and after the data extraction, random effects model and a subgroup analyses will be performed according to the type of intervention, if possible. This protocol aims to generate a systematic review that compiles and synthesizes the best and most recent evidence on the treatment of pain derived from vertebral metastasis.

Download Full-text

Vertebral Metastasis Treated by Vertebroplasty, a Cause of Respiratory Failure: Case Report and Literature Review

Case Reports in Oncology ◽

10.1159/000513492 ◽

2021 ◽

pp. 279-283

Author(s):

Mathieu Chevallier ◽

Chloé Chevallier-Lugon ◽

Alex Friedlaender ◽

Alfredo Addeo

Keyword(s):

Spinal Fractures ◽

Safe Procedure ◽

Vertebral Metastasis ◽

Minimally Invasive Surgical Procedure ◽

Venous Circulation ◽

Minimally Invasive Surgical ◽

Life Threatening ◽

Frequent Site ◽

The Right ◽

Substantial Morbidity

Bone is a frequent site of metastases in advanced cancers including lung, breast, prostate, kidney, or myeloma. Lesions are commonly located on the spine. Neoplastic invasion of the vertebral body can result in painful vertebral fractures, leading to disability and substantial morbidity. Percutaneous vertebroplasty is a minimally invasive surgical procedure used to treat spinal fractures due to osteolytic tumors. It could result in pain reduction or resolution in 80–90% of patients with fractures, and it improves stability. Although considered safe, vertebroplasty has been associated over the years with life-threatening complications. We have reported the case of a 55-year-old patient with lung adenocarcinoma, who underwent vertebroplasty for a pathological neoplastic fracture of L2. The procedure was complicated by a leak of cement into the systemic venous circulation, characterized by an 11-cm filament in the right heart chambers and multiple pulmonary emboli. To our knowledge, only one similar case was previously reported, involving an intracardiac cement filament longer than 10 cm. The data are scant, hence the importance of collecting and reporting possible complications about what is perceived as a rather safe procedure. The case highlights the need for a robust postprocedure imaging plan to detect complications, which can impact patients’ morbidity and survival.

Download Full-text

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Scientific Reports ◽

10.1038/s41598-020-80619-0 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

C. A. Neves ◽

E. D. Tran ◽

I. M. Kessler ◽

N. H. Blevins

Keyword(s):

Facial Nerve ◽

Inner Ear ◽

Temporal Bone ◽

Hausdorff Distance ◽

Sigmoid Sinus ◽

Ct Scans ◽

Automated Segmentation ◽

Dice Coefficient ◽

Lateral Skull Base ◽

End To End

AbstractMiddle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.

Download Full-text