Automated segmentation of the incus and malleus ossicles in conventional tri-dimensional computed tomography images

Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI

Background

Whole-body diffusion weighted imaging (WB-DWI) has proven value to detect multiple myeloma (MM) lesions. However, the large volume of imaging data and the presence of numerous lesions makes the reading process challenging. The aim of the current study was to develop a semi-automatic lesion segmentation algorithm for WB-DWI images in MM patients and to evaluate this smart-algorithm (SA) performance by comparing it to the manual segmentations performed by radiologists.

Methods

An atlas-based segmentation was developed to remove the high-signal intensity normal tissues on WB-DWI and to restrict the lesion area to the skeleton. Then, an outlier threshold-based segmentation was applied to WB-DWI images, and the segmented area’s signal intensity was compared to the average signal intensity of a low-fat muscle on T1-weighted images. This method was validated in 22 whole-body DWI images of patients diagnosed with MM. Dice similarity coefficient (DSC), sensitivity and positive predictive value (PPV) were computed to evaluate the SA performance against the gold standard (GS) and to compare with the radiologists. A non-parametric Wilcoxon test was also performed. Apparent diffusion coefficient (ADC) histogram metrics and lesion volume were extracted for the GS segmentation and for the correctly identified lesions by SA and their correlation was assessed.

Results

The mean inter-radiologists DSC was 0.323 ± 0.268. The SA vs GS achieved a DSC of 0.274 ± 0.227, sensitivity of 0.764 ± 0.276 and PPV 0.217 ± 0.207. Its distribution was not significantly different from the mean DSC of inter-radiologist segmentation (p = 0.108, Wilcoxon test). ADC and lesion volume intraclass correlation coefficient (ICC) of the GS and of the correctly identified lesions by the SA was 0.996 for the median and 0.894 for the lesion volume (p < 0.001). The duration of the lesion volume segmentation by the SA was, on average, 10.22 ± 0.86 min, per patient.

Conclusions

The SA provides equally reproducible segmentation results when compared to the manual segmentation of radiologists. Thus, the proposed method offers robust and efficient segmentation of MM lesions on WB-DWI. This method may aid accurate assessment of tumor burden and therefore provide insights to treatment response assessment.

An Overview of Segmentation Algorithms for the Analysis of Anomalies on Medical Images

Human disease identification from the scanned body parts helps medical practitioners make the right decision in lesser time. Image segmentation plays a vital role in automated diagnosis for the delineation of anatomical organs and anomalies. There are many variants of segmentation algorithms used by current researchers, whereas there is no universal algorithm for all medical images. This paper classifies some of the widely used medical image segmentation algorithms based on their evolution, and the features of each generation are also discussed. The comparative analysis of segmentation algorithms is done based on characteristics like spatial consideration, region continuity, computation complexity, selection of parameters, noise immunity, accuracy, and computation time. Finally, in this work, some of the typical segmentation algorithms are implemented on real-time datasets using Matlab 2010 software, and the outcome of this work will be an aid for the researchers in medical image processing.

Panel 2: Anatomy (Eustachian Tube, Middle Ear, and Mastoid-Anatomy, Physiology, Pathophysiology, and Pathogenesis)

Objective In this report, we review the recent literature (ie, past 4 years) to identify advances in our understanding of the middle ear-mastoid-eustachian tube system. We use this review to determine whether the short-term goals elaborated in the last report were achieved, and we propose updated goals to guide future otitis media research. Data Sources PubMed, Web of Science, Medline. Review Methods The panel topic was subdivided, and each contributor performed a literature search within the given time frame. The keywords searched included middle ear, eustachian tube, and mastoid for their intersection with anatomy, physiology, pathophysiology, and pathology. Preliminary reports from each panel member were consolidated and discussed when the panel met on June 11, 2015. At that meeting, the progress was evaluated and new short-term goals proposed. Conclusions Progress was made on 13 of the 20 short-term goals proposed in 2011. Significant advances were made in the characterization of middle ear gas exchange pathways, modeling eustachian tube function, and preliminary testing of treatments for eustachian tube dysfunction. Implications for Practice In the future, imaging technologies should be developed to noninvasively assess middle ear/eustachian tube structure and physiology with respect to their role in otitis media pathogenesis. The new data derived from these structure/function experiments should be integrated into computational models that can then be used to develop specific hypotheses concerning otitis media pathogenesis and persistence. Finally, rigorous studies on medical or surgical treatments for eustachian tube dysfunction should be undertaken.

Finite element analysis of auditory characteristics in patients with middle ear diseases

CONCLUSION

This study validates that a finite element model of the human ossicular chain and tympanic membrane can be used as an effective surgical assessment tool in clinics.

OBJECTIVE

The present study was performed to investigate the application of a finite element model of ossicular chain and tympanic membrane for fabrication of individualized artificial ossicles.

METHODS

Twenty patients (20 ears) who underwent surgery for middle ear disease (n = 20) and 10 healthy controls (10 ears) were enrolled in the hospital. Computed tomography (CT) and pure tone audiometry were performed before and after surgery. A finite element model was developed using CT scans, and correlation analysis was conducted between stapes displacement and surgical methods. An audiometric test was also performed for 14 patients before and after surgery.

RESULTS

Stapes displacement in the healthy group (average = 3.31 × 10^-5 mm) was significantly greater than that in the impaired group (average = 1.41 × 10^-6 mm) prior to surgery. After surgery, the average displacement in the impaired group was 2.55 × 10^-6 mm, which represented a significant improvement. For the patients who underwent the audiometric test, 10 improved hearing after surgery, and stapes displacement increased in nine of these 10 patients.