Computational techniques to segment and classify lumbar compression fractures

Arpitha, Adela; Rangarajan, Lalitha

doi:10.1007/s11547-020-01145-7

Cited by 20 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…26 ). The risk factors associated with insufficiency fractures are advanced age, post-menopausal state, osteoporosis and lower body mass index [ 70 , 98 , 99 ]. Sapienza and colleagues [ 100 ] analyzed 21 studies including 3929 patients treated by RT for gynecologic cancers and found that 14% developed insufficiency fractures.…”

Section: Imaging Findingsmentioning

confidence: 99%

Imaging side effects and complications of chemotherapy and radiation therapy: a pictorial review from head to toe

et al. 2021

View full text Add to dashboard Cite

Newer biologic drugs and immunomodulatory agents, as well as more tolerated and effective radiation therapy schemes, have reduced treatment toxicity in oncology patients. However, although imaging assessment of tumor response is adapting to atypical responses like tumor flare, expected changes and complications of chemo/radiotherapy are still routinely encountered in post-treatment imaging examinations. Radiologists must be aware of old and newer therapeutic options and related side effects or complications to avoid a misinterpretation of imaging findings. Further, advancements in oncology research have increased life expectancy of patients as well as the frequency of long-term therapy-related side effects that once could not be observed. This pictorial will help radiologists tasked to detect therapy-related complications and to differentiate expected changes of normal tissues from tumor relapse.

show abstract

Section: Imaging Findingsmentioning

confidence: 99%

Imaging side effects and complications of chemotherapy and radiation therapy: a pictorial review from head to toe

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The lack of early biomarkers elicits the development of valuable imaging methods [4]. Magnetic resonance imaging (MRI) is the modality of choice for diagnosing degenerative changes of knee toward OA, even if it can give limited information to detect early stages of OA and subtle changes in response to therapy [5][6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

T2-mapping MRI evaluation of patellofemoral cartilage in patients submitted to intra-articular platelet-rich plasma (PRP) injections

et al. 2021

View full text Add to dashboard Cite

This study evaluated the ability of T2 mapping magnetic resonance imaging at 3 T, in addition to morphological sequences, to assess efficacy of platelet-rich plasma (PRP) injections, characterizing qualitatively and quantitatively the grade of knee cartilage repair in patients with patellofemoral chondropathy. We retrospectively studied 34 patients (22 men, 12 women, mean age 41.8 years, including 22 men) with patellofemoral knee chondropathy, who underwent intra-articular PRP injections and completed a clinical and instrumental follow-up. As control group, we evaluated 34 patients who underwent non-operative therapy. All patients were submitted to clinical (using VAS and WOMAC index) and imaging studies with 3 T magnetic resonance with cartilage analysis with T2 mapping sequences for cartilage analysis before and after treatment. In the study group, mean pre-treatment T2 relaxation time values were 44.2 ± 2.5 ms, considering all articular cartilage compartments, with significant reduction at the follow-up (p < 0.001). At the index compartment, mean pre-treatment T2 relaxation times values were 47.8 ± 3.6 ms, with statistically significant reduction at the follow-up (p < 0.001). Evaluation of focal cartilage lesions reported pre-treatment mean T2 value of 70.1 ± 13.0 ms and post-treatment mean value of 59.9 ± 4.6 ms (p < 0.001). From a clinical point of view, the pre-treatment WOMAC and VAS scores were 18.3 ± 4.5 and 7 (IQR:6–7.2), respectively; the post-treatment values were 7.3 ± 3.2 and 2 (IQR: 1.7–3.0), respectively (p < 0.001). In the control group, despite clinical improvement, we didn’t find significant T2 values change during the follow-up period. In conclusion, T2 mapping is a valuable indicator for chondropathy and treatment-related changes over time.

show abstract

“…Therefore, manual measurement increases the likelihood of misdiagnosis, inter-observer variability, and delayed diagnosis, which can be fatal for the patient 9 , 10 . Consequently, there have been studies on various methods for overcoming these shortcomings 11 , 12 .…”

Section: Introductionmentioning

confidence: 99%

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images

Seo

Lim

Jeong

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U-Net model, with an average sensitivity of 0.934 (± 0.086), an average specificity of 0.997 (± 0.002), an average accuracy of 0.987 (± 0.005), and an average dice similarity coefficient of 0.923 (± 0.073). We then generated 1134 data points on the images of three vertebral bodies by labeling each segment of the segmented vertebral body. These were used in the vertebral compression measurement model based on linear regression and multi-scale residual dilated blocks. The model yielded an average mean absolute error of 2.637 (± 1.872) (%), an average mean square error of 13.985 (± 24.107) (%), and an average root mean square error of 3.739 (± 2.187) (%) in fractured vertebral body data. The proposed algorithm has significant potential for aiding the diagnosis of vertebral compression fractures.

show abstract

Computational techniques to segment and classify lumbar compression fractures

Cited by 20 publications

References 19 publications

Imaging side effects and complications of chemotherapy and radiation therapy: a pictorial review from head to toe

Imaging side effects and complications of chemotherapy and radiation therapy: a pictorial review from head to toe

T2-mapping MRI evaluation of patellofemoral cartilage in patients submitted to intra-articular platelet-rich plasma (PRP) injections

A deep learning algorithm for automated measurement of vertebral body compression from X-ray images

Contact Info

Product

Resources

About