TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images.

Purpose: To present a deep learning segmentation model that can automatically and robustly segment all major anatomic structures on body CT images. Materials and Methods: In this retrospective study, 1204 CT examinations (from 2012, 2016, and 2020) were used to segment 104 anatomic structures (27 organs, 59 bones, 10 muscles, and eight vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiation therapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, abnormalities, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients to evaluate the model's performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age-dependent volume and attenuation changes. Results: The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major abnormalities. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 vs 0.871; P < .001). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (eg, age and aortic volume [rs = 0.64; P < .001]; age and mean attenuation of the autochthonous dorsal musculature [rs = -0.74; P < .001]). Conclusion: The developed model enables robust and accurate segmentation of 104 anatomic structures. The annotated dataset (https://doi.org/10.5281/zenodo.6802613) and toolkit (https://www.github.com/wasserth/TotalSegmentator) are publicly available.Keywords: CT, Segmentation, Neural Networks Supplemental material is available for this article. © RSNA, 2023See also commentary by Sebro and Mongan in this issue.

Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT.

PURPOSE/OBJECTIVE: Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams. METHODS & MATERIALS: A cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters. RESULTS: We evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively). CONCLUSION: Re-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.

Sonographic real-time imaging of tissue perfusion in a porcine haemorrhagic shock model.

Injection of fluorescence-labelled microspheres (FMs) in pigs allows only the postmortem determination of organ perfusion. Colour duplex ultrasound (CDU) and contrast-enhanced ultrasound were established as techniques for real-time imaging of tissue perfusion in a porcine haemorrhagic shock model. Haemorrhagic shock was provoked in nine domestic pigs by taking at least 15% of the calculated blood volume. Ultrasound examinations were performed with a Hitachi HI VISION Ascendus. SonoVue was injected for contrast-enhanced ultrasound. Monitoring of the resistive index and time-to-peak ratio enabled quantification of tissue perfusion in vivo during the entire study, allowing real-time differentiation of animals with systemic shock versus failing shock effect. Postmortem analyses of injected FMs confirmed the sonographic in vivo results. Determination of the resistive index and time-to-peak ratio by CDU and contrast-enhanced ultrasound allowed real-time monitoring of tissue perfusion. Effects of haemorrhagic shock and therapeutic approaches related to organ perfusion can be observed live and in vivo.

Use of vacuum-assisted closure negative pressure wound therapy in combat-related injuries--literature review.

Despite surgical and technological advances, managing combat-related injuries remains challenging both within and outside of the war theater. Unique characteristics of a war theater such as environmental contamination, varying evacuation procedures, and differing levels of medical care, add to the complexity. The advent of body armor has increased blast survival rates and soldiers are surviving with increasingly mangled limbs that require lengthy, multifaceted care. An inherent high risk of infection contraindicates immediate closure for these wounds. There is growing reported use of negative pressure wound therapy with reticulated open-cell foam (NPWT/ROCF) as delivered by vacuum-assisted closure (VAC) therapy (KCI Licensing Inc., San Antonio, TX) as an adjunctive therapy in these open soft-tissue combat wounds. This review evaluates the efficacy of NPWT/ROCF for adjunctive treatment of wartime wounds. Following a literature review, data are summarized and presented.

Classification--important step to improve management of patients with an open abdomen.

This short report is a distillation of the proceedings from a consensus group meeting in January 2009. It outlines a proposed classification system for patients with an open abdomen (OA). The classification allows (1) a description of the patient's clinical course; (2) standardized clinical guidelines for improving OA management; and (3) improved reporting of OA status, which will facilitate comparisons between studies and heterogeneous patient populations. The following grading is suggested: grade 1A, clean OA without adherence between bowel and abdominal wall or fixity of the abdominal wall (lateralization); grade 1B, contaminated OA without adherence/fixity; grade 2A, clean OA developing adherence/fixity; grade 2B, contaminated OA developing adherence/fixity; grade 3, OA complicated by fistula formation; grade 4, frozen OA with adherent/fixed bowel, unable to close surgically, with or without fistula. We propose that this classification system will facilitate communication, clarify OA management, and potentially improve patient care.