Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 2;63(1):ezad014.
doi: 10.1093/ejcts/ezad014.

Preoperative visualization of congenital lung abnormalities: hybridizing artificial intelligence and virtual reality

Affiliations

Preoperative visualization of congenital lung abnormalities: hybridizing artificial intelligence and virtual reality

Wouter Bakhuis et al. Eur J Cardiothorac Surg. .

Abstract

Objectives: When surgical resection is indicated for a congenital lung abnormality (CLA), lobectomy is often preferred over segmentectomy, mostly because the latter is associated with more residual disease. Presumably, this occurs in children because sublobar surgery often does not adhere to anatomical borders (wedge resection instead of segmentectomy), thus increasing the risk of residual disease. This study investigated the feasibility of identifying eligible cases for anatomical segmentectomy by combining virtual reality (VR) and artificial intelligence (AI).

Methods: Semi-automated segmentation of bronchovascular structures and lesions were visualized with VR and AI technology. Two specialists independently evaluated via a questionnaire the informative value of regular computed tomography versus three-dimensional (3D) VR images.

Results: Five asymptomatic, non-operated cases were selected. Bronchovascular segmentation, volume calculation and image visualization in the VR environment were successful in all cases. Based on the computed tomography images, assignment of the CLA lesion to specific lung segments matched between the consulted specialists in only 1 out of the cases. Based on the three 3D VR images, however, the localization matched in 3 of the 5 cases. If the patients would have been operated, adding the 3D VR tool to the preoperative workup would have resulted in changing the surgical strategy (i.e. lobectomy versus segmentectomy) in 4 cases.

Conclusions: This study demonstrated the technical feasibility of a hybridized AI-VR visualization of segment-level lung anatomy in patients with CLA. Further exploration of the value of 3D VR in identifying eligible cases for anatomical segmentectomy is therefore warranted.

Keywords: Congenital lung abnormalities; Congenital pulmonary airway malformations; Paediatric lung surgery; Segmentectomy; Virtual reality.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Assessment of CLA lesion size, affect lung lobes and lung segments and determination of lung segment sparing based on both imaging modalities. In the questionnaire, the paediatric thoracic surgeon and the radiologist scored the 5 cases from 1 (strongly disagree) to 5 (strongly agree). 2D-CT: two-dimensional computed tomography; 3D-VR: three-dimensional virtual reality; CLA: congenital lung abnormality
Figure 2:
Figure 2:
Surgical information among different imaging modalities. Surgical information about the CLA lesions was gathered from the questionnaire filled in by the paediatric thoracic surgeon. Scored from 1 (strongly disagree) to 5 (strongly agree). Q1: the pulmonary artery branches that need to be ligated can be determined on this imaging modality; Q2: the pulmonary vein branches that need to be ligated can be determined on this imaging modality; Q3: the bronchial branches that need to be ligated can be determined on this imaging modality; Q4: surgical strategy [(multi)segmentectomy or lobectomy] can be decided upon based on this imaging modality; Q5: this modality prepares me for surgery; Q6: I am likely to consult this scan in the preoperative planning; and Q7: I am likely to consult this scan during surgery. 2D-CT: two-dimensional computed tomography; 3D-VR: three-dimensional virtual reality; CLA: congenital lung abnormality; LLL: left lower lobe; LUL: left upper lobe; Q: question; RLL: right lower lobe.
Figure 3:
Figure 3:
Right lower lobe segmentation: BPS of patient 3. Frontal Pulmo3D view after disabling S7, with BPS encircled, showing that the BPS is located in the right lower lobe. Segment 6 is affected as well, but arterial supply of BPS is not visualized. BPS: bronchopulmonary sequestration.
Figure 4:
Figure 4:
Right lower lobe segmentation: CPAM in extra lung segment of patient 4. (A) Frontal PulmoVR view, showing all bronchial branches of right lower lobe. Five bronchial branches were visualized (B6–B10), although 6 segments were reconstructed (SX). (B) Dorsal Pulmo3D view, showing CPAM involvement in all 4 visible segments (S6, S7, S10 and SX). CPAM: congenital pulmonary airway malformation; S: segment.
Figure 5:
Figure 5:
Left lower lobe segmentation: BPS of patient 5. (A) Dorsal Pulmo3D view showing the relation of the BPS with the aberrant arterial supply and venous drainage. (B) Frontal PulmoVR view of bronchial tree, with all bronchial branches of left lower lobe coloured. Additional bronchial branch is visible in white. 3D: three-dimensional; BPS: bronchopulmonary sequestration.
None

References

    1. Andrade CF, da Costa Ferreira HP, Fischer GB.. Malformações pulmonares congênitas. J Bras Pneumol 2011;37:259–71. - PubMed
    1. Hermelijn SM, Elders BBLJ, Ciet P, Wijnen RMH, Tiddens HAWM, Schnater JM. et al. A clinical guideline for structured assessment of CT-imaging in congenital lung abnormalities. Paediatr Respir Rev 2021;37:80–8. - PubMed
    1. Stocker LJ, Wellesley DG, Stanton MP, Parasuraman R, Howe DT.. The increasing incidence of foetal echogenic congenital lung malformations: an observational study. Prenat Diagn 2015;35:148–53. - PubMed
    1. Peters NCJ, Hijkoop A, Hermelijn SM, Van Schoonhoven MM, Eggink AJ, Van Rosmalen J et al. Prediction of postnatal outcome in fetuses with a congenital lung malformation: a 2‐year follow‐up study. Ultrasound Obstet Gynecol 2021;58:428–38. doi:10.1002/uog.23542. - DOI - PubMed
    1. Stanton M, Njere I, Ade-Ajayi N, Patel S, Davenport M.. Systematic review and meta-analysis of the postnatal management of congenital cystic lung lesions. J Pediatr Surg 2009;44:1027–33. - PubMed