Dataset Information

Development and Validation of Image-Based Deep Learning Models to Predict Surgical Complexity and Complications in Abdominal Wall Reconstruction.

ABSTRACT:

Importance

Image-based deep learning models (DLMs) have been used in other disciplines, but this method has yet to be used to predict surgical outcomes.

Objective

To apply image-based deep learning to predict complexity, defined as need for component separation, and pulmonary and wound complications after abdominal wall reconstruction (AWR).

Design, setting, and participants

This quality improvement study was performed at an 874-bed hospital and tertiary hernia referral center from September 2019 to January 2020. A prospective database was queried for patients with ventral hernias who underwent open AWR by experienced surgeons and had preoperative computed tomography images containing the entire hernia defect. An 8-layer convolutional neural network was generated to analyze image characteristics. Images were batched into training (approximately 80%) or test sets (approximately 20%) to analyze model output. Test sets were blinded from the convolutional neural network until training was completed. For the surgical complexity model, a separate validation set of computed tomography images was evaluated by a blinded panel of 6 expert AWR surgeons and the surgical complexity DLM. Analysis started February 2020.

Exposures

Image-based DLM.

Main outcomes and measures

The primary outcome was model performance as measured by area under the curve in the receiver operating curve (ROC) calculated for each model; accuracy with accompanying sensitivity and specificity were also calculated. Measures were DLM prediction of surgical complexity using need for component separation techniques as a surrogate and prediction of postoperative surgical site infection and pulmonary failure. The DLM for predicting surgical complexity was compared against the prediction of 6 expert AWR surgeons.

Results

A total of 369 patients and 9303 computed tomography images were used. The mean (SD) age of patients was 57.9 (12.6) years, 232 (62.9%) were female, and 323 (87.5%) were White. The surgical complexity DLM performed well (ROC = 0.744; P < .001) and, when compared with surgeon prediction on the validation set, performed better with an accuracy of 81.3% compared with 65.0% (P < .001). Surgical site infection was predicted successfully with an ROC of 0.898 (P < .001). However, the DLM for predicting pulmonary failure was less effective with an ROC of 0.545 (P = .03).

Conclusions and relevance

Image-based DLM using routine, preoperative computed tomography images was successful in predicting surgical complexity and more accurate than expert surgeon judgment. An additional DLM accurately predicted the development of surgical site infection.

SUBMITTER: Elhage SA

PROVIDER: S-EPMC8264757 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceConcern regarding surgical trainees' operative autonomy has increased in recent years, emphasizing patient safety and preparation for independent practice. Regarding abdominal wall reconstruction (AWR), long-term outcomes of fellow autonomy have yet to be delineated.ObjectivesTo evaluate the long-term outcomes of AWRs performed by fellows and compare them with those of AWRs performed by assistant, associate, and senior-level professors.Design, setting, and participantsThis retrospective cohort study included patients who underwent AWR for ventral hernias or repair of tumor resection defects at a 710-bed tertiary cancer center between March 1, 2005, and June 30, 2019. The analysis was conducted between January 2020 and December 2021.ExposureAcademic rank of primary surgeon.Main outcomes and measuresThe primary outcome was hernia recurrence. Secondary outcomes were surgical site occurrence, surgical site infection, length of hospital stay, unplanned return to the operating room, and 30-day readmission. Multivariable hierarchical models were constructed to identify predictive factors.ResultsOf 810 consecutive patients, 720 (mean [SD] age, 59.8 [11.5] years; 375 female [52.1%]) met the inclusion criteria. Mean (SD) body mass index was 31.4 (6.7), and mean (SD) follow-up time was 42 (29) months. Assistant professors performed the most AWRs (276 [38.3%]), followed by associate professors (169 [23.5%]), senior-level professors (157 [21.8%]), and microsurgical fellows (118 [16.4%]). Compared with fellows and more junior surgeons, senior-level professors tended to operate on significantly older patients (mean [SD] age, 59.9 [10.9] years; P = .03), more patients with obesity (103 [65.6%]; P = .003), and patients with larger defects (247.9 [216.0] cm; P < .001), parastomal hernias (27 [17.2%]; P = .001), or rectus muscle violation (53 [33.8%]; P = .03). No significant differences were found for hernia recurrence, surgical site occurrence, surgical site infection, 30-day readmission rates, or length of stay among the fellows and assistant, associate, and senior-level professors in adjusted models. Compared with fellows, assistant professors (OR, 0.22; 95% CI, 0.08-0.64) and senior-level professors (OR, 0.20; 95% CI, 0.06-0.69) had lower rates of unplanned return to the operating room.Conclusions and relevanceThis cohort study provides evidence-based reassurance that providing fellows with autonomy in performing AWRs does not compromise long-term patient outcomes. These findings may incite efforts to increase appropriate surgical trainee autonomy, thereby empowering future generations of competent, independent surgeons.

Project description:BackgroundTraditional reconstruction techniques have certain limitations in balancing image quality and reducing radiation dose. The deep learning image reconstruction (DLIR) algorithm opens the door to a new era of medical image reconstruction. The purpose of the study was to evaluate the DLIR images at 1.25 mm thickness in balancing image noise and spatial resolution in low-dose abdominal computed tomography (CT) in comparison with the conventional adaptive statistical iterative reconstruction-V at 40% strength (ASIR-V40%) at 5 and 1.25 mm.MethodsThis retrospective study included 89 patients who underwent low-dose abdominal CT. Five sets of images were generated using ASIR-V40% at a 5 mm slice thickness and 1.25 mm (high-resolution) with DLIR at 1.25 mm using 3 strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). Qualitative evaluation was performed for image noise, artifacts, and visualization of small structures, while quantitative evaluation was performed for standard deviation (SD), signal-to-noise ratio (SNR), and spatial resolution (defined as the edge rising slope).ResultsAt 1.25 mm, DLIR-M and DLIR-H images had significantly lower noise (SD in fat: 14.29±3.37 and 9.65±3.44 HU, respectively), higher SNR for liver (3.70±0.78 and 5.64±1.20, respectively), and higher overall image quality (4.30±0.44 and 4.67±0.40, respectively) than did the respective values in ASIR-V40% images (20.60±4.04 HU, 2.60±0.63, and 3.77±0.43; all P values <0.05). Compared with the 5 mm ASIR-V40% images, the 1.25 mm DLIR-H images had lower noise (SD: 9.65±3.44 vs. 13.63±10.03 HU), higher SNR (5.64±1.20 vs. 4.69±1.28), and higher overall image quality scores (4.67±0.40 vs. 3.94±0.46) (all P values <0.001). In addition, DLIR-L, DLIR-M, and DLIR-H images had a significantly higher spatial resolution in terms of edge rising slope (59.66±21.46, 58.52±17.48, and 59.26±13.33, respectively, vs. 33.79±9.23) and significantly higher image quality scores in the visualization of fine structures (4.43±0.50, 4.41±0.49, and 4.38±0.49, respectively vs. 2.62±0.49) than did the 5 mm ASIR-V40 images.ConclusionsThe 1.25 mm DLIR-M and DLIR-H images had significantly reduced image noise and improved SNR and overall image quality compared to the 1.25 mm ASIR-V40% images, and they had significantly improved the spatial resolution and visualization of fine structures compared to the 5 mm ASIR-V40% images. DLIR-H images had further reduced image noise compared with the 5 mm ASIR-V40% images, and DLIR-H was the most effective technique at balancing the image noise and spatial resolution in low-dose abdominal CT.