Preoperative Computed Tomography Morphological Features Indicative of Incisional Hernia Formation After Abdominal Surgery

Rectus Abdominis Muscle Atrophy and Asymmetry After Pulmonary Lobectomy

INTRODUCTION

Pulmonary lobectomy can result in intercostal nerve injury, leading to denervation of the rectus abdominis (RA) resulting in asymmetric muscle atrophy or an abdominal bulge. While there is a high rate of intercostal nerve injury during thoracic surgery, there are no studies that evaluate the magnitude and predisposing factors for RA atrophy in a large cohort.

METHODS

A retrospective chart review was conducted of 357 patients who underwent open, thoracoscopic or robotic pulmonary lobectomy at a single academic center. RA volumes were measured on computed tomography scans preoperatively and postoperatively on both the operated and nonoperated sides from the level of the xiphoid process to the thoracolumbar junction. RA volume change and association of surgical/demographic characteristics was assessed.

RESULTS

Median RA volume decreased bilaterally after operation, decreasing significantly more on the operated side (-19.5%) versus the nonoperated side (-6.6%) (P < 0.0001). 80.4% of the analyzed cohort experienced a 10% or greater decrease from preoperative RA volume on the operated side. Overweight individuals (body mass index 25.5-29.9) experienced a 1.7-fold greater volume loss on the operated side compared to normal weight individuals (body mass index 18.5-24.9) (P = 0.00016). In all right-sided lobectomies, lower lobe resection had the highest postoperative volume loss (Median (interquartile range): -28 (-35, -15)) (P = 0.082).

CONCLUSIONS

This study of postlobectomy RA asymmetry includes the largest cohort to date; previous literature only includes case reports. Lobectomy operations result in asymmetric RA atrophy and predisposing factors include demographics and surgical approach. Clinical and quality of life outcomes of RA atrophy, along with mitigation strategies, must be assessed.

Machine learning, deep learning and hernia surgery. Are we pushing the limits of abdominal core health? A qualitative systematic review

INTRODUCTION

This systematic review aims to evaluate the use of machine learning and artificial intelligence in hernia surgery.

METHODS

The PRISMA guidelines were followed throughout this systematic review. The ROBINS-I and Rob 2 tools were used to perform qualitative assessment of all studies included in this review. Recommendations were then summarized for the following pre-defined key items: protocol, research question, search strategy, study eligibility, data extraction, study design, risk of bias, publication bias, and statistical analysis.

RESULTS

A total of 13 articles were ultimately included for this review, describing the use of machine learning and deep learning for hernia surgery. All studies were published from 2020 to 2023. Articles varied regarding the population studied, type of machine learning or Deep Learning Model (DLM) used, and hernia type. Of the thirteen included studies, all included either inguinal, ventral, or incisional hernias. Four studies evaluated recognition of surgical steps during inguinal hernia repair videos. Two studies predicted outcomes using image-based DMLs. Seven studies developed and validated deep learning algorithms to predict outcomes and identify factors associated with postoperative complications.

CONCLUSION

The use of ML for abdominal wall reconstruction has been shown to be a promising tool for predicting outcomes and identifying factors that could lead to postoperative complications.

Optimal computed tomography-based biomarkers for prediction of incisional hernia formation

PURPOSE

Unstructured data are an untapped source for surgical prediction. Modern image analysis and machine learning (ML) can harness unstructured data in medical imaging. Incisional hernia (IH) is a pervasive surgical disease, well-suited for prediction using image analysis. Our objective was to identify optimal biomarkers (OBMs) from preoperative abdominopelvic computed tomography (CT) imaging which are most predictive of IH development.

METHODS

Two hundred and twelve rigorously matched colorectal surgery patients at our institution were included. Preoperative abdominopelvic CT scans were segmented to derive linear, volumetric, intensity-based, and textural features. These features were analyzed to find a small subset of OBMs, which are maximally predictive of IH. Three ML classifiers (Ensemble Boosting, Random Forest, SVM) trained on these OBMs were used for prediction of IH.

RESULTS

Altogether, 279 features were extracted from each CT scan. The most predictive OBMs found were: (1) abdominopelvic visceral adipose tissue (VAT) volume, normalized for height; (2) abdominopelvic skeletal muscle tissue volume, normalized for height; and (3) pelvic VAT volume to pelvic outer aspect of body wall skeletal musculature (OAM) volume ratio. Among ML prediction models, Ensemble Boosting produced the best performance with an AUC of 0.85, accuracy of 0.83, sensitivity of 0.86, and specificity of 0.81.

CONCLUSION

These OBMs suggest increased intra-abdominopelvic volume/pressure as the salient pathophysiologic driver and likely mechanism for IH formation. ML models using these OBMs are highly predictive for IH development. The next generation of surgical prediction will maximize the utility of unstructured data using advanced image analysis and ML.

GA-Net: A geographical attention neural network for the segmentation of body torso tissue composition

PURPOSE

Body composition analysis (BCA) of the body torso plays a vital role in the study of physical health and pathology and provides biomarkers that facilitate the diagnosis and treatment of many diseases, such as type 2 diabetes mellitus, cardiovascular disease, obstructive sleep apnea, and osteoarthritis. In this work, we propose a body composition tissue segmentation method that can automatically delineate those key tissues, including subcutaneous adipose tissue, skeleton, skeletal muscle tissue, and visceral adipose tissue, on positron emission tomography/computed tomography scans of the body torso.

METHODS

To provide appropriate and precise semantic and spatial information that is strongly related to body composition tissues for the deep neural network, first we introduce a new concept of the body area and integrate it into our proposed segmentation network called Geographical Attention Network (GA-Net). The body areas are defined following anatomical principles such that the whole body torso region is partitioned into three non-overlapping body areas. Each body composition tissue of interest is fully contained in exactly one specific minimal body area. Secondly, the proposed GA-Net has a novel dual-decoder schema that is composed of a tissue decoder and an area decoder. The tissue decoder segments the body composition tissues, while the area decoder segments the body areas as an auxiliary task. The features of body areas and body composition tissues are fused through a soft attention mechanism to gain geographical attention relevant to the body tissues. Thirdly, we propose a body composition tissue annotation approach that takes the body area labels as the region of interest, which significantly improves the reproducibility, precision, and efficiency of delineating body composition tissues.

RESULTS

Our evaluations on 50 low-dose unenhanced CT images indicate that GA-Net outperforms other architectures statistically significantly based on the Dice metric. GA-Net also shows improvements for the 95% Hausdorff Distance metric in most comparisons. Notably, GA-Net exhibits more sensitivity to subtle boundary information and produces more reliable and robust predictions for such structures, which are the most challenging parts to manually mend in practice, with potentially significant time-savings in the post hoc correction of these subtle boundary placement errors. Due to the prior knowledge provided from body areas, GA-Net achieves competitive performance with less training data. Our extension of the dual-decoder schema to TransUNet and 3D U-Net demonstrates that the new schema significantly improves the performance of these classical neural networks as well. Heatmaps obtained from attention gate layers further illustrate the geographical guidance function of body areas for identifying body tissues.

CONCLUSIONS

(i) Prior anatomic knowledge supplied in the form of appropriately designed anatomic container objects significantly improves the segmentation of bodily tissues. (ii) Of particular note are the improvements achieved in the delineation of subtle boundary features which otherwise would take much effort for manual correction. (iii) The method can be easily extended to existing networks to improve their accuracy for this application.

Incisional Hernia: A Surgical Complication or Medical Disease?

Incisional hernia (IH) is a frequent complication following abdominal surgery. The development of IH could be more sophisticated than a simple anatomical failure of the abdominal wall. Reported IH incidence varies among studies. This review presented an overview of definitions, molecular basis, risk factors, incidence, clinical presentation, surgical techniques, postoperative care, cost, risk prediction tools, and proposed preventative measures. A literature search of PubMed was conducted to include high-quality studies on IH. The incidence of IH depends on the primary surgical pathology, incision site and extent, associated medical comorbidities, and risk factors. The review highlighted inherent and modifiable risk factors. The disorganisation of the extracellular matrix, defective fibroblast functions, and ratio variations of different collagen types are implicated in molecular mechanisms. Elective repair of IH alleviates symptoms, prevents complications, and improves the quality of life (QOL). Recent studies introduced risk prediction tools to implement preventative measures, including suture line reinforcement or prophylactic mesh application in high-risk groups. Elective repair improves QOL and prevents sinister outcomes associated with emergency IH repair. The watchful wait strategy should be reviewed, and options should be discussed thoroughly during patients' counselling. Risk stratification tools for predicting IH would help adopt prophylactic measures.

Incidence, risk factors, and burden of incisional hernia repair after abdominal surgery in France: a nationwide study

PURPOSE

Incisional hernias are common after laparotomies. The aims of this study were to assess the rate of incisional hernia repair after abdominal surgery, recurrence rate, hospital costs, and risk factors, in France.

METHODS

This national, retrospective, longitudinal, observational study was based on the exhaustive hospital discharge database (PMSI). All adult patients (≥ 18 years old) hospitalised for an abdominal surgical procedure between 01-01-2013 and 31-12-2014 and hospitalised for incisional hernia repair within five years were included. Descriptive analyses and cost analyses from the National Health Insurance (NHI) viewpoint (hospital care for the hernia repair) were performed. To identify risk factors for hernia repair a multivariable Cox model and a machine learning analysis were performed.

RESULTS

In 2013-2014, 710074 patients underwent abdominal surgery, of which 32633 (4.6%) and 5117 (0.7%) had ≥ 1 and ≥ 2 incisional hernia repair(s) within five years, respectively. Mean hospital costs amounted to €4153/hernia repair, representing nearly €67.7 million/year. Some surgical sites exposed patients at high risk of incisional hernia repair: colon and rectum (hazard ratio [HR] 1.2), and other sites on the small bowel and the peritoneum (HR 1.4). Laparotomy procedure and being ≥ 40 years old put patients at high risk of incisional hernia repair even when operated on low-risk sites such as stomach, duodenum, and hepatobiliary.

CONCLUSION

The burden of incisional hernia repair is high and most patients are at risk either due to age ≥ 40 or the surgery site. New approaches to prevent the onset of incisional hernia are warranted.