The role of artificial intelligence in abdominal wall surgery: recent progress and embracing uncertainty

Abstract

Artificial intelligence (AI) is profoundly impacting most, if not all, scientific and medical disciplines. In abdominal wall surgery (AWS), which includes common procedures such as hernia repair, abdominal wall reconstruction, and separation, AI models trained on surgical data have immense potential to enhance clinical practice and patient outcomes. The benefits include better procedure planning, standardization, interventional guidance, awareness of critical structures, complication prevention, quality assurance, and patient monitoring. Moreover, AI may significantly transform surgical education by enhancing training, skill assessment, and feedback mechanisms, leading to better-prepared surgeons. This review article highlights the latest developments in AI and AWS, focusing on key emerging applications and why embracing AI model prediction uncertainty is essential to translating these research efforts to clinical practice.

Keywords

Artificial intelligence / surgery / hernia / computer-assisted surgery / machine learning

References

[1] HerniaSurge Group. International guidelines for groin hernia management.Hernia2018;22:1-165 PMCID:PMC5809582

[2] Allied Market Research. Hernia repair devices and consumables market size, share, competitive landscape and trend analysis report, by product, surgery type and hernia type : global opportunity analysis and industry forecast, 2020-2027. Available from: https://www.alliedmarketresearch.com/hernia-repair-devices-market. [Last accessed on 17 Apr 2025]

[3] Wang F,Ma Q.Global, regional, and national burden of inguinal, femoral, and abdominal hernias: a systematic analysis of prevalence, incidence, deaths, and DALYs with projections to 2030.Int J Surg2024;110:1951-67 PMCID:PMC11020045

[4] Smith JM,Mericli AF,Butler CE.Parastomal hernia repair.Plast Aesthet Res2022;9:10

[5] Köckerling F,Berrevoet F.The reality of general surgery training and increased complexity of abdominal wall hernia surgery.Hernia2019;23:1081-91 PMCID:PMC6938469

[6] Tuma F,Varacallo MA. Anatomy, abdomen and pelvis: inguinal region (inguinal canal). Available from: http://www.ncbi.nlm.nih.gov/books/NBK470204/. [Last accessed on 17 Apr 2025]

[7] Roos MM,Schouten N.Higher recurrence rate after endoscopic totally extraperitoneal (TEP) inguinal hernia repair with ultrapro lightweight mesh: 5-year results of a randomized controlled trial (TULP-trial).Ann Surg2018;268:241-6

[8] Wu F,Liu Y,Yu Y.Lightweight mesh versus heavyweight mesh for laparo-endoscopic inguinal hernia repair: a systematic review and meta-analysis.Hernia2020;24:31-9

[9] Bakker WJ,Boschman JS.Heavyweight mesh is superior to lightweight mesh in laparo-endoscopic inguinal hernia repair: a meta-analysis and trial sequential analysis of randomized controlled trials.Ann Surg2021;273:890-9

[10] Levy AS,Celie KB.Quantifying fascial tension in ventral hernia repair and component separation.Hernia2021;25:107-14

[11] Dietz UA,Gokcal F.Excess body weight and abdominal hernia.Visc Med2021;37:246-53 PMCID:PMC8406351

[12] de Beaux A,Parent T.Hernia Basecamp - a free to use, online hernia learning platform. Analysis of its use since launch in June 2021.J Abdom Wall Surg2023;2:11803 PMCID:PMC10831634

[13] Xu Y,Zhou X,Cui W.Electrospun fiber-based immune engineering in regenerative medicine.Smart Med2024;3:e20230034 PMCID:PMC11235953

[14] Murphy BL,Zhang J,Farley DR.Trends of inguinal hernia repairs performed for recurrence in the United States.Surgery2018;163:343-50

[15] Palser TR,Williams RN,Beckingham IJ.Variation in outcomes and use of laparoscopy in elective inguinal hernia repair.BJS Open2019;3:466-75 PMCID:PMC6677107

[16] Takeuchi M,Lipps C.Towards automatic verification of the critical view of the myopectineal orifice with artificial intelligence.Surg Endosc2023;37:4525-34

[17] Takeuchi M,Ndagijimana A.Automatic surgical phase recognition in laparoscopic inguinal hernia repair with artificial intelligence.Hernia2022;26:1669-78

[18] LeCun Y,Hinton G.Deep learning.Nature2015;521:436-44

[19] Chan H,Hadjiiski LM.Deep learning in medical image analysis. In: Lee G, Fujita H, editors. Deep learning in medical image analysis. Cham: Springer International Publishing; 2020. pp. 3-21. PMCID:PMC7442218

[20] De Coster M,Van Herreweghe M.Machine translation from signed to spoken languages: state of the art and challenges.Univ Access Inf Soc2024;23:1305-31

[21] Cao H,Gao Z.A survey on generative diffusion models.IEEE Trans Knowl Data Eng2024;36:2814-30

[22] Bengesi S,Sarker MK,Irungu J.Advancements in generative AI: a comprehensive review of GANs, GPT, autoencoders, diffusion model, and transformers.IEEE Access2024;12:69812-37

[23] Liu C.AI-empowered persuasive video generation: a survey.ACM Comput Surv2023;55:1-31

[24] Ning Y,Wu Z,Zhang LJ.A review of deep learning based speech synthesis.Appl Sci2019;9:4050

[25] ChatGPT. Available: https://chatgpt.com. [Last accessed on 17 Apr 2025]

[26] Isensee F,Kohl SAA,Maier-Hein KH.nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.Nat Methods2021;18:203-11

[27] Abadi M,Barham P. TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv 2016, arXiv:1603.04467. Available from: https://doi.org/10.48550/arXiv.1603.04467. [Last accessed on 17 Apr 2025]

[28] Paszke A,Chintala S. Automatic differentiation in PyTorch. 2017. Available from: https://www.semanticscholar.org/paper/Automatic-differentiation-in-PyTorch-Paszke-Gross/b36a5bb1707bb9c70025294b3a310138aae8327a. [Last accessed on 17 Apr 2025]

[29] Krishnan R,Topol EJ.Self-supervised learning in medicine and healthcare.Nat Biomed Eng2022;6:1346-52

[30] Muehlematter UJ,Vokinger KN.Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015-20): a comparative analysis.Lancet Digit Health2021;3:e195-203

[31] Bohr A. Artificial intelligence in healthcare. Academic Press, 2020. Available from: https://shop.elsevier.com/books/artificial-intelligence-in-healthcare/bohr/978-0-12-818438-7. [Last accessed on 17 Apr 2025]

[32] Panesar A.Machine learning and AI for healthcare: big data for improved health outcomes. Berkeley, CA: Apress, 2021.

[33] Claus CMP,Malcher F.DECOMP Report: answers surgeons expect from an abdominal wall imaging exam.Rev Col Bras Cir2022;49:e20223172 PMCID:PMC10578831

[34] Soler L,Marescaux J.Patient-specific anatomy: the new area of anatomy based on 3D modelling. In: Uhl J, Jorge J, Lopes DS, Campos PF, editors. Digital anatomy. Cham: Springer International Publishing; 2021. pp. 285-97.

[35] Liu X,Liu S.A review of deep-learning-based medical image segmentation methods.Sustainability2021;13:1224

[36] Wasserthal J,Meyer MT.TotalSegmentator: robust segmentation of 104 anatomic structures in CT images.Radiol Artif Intell2023;5:e230024 PMCID:PMC10546353

[37] Zhang Q,He K.A new technique for the 3D reconstruction of the incisional hernia: a pilot study.Clin Imaging2020;67:91-4

[38] Yao S,Liu FD.Significance of measurements of herniary area and volume and abdominal cavity volume in the treatment of incisional hernia: application of CT 3D reconstruction in 17 cases.Comput Aided Surg2012;17:40-5

[39] Elhage SA,Ayuso SA.Development and validation of image-based deep learning models to predict surgical complexity and complications in abdominal wall reconstruction.JAMA Surg2021;156:933-40 PMCID:PMC8264757

[40] Ayuso SA,Zhang Y.Predicting rare outcomes in abdominal wall reconstruction using image-based deep learning models.Surgery2023;173:748-55

[41] Kao AM,Augenstein VA.Prevention and treatment strategies for mesh infection in abdominal wall reconstruction.Plast Reconstr Surg2018;142:149S-55S

[42] Claus C,Malcher F,Felix E.Ten golden rules for a safe MIS inguinal hernia repair using a new anatomical concept as a guide.Surg Endosc2020;34:1458-64

[43] Lin C,Zhao Y,He K.SGT++: improved scene graph-guided transformer for surgical report generation.IEEE Trans Med Imaging2024;43:1337-46

[44] Nagaya T,Choyke PL.Fluorescence-guided surgery.Front Oncol2017;7:314

[45] Diana M.Enabling precision digestive surgery with fluorescence imaging.Transl Gastroenterol Hepatol2017;2:97 PMCID:PMC5723751

[46] Barberio M,Pizzicannella M.Intraoperative guidance using hyperspectral imaging: a review for surgeons.Diagnostics2021;11:2066 PMCID:PMC8624094

[47] Yoon J.Hyperspectral imaging for clinical applications.BioChip J2022;16:1-12

[48] Aasvang EK.The future of postoperative vital sign monitoring in general wards: improving patient safety through continuous artificial intelligence-enabled alert formation and reduction.Curr Opin Anaesthesiol2023;36:683-90

[49] Tanner J,Harris R.Digital wound monitoring with artificial intelligence to prioritise surgical wounds in cardiac surgery patients for priority or standard review: protocol for a randomised feasibility trial (WISDOM).BMJ Open2024;14:e086486 PMCID:PMC11409336

[50] Le DTP.Unveiling the role of artificial intelligence for wound assessment and wound healing prediction.Explor Med2023;4:589-611

[51] Ganesan O,Guo L.A review of artificial intelligence in wound care.Art Int Surg2024;4:364-75

[52] Jamadar DA,Girish G.Abdominal wall hernia mesh repair: sonography of mesh and common complications.J Ultrasound Med2008;27:907-17

[53] Lacour M,Casa C.CT findings of complications after abdominal wall repair with prosthetic mesh.Diagn Interv Imaging2017;98:517-28

[54] Pinto-Coelho L.How artificial intelligence is shaping medical imaging technology: a survey of innovations and applications.Bioengineering2023;10:1435 PMCID:PMC10740686

[55] Sajdeya R.Harnessing artificial intelligence for predicting and managing postoperative pain: a narrative literature review.Curr Opin Anaesthesiol2024;37:604-15

[56] van de Sande D,Verhoef C.Optimizing discharge after major surgery using an artificial intelligence-based decision support tool (DESIRE): an external validation study.Surgery2022;172:663-9

[57] Geoghegan L,Wormald JCR.Automated conversational agents for post-intervention follow-up: a systematic review.BJS Open2021;5:zrab070 PMCID:PMC8320342

[58] Park JJ,Demetriades AK.The role of artificial intelligence in surgical simulation.Front Med Technol2022;4:1076755 PMCID:PMC9794840

[59] Bencteux V,Shlomovitz E.Automatic task recognition in a flexible endoscopy benchtop trainer with semi-supervised learning.Int J Comput Assist Radiol Surg2020;15:1585-95

[60] Eckhoff JA,Altieri MS.SAGES consensus recommendations on surgical video data use, structure, and exploration (for research in artificial intelligence, clinical quality improvement, and surgical education).Surg Endosc2023;37:8690-707 PMCID:PMC10616217

[61] Mutter D,Dallemagne B,Leroy J.WeBSurg: an innovative educational Web site in minimally invasive surgery - principles and results.Surg Innov2011;18:8-14

[62] Seenivasan L,Krishna AK. Surgical-VQA: visual question answering in surgical scenes using transformer. arXiv 2022, arXiv:2206.11053. Available from: https://doi.org/10.48550/arXiv.2206.11053. [Last accessed on 17 Apr 2025]

[63] Browne R,Hurley CM,O’Sullivan JB.ChatGPT-4 can help hand surgeons communicate better with patients.J Hand Surg Glob Online2024;6:436-8 PMCID:PMC11133925

[64] Ruksakulpiwat S,Ajibade A.Using ChatGPT in medical research: current status and future directions.J Multidiscip Healthc2023;16:1513-20 PMCID:PMC10239248

[65] Lai H,Sun M.Assessing the risk of bias in randomized clinical trials with large language models.JAMA Netw Open2024;7:e2412687 PMCID:PMC11112444

[66] Kirova VD,Laracy JR.Software engineering education must adapt and evolve for an LLM environment. In: Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1, New York, USA. 2024. Association for Computing Machinery; 2024. pp. 666-72.

[67] Steyerberg EW.Prediction models need appropriate internal, internal-external, and external validation.J Clin Epidemiol2016;69:245-7 PMCID:PMC5578404

[68] Daes J.Critical view of the myopectineal orifice.Ann Surg2017;266:e1-2

[69] Barberio M,Bencteux V.Deep learning analysis of in vivo hyperspectral images for automated intraoperative nerve detection.Diagnostics2021;11:1508 PMCID:PMC8391550

[70] Wang C. Calibration in deep learning: a survey of the state-of-the-art. arXiv 2023, arXiv:2308.01222. Available from: https://doi.org/10.48550/arXiv.2308.01222. [Last accessed on 17 Apr 2025]

[71] Borys K,Nauta M.Explainable AI in medical imaging: an overview for clinical practitioners - Saliency-based XAI approaches.Eur J Radiol2023;162:110787

[72] Alberdi E,Strigini L.Effects of incorrect computer-aided detection (CAD) output on human decision-making in mammography.Acad Radiol2004;11:909-18