Auditorium of the future: e learning platform

Principles of surgical training have not changed, but methods of training are evolving very fast. Online tools are being adopted in both knowledge and skills training for surgical residents. As a result, to evaluate the outcome of these tools, online assessment is also developing. Knowledge resources are very diverse ranging from lectures, webinars, surgical videos to three-dimensional planning and printing. Skills resources include virtual reality simulators, remote skills training and interdisciplinary teamwork. Assessment of E-learning tools can be performed using online questions, task-based simulations, branching scenarios and online interviews/discussions. In thoracic surgery, video assisted thoracic surgery (VATS) lobectomy simulator has been developed and it appears to be an important tool for minimally invasive thoracic surgery education. Training programs incorporate e-Learning in their curriculum and online training and assessment will become an important part of thoracic surgical training as well.     

Artificial intelligence in gastric cancer: Application and future perspectives

Gastric cancer is the fourth leading cause of cancer-related mortality across the globe, with a 5-year survival rate of less than 40%. In recent years, several applications of artificial intelligence(AI) have emerged in the gastric cancer field based on its efficient computational power and learning capacities, such as imagebased diagnosis and prognosis prediction. AI-assisted diagnosis includes pathology, endoscopy, and computerized tomography, while researchers in the prognosis circle focus on recurrence, metastasis, and survival prediction. In this review, a comprehensive literature search was performed on articles published up to April 2020 from the databases of Pub Med, Embase, Web of Science, and the Cochrane Library. Thereby the current status of AI-applications was systematically summarized in gastric cancer. Moreover, future directions that target this field were also analyzed to overcome the risk of overfitting AI models and enhance their accuracy as well as the applicability in clinical practice.     

Current methods of staging and restaging of the mediastinal nodes in non-small-cell lung cancer

To analyze the current methods of primary staging and repeated staging (restaging) of the mediastinal nodes in non-small-cell lung cancer (NSCLC), all methods currently used for staging of NSCLC are analyzed. These methods include imaging techniques [computer tomography (CT), positron emission tomography (PET) combined with CT (PET/CT)], endoscopic/ultrasound techniques (endobronchial ultrasound/transbronchial needle aspiration) and endoscopic ultrasound/fine needle aspiration and surgical techniques [standard cervical mediastinoscopy, video-assisted mediastinoscopy, extended mediastinoscopy, video-assisted mediastinoscopic lymphadenectomy, transcervical extended mediastinal lymphadenectomy, anterior mediastinotomy (Chamberlain procedure) and video-assisted thoracic surgery]. The diagnostic yield of Chest CT is regarded insufficient for both, primary staging and restaging. The PET/CT became a standard imaging technique preceding curative surgery of radical chemo-radiotherapy. The issue of intraoperative staging is also described. Finally, the author’s proposed algorithm of staging, both for primary staging and restaging after neoadjuvant therapy is presented. Detailed staging of NSCLC enables selection of patients with early stage disease for curative surgical/multimodality treatment and helps to avoid unnecessary surgery in advanced disease.     

A systematic review and meta-analysis of diagnostic performance and physicians’ perceptions of artificial intelligence (AI)-assisted CT diagnostic technology for the classification of pulmonary nodules

BackgroundLung cancer was the second most commonly diagnosed cancer and the leading cause of cancer death in 2020. Although artificial intelligence (AI)-assisted diagnostic technologies have shown promise and has been used in clinical practice in recent years, no products related to AI-assisted CT diagnostic technologies for the classification of pulmonary nodules have been approved by the National Medical Products Administration in China. The objective of this article was to systematically review the diagnostic performance of AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant and to analyze physicians’ perceptions of this technology in China.MethodsAll relevant studies from 6 literature databases were searched and screened according to the inclusion and exclusion criteria. Data were extracted and the study quality was assessed by two reviewers. The study heterogeneity and publication bias were estimated. A questionnaire survey on the perceptions of physicians was conducted in 9 public tertiary hospitals in China. A meta-analysis, meta-regression and univariate logistic model were used in the systematic review and to explore the association of physicians’ perceptions with their rate of support for the clinical application of the technology.ResultsTwenty-seven studies with 5,727 pulmonary nodules were finally included in the meta-analysis. We found that the quality of the included studies was generally acceptable and that the pooled sensitivity and specificity of AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant were 0.90 and 0.89, respectively. The pooled diagnostic odds ratio (DOR) was 70.33. The majority of the surveyed physicians in China perceived “reduced workload for radiologists” and “improved diagnostic efficiency” as the important benefits of this technology. In addition, diagnostic accuracy (including misdiagnosis) and practical experience were significantly associated with whether physicians supported its clinical application.ConclusionsIn the context of lung cancer diagnosis, AI-assisted CT diagnostic technology for the classification of pulmonary nodules as benign or malignant has good diagnostic performance, but its specificity needs to be improved.     

Developing a virtual reality simulation system for preoperative planning of thoracoscopic thoracic surgery

BackgroundVideo-assisted thoracoscopic surgery (VATS) has become a standard approach for the treatment of lung cancer. However, its minimally invasive nature limits the field of view and reduces tactile feedback. These limitations make it vital that surgeons thoroughly familiarize themselves with the patient’s anatomy preoperatively. We have developed a virtual reality (VR) surgical navigation system using head-mounted displays (HMD). The aim of this study was to investigate the potential utility of this VR simulation system in both preoperative planning and intraoperative assistance, including support during thoracoscopic sublobar resection.MethodsThree-dimensional (3D) polygon data derived from preoperative computed tomography data was loaded into BananaVision software developed at Colorado State University and displayed on an HMD. An interactive 3D reconstruction image was created, in which all the pulmonary structures could be individually imaged. Preoperative resection simulations were performed with patient-individualized reconstructed 3D images.ResultsThe 3D anatomic structure of pulmonary vessels and a clear vision into the space between the lesion and adjacent tissues were successfully appreciated during preoperative simulation. Surgeons could easily evaluate the real patient’s anatomy in preoperative simulations to improve the accuracy and safety of actual surgery. The VR software and HMD allowed surgeons to visualize and interact with real patient data in true 3D providing a unique perspective.ConclusionsThis initial experience suggests that a VR simulation with HMD facilitated preoperative simulation. Routine imaging modalities combined with VR systems could substantially improve preoperative planning and contribute to the safety and accuracy of anatomic resection.     

Cervical thoracic duct cyst

Thoracic duct cysts are rare lesions presenting as mediastinal or supraclavicular masses. We report a case of a 77-year-old female who presented with a left supraclavicular mass. A cervical thoracic duct cyst was suspected after contrast-enhanced computed tomography (CT) of the neck and chest. Diagnosis was confirmed by ultrasound-guided cyst aspiration and lymphangiography. Therapeutic embolization of the thoracic duct was unsuccessful. Definitive treatment was achieved with thoracic duct ligation using video-assisted thoracoscopic surgery (VATS) followed by surgical excision of the cyst. This is believed to be the first report of using minimally invasive surgery for thoracic duct ligation in the treatment of a thoracic duct cyst.     

Video-assisted thoracoscopic surgery as a first-line treatment for mediastinal parathyroid adenomas: strategic value of imaging

OBJECTIVE: To present first-line thoracic surgery made possible by localization studies in three patients with ectopic parathyroid adenomas. DESIGN AND METHODS: Three patients with ectopic parathyroid tissue in the mediastinum were examined by ultrasound, technetium-99m sestamibi scintigraphy, computed tomography (CT), and venous catheterization with measurement of parathyroid hormone. Without previous cervical exploration, video-assisted thoracic surgery (VATS) was used in all cases to avoid the need for thoracic open surgical procedures. RESULTS AND CONCLUSIONS: The mediastinal parathyroid glands were all detected at scintigraphy, and CT and venous catheterization were helpful in anatomic and functioning characterization. All pathologic glands were successfully resected, with only one minor complication. VATS can safely remove a deep mediastinal parathyroid adenoma and avoid more aggressive open approaches. In an experienced referral center, systematic and sophisticated imaging studies may accurately identify and localize rare ectopic parathyroid adenomas, and avoid cervical surgery.     

Artificial intelligence in thoracic surgery: a narrative review

ObjectiveThe aim of this article is to review the current applications of artificial intelligence in thoracic surgery, from diagnosis and pulmonary disease management, to preoperative risk-assessment, surgical planning, and outcomes prediction.BackgroundArtificial intelligence implementation in healthcare settings is rapidly growing, though its widespread use in clinical practice is still limited. The employment of machine learning algorithms in thoracic surgery is wide-ranging, including all steps of the clinical pathway.MethodsWe performed a narrative review of the literature on Scopus, PubMed and Cochrane databases, including all the relevant studies published in the last ten years, until March 2021.ConclusionMachine learning methods are promising encouraging results throughout the key issues of thoracic surgery, both clinical, organizational, and educational. Artificial intelligence-based technologies showed remarkable efficacy to improve the perioperative evaluation of the patient, to assist the decision-making process, to enhance the surgical performance, and to optimize the operating room scheduling. Still, some concern remains about data supply, protection, and transparency, thus further studies and specific consensus guidelines are needed to validate these technologies for daily common practice.KeywordsArtificial intelligence (AI); thoracic surgery; machine learning; lung resection; perioperative medicine     

Virtual angioscopy assessment for acute type B aortic dissection endovascular repair

Introduction : Virtual angioscopy 3D reconstruction (VA) based on Multidetector computed tomography (m‐CT) can be an important tool in endovascular aortic repair assessment. Here, we present a case of an acute type B aortic dissection, evaluated with preoperative virtual angioscopy 3D reconstruction (VA). Case Report : A 60 years‐old‐man presented with type B acute aortic dissection. Due to renal malperfusion and uncontrolled hypertension TEVAR and renal stenting was performed based on m‐CT and VA images. Discussion : Aortic dissection endovascular repair requires an accurate evaluation based on M‐CT or magnetic resonance angiography (MRA). VA is a CT‐based 3D reconstruction that provides a sort of information comparable to intravascular ultrasound (IVUS) that can be very helpful when it is not available and has many other potential applications in vascular surgery. © 2009 Wiley‐Liss, Inc.     

Genome-wide microsatellite analysis of focal nodular hyperplasia: a strong tool for the differential diagnosis of non-neoplastic liver nodule from hepatocellular carcinoma

Allelic imbalance (AI), which represents certain chromosomal gains or losses, has been described in hepatocellular carcinoma (HCC), but the significance of AI analysis in focal nodular hyperplasia (FNH) has not been fully clarified. We hypothesized, therefore, that comprehensive allelotyping of FNH could be a useful tool for differentiating FNH from HCC. A 27‐year‐old man was admitted to the hospital because of general fatigue. A computed tomography (CT) scan disclosed a hepatic nodule 8cm in diameter. No definite diagnosis was made after imaging or by biopsy before surgery. Macroscopically and microscopically, the surgical specimen showed typical features of FNH. Comprehensive microsatellite analysis was carried out with 382 microsatellite markers distributed throughout all chromosomes. To detect AI effectively, the cutoff value of the AI index was set at 0.70. Among the 382 microsatellite markers, 212 loci were informative, but no AI was detected. The absence of gross chromosomal alterations strongly suggested that the large nodule was FNH rather than HCC, in terms of its genetic background. The patient's subsequent clinical course revealed the nodule to be benign. The results suggest that this genome‐wide microsatellite analysis is a useful tool for the differential diagnosis of non‐neoplastic liver nodules from HCC.     

Thoracic aortic aneurysm and rupture in giant cell arteritis. a descriptive study of 41 cases

Objective. To determine the features and outcomes of patients with giant cell arteritis (GCA) who have aneurysms or rupture of the thoracic aorta. Methods. Patients with GCA seen over a 40-year period who had aneurysms and/or rupture of the thoracic aorta were identified by assistance of a computerized indexing system. The presence of thoracic aortic aneurysms (TAA), with or without aortic valve insufficiency (AI), was determined by radiographs, computed tomography scans, and ultrasound studies of the thorax, angiograms of the aorta, and postmortem examination. Results. Ten men and 31 women with GCA were found to have TAA and/or rupture. Three developed TAA before GCA was diagnosed, 5 developed aortic findings near the time of the diagnosis, and 33 after the diagnosis of GCA (median of 7 years after diagnosis). Sixteen patients developed acute aortic dissection, which caused death in 8. Nineteen patients also had AI due to aortic root dilation, 15 of whom developed congestive heart failure. Eighteen patients underwent 21 surgical procedures for TAA resection and/or aortic valve replacement or repair. Aortitis was documented histologically in 10 cases. Conclusion. Thoracic aortic complications in GCA are associated with serious outcomes that have been underrecognized and may be fatal. Physicians should be alert to the development of these complications at any time in the course of GCA, even many years after usual symptoms have subsided.     

Precise and fast video assisted thoracoscopic bronchial sleeve resection

Surgical management for lung cancer is basically a destructive one. The lung parenchyma removed is in the balance between the purpose of curative resection and the preservation of patient’s lung function. Bronchial sleeve has been alternatively developed to achieve the same purpose, but through a different way—to save back healthy lung tissue through reconstruction of the central airway. Sleeve resection had been done with open technique for years, and just like the other thoracic operations, has continuously evolved into the era of minimally invasive surgery in spite of its difficulty. With rapid advancement and availability in technology—high resolution 3-D dynamic chest computed tomography (CT), PET-CT, and endobronchial ultrasound (EBUS), these tools are very helpful for us to have more precise tumor staging, and suitable for preoperative surgical planning. Under magnified 3-D endoscopic view and modified endoscopic suturing method, re-anastomosis of the airway could be easier and quicker, which would facilitate this innovative operation to accumulate experience in the not too distant future.     

Artificial intelligence-assisted endoscopic detection of esophageal neoplasia in early stage: The next step?

Esophageal cancer (EC) is a common malignant tumor of the digestive tract and originates from the epithelium of the esophageal mucosa. It has been confirmed that early EC lesions can be cured by endoscopic therapy, and the curative effect is equivalent to that of surgical operation. Upper gastrointestinal endoscopy is still the gold standard for EC diagnosis. The accuracy of endoscopic examination results largely depends on the professional level of the examiner. Artificial intelligence (AI) has been applied in the screening of early EC and has shown advantages; notably, it is more accurate than less-experienced endoscopists. This paper reviews the application of AI in the field of endoscopic detection of early EC, including squamous cell carcinoma and adenocarcinoma, and describes the relevant progress. Although up to now most of the studies evaluating the clinical application of AI in early EC endoscopic detection are focused on still images, AI-assisted real-time detection based on live-stream video may be the next step.     

Thoracic surgery in Taiwan

Taiwanese surgeons have pioneered major advances in the field of minimally invasive thoracic surgery. Since the establishment of the Taiwan Association of Thoracic and Cardiovascular Surgery [1986], the landscape of thoracic surgery has rapidly evolved from traditional thoracotomy to multi-port video-assisted thoracoscopic approaches. By early 21st century, further developments have included the single-port and subxiphoid techniques. This paper provides an overview of the Taiwanese thoracic surgery environment and its major accomplishments. With the increasing use of low-dose computed tomography for lung cancer screening, the detection of small pulmonary nodules has been growing steadily. High-end hybrid operating rooms comprising both imaging and surgical equipment are increasingly being applied in Taiwan as platforms for image-guided video-assisted thoracoscopic surgery (iVATS). Recently, we described an iVATS workflow for simultaneous detection and removal of small pulmonary nodules which was entirely performed by thoracic surgeons. With respect to esophageal malignancies, the implementation of robot-assisted esophagectomy has been a significant milestone in Taiwan. This technique allowed conducting an extensive lymph node dissection along the bilateral recurrent laryngeal nerve in a safe and effective manner. With 14 medical schools and 26 medical centers located on the island, Taiwan has been able to maintain a constant doctor-to-population ratio of 1-to-500. By partnering with the National Health Insurance and by taking advantage of state-of-the-art technologies, Taiwanese thoracic surgeons are continuously striving to deliver high-quality and cost-effective surgical care.     

Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology

ObjectiveThis review will focus on how AI—and, specifically, deep learning—can be applied to complement aspects of the current healthcare system. We describe how AI-based tools can augment existing clinical workflows by discussing the applications of AI to worklist prioritization and patient triage, the performance-boosting effects of AI as a second reader, and the use of AI to facilitate complex quantifications. We also introduce prominent examples of recent AI applications, such as tuberculosis screening in resource-constrained environments, the detection of lung cancer with screening CT, and the diagnosis of COVID-19. We also provide examples of prognostic predictions and new discoveries beyond existing clinical practices.BackgroundArtificial intelligence (AI) has shown promising performance for thoracic diseases, particularly in the field of thoracic radiology. However, it has not yet been established how AI-based image analysis systems can help physicians in clinical practice.MethodsThis review included peer-reviewed research articles on AI in the thorax published in English between 2015 and 2021.ConclusionsWith advances in technology and appropriate preparation of physicians, AI could address various clinical problems that have not been solved due to a lack of clinical resources or technological limitations.KeywordsArtificial intelligence (AI); deep learning (DL); computer aided diagnosis (CAD); thoracic radiology; pulmonary medicine     

Aiming at One-Stage Corrective Surgery for Extended Thoracic Aortic Dilatation

Definitive treatment of extended thoracic aortic dilatation is a major surgical challenge. Histopathology of resected thoracic aortic wall may reveal undiagnosed aortitis affecting outcome. We sought to investigate the benefit of thorough histopathology after one-stage corrective surgery for the treatment of extended thoracic aortic dilatation. Five patients underwent one-stage corrective surgery using the hybrid open arch repair by the frozen elephant trunk together with endovascular aortic grafting. A representative sample of the resected aortic arch was procured for histology. T- and B-lymphocytes, plasma cells, macrophages, and immunoglobulin G4 (IgG4) positivity were evaluated by immunohistochemistry. The mean preoperative maximum aortic diameter was 54 mm (range, 41–79 mm). The mean follow-up was 18 months (range, 1–24 months). As confirmed by computed tomography (CT) upon follow-up, complete thrombosis of the false lumen at the level of the frozen elephant trunk was achieved in all patients with dissection. One patient was operated due to atherosclerotic dilatation of the thoracic aorta, and postoperative CT showed successful exclusion of the atherosclerotic dilatation; this 75-year-old man was diagnosed with IgG4-positive aortitis and experienced unexpected blindness after surgery without evidence of emboli or long-term neurological impairment upon repeated brain CT. The hybrid open arch repair by the frozen elephant trunk and simultaneous endovascular repair is a feasible choice for one-stage surgery through sternotomy aiming at definitive treatment of extended thoracic aortic pathology. However, systematic evaluation of inflammation may reveal concealed aortitis affecting postoperative outcome and need for long-term surveillance.     

Artificial intelligence in perioperative management of major gastrointestinal surgeries

Artificial intelligence (AI) demonstrated by machines is based on reinforcement learning and revolves around the usage of algorithms. The purpose of this review was to summarize concepts, the scope, applications, and limitations in major gastrointestinal surgery. This is a narrative review of the available literature on the key capabilities of AI to help anesthesiologists, surgeons, and other physicians to understand and critically evaluate ongoing and new AI applications in perioperative management. AI uses available databases called “big data” to formulate an algorithm. Analysis of other data based on these algorithms can help in early diagnosis, accurate risk assessment, intraoperative management, automated drug delivery, predicting anesthesia and surgical complications and postoperative outcomes and can thus lead to effective perioperative management as well as to reduce the cost of treatment. Perioperative physicians, anesthesiologists, and surgeons are well-positioned to help integrate AI into modern surgical practice. We all need to partner and collaborate with data scientists to collect and analyze data across all phases of perioperative care to provide clinical scenarios and context. Careful implementation and use of AI along with real-time human interpretation will revolutionize perioperative care, and is the way forward in future perioperative management of major surgery.     

Evidence-base guideline on management of colorectal liver metastases in the Netherlands

A dutch national evidence-based guideline on the diagnosis and treatment of patients with colorectal liver metastases has been developed. The most important recommendations are as follows. For synchronous liver metastases, spiral computed tomography (CT) or magnetic resonance imaging (MRI) should be used as imaging. For evaluation of lung metastases, imaging can be limited to chest radiography. For detection of metachronous liver metastases, ultrasonography could be performed as initial modality if the entire liver is adequately visualised. In doubtful cases or potential candidates for surgery, CT or MRI should be performed as additional imaging. For evaluation of extrahepatic disease, abdominal and chest CT could be performed. Fluorodeoxyglucose positron emission tomography could be valuable in patients selected for surgery based on CT (liver/abdomen/chest), for identifying additional extrahepatic disease. Surgical resection is the treatment of choice with a five-year survival of 30 to 40%. Variation in selection criteria for surgery is caused by inconclusive data in the literature concerning surgical margins.     

Diagnosis of aneurysm of the thoracic aorta. Comparison between two non invasive techniques: two-dimensional echocardiography and computed tomography

In order to assess the respective values of two-dimensionalechocardiography (2D echo) and computed tomography (CT) in theevaluation of aneurysms of the thoracic aorta, 14 patients withangiographically proven aneurysms of the thoracic aorta (threeof which were dissecting aneurysms) were studied. The entire thoracic aorta was visualized in 10/14 patients by2D Echo and in all patients by CT. An intimal flap was recognized by 2D echo in each case witha dissection whereas such a recognition was never possible withCT. CT identified calcification of the wall of an huge aneurysmof the ascending aorta in one case and a thrombotic stratificationin the lumen of the descending thoracic aorta in another case;both abnormalities were missed by echocardiography probablybecause of inappropriate gain setting. In conclusion, 2D Echo and CT are both useful in the evaluationof aneurysms of the thoracic aorta: 2D echo appears to be superiorin the recognition of an intimal flap due to dissection whereasCT allows a better recognition of the configuration, extensionand tissue modifications of the aneurysm.     

Augmented reality and image overlay navigation with OsiriX in laparoscopic and robotic surgery: not only a matter of fashion

Background

New technologies can considerably improve preoperative planning, enhance the surgeon’s skill and simplify the approach to complex procedures. Augmented reality techniques, robot assisted operations and computer assisted navigation tools will become increasingly important in surgery and in residents’ education.

Methods

We obtained 3D reconstructions from simple spiral computed tomography (CT) slides using OsiriX, an open source processing software package dedicated to DICOM images. These images were then projected on the patient's body with a beamer fixed to the operating table to enhance spatial perception during surgical intervention (augmented reality).

Results

Changing a window's deepness level allowed the surgeon to navigate through the patient's anatomy, highlighting regions of interest and marked pathologies. We used image overlay navigation for laparoscopic operations such cholecystectomy, abdominal exploration, distal pancreas resection and robotic liver resection.

Conclusions

Augmented reality techniques will transform the behaviour of surgeons, making surgical interventions easier, faster and probably safer. These new techniques will also renew methods of surgical teaching, facilitating transmission of knowledge and skill to young surgeons.