Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System.

The game of Jenga is a benchmark used for developing innovative manipulation solutions for complex tasks. Indeed, it encourages the study of novel robotics methods to successfully extract blocks from a tower. A Jenga game involves many traits of complex industrial and surgical manipulation tasks, requiring a multi-step strategy, the combination of visual and tactile data, and the highly precise motion of a robotic arm to perform a single block extraction. In this work, we propose a novel, cost-effective architecture for playing Jenga with e.Do, a 6DOF anthropomorphic manipulator manufactured by Comau, a standard depth camera, and an inexpensive monodirectional force sensor. Our solution focuses on a visual-based control strategy to accurately align the end-effector with the desired block, enabling block extraction by pushing. To this aim, we trained an instance segmentation deep learning model on a synthetic custom dataset to segment each piece of the Jenga tower, allowing for visual tracking of the desired block's pose during the motion of the manipulator. We integrated the visual-based strategy with a 1D force sensor to detect whether the block could be safely removed by identifying a force threshold value. Our experimentation shows that our low-cost solution allows e.DO to precisely reach removable blocks and perform up to 14 consecutive extractions in a row.

Efficient-CapsNet: capsule network with self-attention routing.

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of features detectors. Even though capsules networks are still in their infancy, they constitute a promising solution to extend current convolutional networks and endow artificial visual perception with a process to encode more efficiently all feature affine transformations. Indeed, a properly working capsule network should theoretically achieve higher results with a considerably lower number of parameters count due to intrinsic capability to generalize to novel viewpoints. Nevertheless, little attention has been given to this relevant aspect. In this paper, we investigate the efficiency of capsule networks and, pushing their capacity to the limits with an extreme architecture with barely 160 K parameters, we prove that the proposed architecture is still able to achieve state-of-the-art results on three different datasets with only 2% of the original CapsNet parameters. Moreover, we replace dynamic routing with a novel non-iterative, highly parallelizable routing algorithm that can easily cope with a reduced number of capsules. Extensive experimentation with other capsule implementations has proved the effectiveness of our methodology and the capability of capsule networks to efficiently embed visual representations more prone to generalization.

Open Abdomen in Obese Patients: Pay Attention! New Evidences from IROA, the International Register of Open Abdomen.

BACKGROUND: Open abdomen is the cornerstone of damage control strategies in acute care and trauma surgery. The role of BMI has not been well investigated. The aim of the study was to assess the role of BMI in determining outcomes after open abdomen. METHODS: This is an analysis of patients recorded into the International Register of Open Abdomen; patients were classified in two groups according to BMI using a cutoff of 30 kg/m2. The primary outcome was in-hospital mortality; secondary outcomes were primary fascia closure rate, length of treatment, complication rate, entero-atmospheric fistula rate and length of ICU stay. RESULTS: A total of 591 patients were enrolled from 57 centers, and obese patients were 127 (21.5%). There was no difference in mortality between the two groups; complications developed during the open treatment were higher in obese patients (63.8% vs. 53.4%, p = 0.038) while post-closure complications rate was similar. Obese patients had a significantly longer duration of the open treatment (9.1 ± 11.5 days vs. 6.3 ± 7.5 days; p = 0,002) and lower primary fascia closure rate (75.5% vs. 89.5%; p < 0,001). No differences in fistula rate were found. There was a linear correlation between the duration of open abdomen and the BMI (Pearson's linear correlation coefficient = 0,201; p < 0,001). CONCLUSIONS: Open abdomen in obese patients seems to be safe as in non-obese patients with similar mortality; however, in obese patients the length of open abdomen is significantly higher with higher complication rate, longer ICU length of stay and lower primary fascia closure rate. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov, Identifier: NCT02382770.

The open abdomen in trauma and non-trauma patients: WSES guidelines.

Damage control resuscitation may lead to postoperative intra-abdominal hypertension or abdominal compartment syndrome. These conditions may result in a vicious, self-perpetuating cycle leading to severe physiologic derangements and multiorgan failure unless interrupted by abdominal (surgical or other) decompression. Further, in some clinical situations, the abdomen cannot be closed due to the visceral edema, the inability to control the compelling source of infection or the necessity to re-explore (as a "planned second-look" laparotomy) or complete previously initiated damage control procedures or in cases of abdominal wall disruption. The open abdomen in trauma and non-trauma patients has been proposed to be effective in preventing or treating deranged physiology in patients with severe injuries or critical illness when no other perceived options exist. Its use, however, remains controversial as it is resource consuming and represents a non-anatomic situation with the potential for severe adverse effects. Its use, therefore, should only be considered in patients who would most benefit from it. Abdominal fascia-to-fascia closure should be done as soon as the patient can physiologically tolerate it. All precautions to minimize complications should be implemented.

The role of open abdomen in non-trauma patient: WSES Consensus Paper.

The open abdomen (OA) is defined as intentional decision to leave the fascial edges of the abdomen un-approximated after laparotomy (laparostomy). The abdominal contents are potentially exposed and therefore must be protected with a temporary coverage, which is referred to as temporal abdominal closure (TAC). OA use remains widely debated with many specific details deserving detailed assessment and clarification. To date, in patients with intra-abdominal emergencies, the OA has not been formally endorsed for routine utilization; although, utilization is seemingly increasing. Therefore, the World Society of Emergency Surgery (WSES), Abdominal Compartment Society (WSACS) and the Donegal Research Academy united a worldwide group of experts in an international consensus conference to review and thereafter propose the basis for evidence-directed utilization of OA management in non-trauma emergency surgery and critically ill patients. In addition to utilization recommendations, questions with insufficient evidence urgently requiring future study were identified.

Splenic trauma: WSES classification and guidelines for adult and pediatric patients.

Spleen injuries are among the most frequent trauma-related injuries. At present, they are classified according to the anatomy of the injury. The optimal treatment strategy, however, should keep into consideration the hemodynamic status, the anatomic derangement, and the associated injuries. The management of splenic trauma patients aims to restore the homeostasis and the normal physiopathology especially considering the modern tools for bleeding management. Thus, the management of splenic trauma should be ultimately multidisciplinary and based on the physiology of the patient, the anatomy of the injury, and the associated lesions. Lastly, as the management of adults and children must be different, children should always be treated in dedicated pediatric trauma centers. In fact, the vast majority of pediatric patients with blunt splenic trauma can be managed non-operatively. This paper presents the World Society of Emergency Surgery (WSES) classification of splenic trauma and the management guidelines.

Erratum to: IROA: International Register of Open Abdomen, preliminary results.

[This corrects the article DOI: 10.1186/s13017-017-0123-8.].

IROA: International Register of Open Abdomen, preliminary results.

BACKGROUND: No definitive data about open abdomen (OA) epidemiology and outcomes exist. The World Society of Emergency Surgery (WSES) and the Panamerican Trauma Society (PTS) promoted the International Register of Open Abdomen (IROA). METHODS: A prospective observational cohort study including patients with an OA treatment. Data were recorded on a web platform (Clinical Registers®) through a dedicated website: www.clinicalregisters.org. RESULTS: Four hundred two patients enrolled. Adult patients: 369 patients; Mean age: 57.39±18.37; 56% male; Mean BMI: 36±5.6. OA indication: Peritonitis (48.7%), Trauma (20.5%), Vascular Emergencies/Hemorrhage (9.4%), Ischemia (9.1%), Pancreatitis (4.2%),Post-operative abdominal-compartment-syndrome (3.9%), Others (4.2%). The most adopted Temporary-abdominal-closure systems were the commercial negative pressure ones (44.2%). During OA 38% of patients had complications; among them 10.5% had fistula. Definitive closure: 82.8%; Mortality during treatment: 17.2%. Mean duration of OA: 5.39(±4.83) days; Mean number of dressing changes: 0.88(±0.88). After-closure complications: (49.5%) and Mortality: (9%). No significant associations among TACT, indications, mortality, complications and fistula. A linear correlationexists between days of OA and complications (Pearson linear correlation = 0.326 p<0.0001) and with the fistula development (Pearson = 0.146 p= 0.016). Pediatric patients: 33 patients. Mean age: 5.91±(3.68) years; 60% male. Mortality: 3.4%; Complications: 44.8%; Fistula: 3.4%. Mean duration of OA: 3.22(±3.09) days. CONCLUSION: Temporary abdominal closure is reliable and safe. The different techniques account for different results according to the different indications. In peritonitis commercial negative pressure temporary closure seems to improve results. In trauma skin-closure and Bogotà-bag seem to improve results. TRIAL REGISTRATION: ClinicalTrials.gov NCT02382770.