[Challenges and options for advanced training in surgery : An interdisciplinary position paper against the background of the hospital structural reform in Germany]. / Herausforderungen und Chancen für die chirurgische Weiterbildung : Ein fachgesellschaftsübergreifendes Positionspapier vor dem Hintergrund der Krankenhausstrukturreform.

BACKGROUND: Even now the further training in surgery faces considerable challenges. The planned hospital structural reform will result in new bureaucratic and organizational hurdles, which could lead to a considerable loss of quality in advanced surgical training across all disciplines. OBJECTIVE: The aim of this position paper is to describe the current and future challenges for advanced surgical training and to identify possible approaches and opportunities for the further development against the background of the planned hospital structural reform. MATERIAL AND METHODS: For the development of this position paper a committee of representatives of the Young Forums of the German surgical societies identified and critically discussed current problems and challenges of the present residency training system and formulated a list of demands for a sustainable residency training concept. RESULTS: The planned shift to outpatient treatment and centralization were identified as central challenges for surgical residency training. Surgical training must be considered consistently and from the outset in all political reform efforts. In addition to a transparent and cost-appropriate financing of residency training, we call for the involvement of all German surgical societies in the reform process. Furthermore, the social framework conditions for junior surgeons should be considered. CONCLUSION: The structural change in the hospital landscape in Germany, which is being forced by politicians, harbors the risk of a further loss of quality and experience in surgical treatment and training. At the same time, the planned hospital reform offers a unique opportunity to address existing problems and challenges in surgical training and to consider them as a starting point for structural changes which are fit for the future.

The Use of Artificial Intelligence for the Classification of Craniofacial Deformities.

Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation-free imaging technique. A total of 487 patients with photogrammetry scans were included in this retrospective cohort study: children with craniosynostosis (n = 227), positional deformities (n = 206), and healthy children (n = 54). Three two-dimensional images were extracted from each photogrammetry scan. The datasets were divided into training, validation, and test sets. During the training, fine-tuned ResNet-152s were utilized. The performance was quantified using tenfold cross-validation. For the detection of craniosynostosis, sensitivity was at 0.94 with a specificity of 0.85. Regarding the differentiation of the five existing classes (trigonocephaly, scaphocephaly, positional plagiocephaly left, positional plagiocephaly right, and healthy), sensitivity ranged from 0.45 (positional plagiocephaly left) to 0.95 (scaphocephaly) and specificity ranged from 0.87 (positional plagiocephaly right) to 0.97 (scaphocephaly). We present a CNN-based approach to classify craniofacial deformities on two-dimensional images with promising results. A larger dataset would be required to identify rarer forms of craniosynostosis as well. The chosen 2D approach enables future applications for digital cameras or smartphones.

Accuracy of Patient-Specific Implants in Virtually Planned Segmental Le Fort I Osteotomies.

(1) Background: In orthognathic surgery, segmental Le Fort I osteotomies are a valuable method to correct maxillary deformities or transversal discrepancies. However, these procedures are technically challenging, and osteosynthesis can be prone to error. (2) Methods: In this retrospective, monocentric cohort study, patients were enrolled who underwent a virtually planned segmental maxillary osteotomy during their combined treatment. Positioning and osteosynthesis were achieved by either a 3D-printed splint and conventional miniplates or patient-specific implants (PSI). The preoperative CT data, virtual planning data, and postoperative CBCT data were segmented. The deviation of all the segments from the desired virtually planned position was measured using the analysis function of IPS CaseDesigner. (3) Results: 28 Patients in the PSI Group and 22 in the conventional groups were included. The PSI group showed significantly lower deviation from the planned position anteroposteriorly (-0.63 ± 1.62 mm vs. -1.3 ± 2.54 mm) and craniocaudally (-1.39 ± 1.59 mm vs. -2.7 ± 3.1 mm). For rotational deviations, the pitch (0.64 ± 2.59° vs. 2.91 ± 4.08°), as well as the inward rotation of the lateral segments, was positively influenced by PSI. (4). Conclusions: The presented data show that patient-specific osteosynthesis significantly reduces deviations from the preoperative plan in virtually planned cases. Transversal expansions and vertical positioning can be addressed better.