Search

INTRODUCTION: The lungs have three main fissures: the right oblique fissure (ROF), right horizontal fissure (RHF), and left oblique fissure (LOF). These can be complete, incomplete or absent; quantifying the degree of completeness of these fissures is novel. Standard textbooks often refer to the fissures as complete, but awareness of variation is essential in thoracic surgery. MATERIALS AND METHODS: Fissures in 81 pairs of cadaveric lungs were classified. Oblique fissures were measured from lung hila posteriorly to the lung hila anteriorly; and the RHF measured from the ROF to the anteromedial lung edge. The degree of completeness of fissures was expressed as a percentage of the total projected length were they to be complete. The frequency and location of accessory fissures was noted. RESULTS: LOF were complete in 66/81 (81.5%), incomplete in 13/81 (16.0%) and absent in 2/81 (2.47%); ROF were complete in 52/81 (64.2%), incomplete in 29/81 (35.8%) and never absent; RHF were more variable, complete in 18/81 (22.2%), incomplete in 54/81 (66.7%) and absent in 9/81 (11.1%). LOF and ROF were on average 97.1% and 91.6% complete, respectively, being deficient posteriorly at the lung hila. The RHF on average 69.4% complete, being deficient anteromedially. There were accessory fissures in 10 left and 19 right lungs. CONCLUSIONS: This study provides a projection of the anatomy thoracic surgeons may encounter at operation, in particular the variable RHF. This knowledge is essential for optimal outcomes in both benign and oncological procedures influenced by the fissures.

Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving provider and patient experience. We argue that unlocking this potential requires a systematic way to measure the performance of medical AI models on large-scale heterogeneous data. To meet this need, we are building MedPerf, an open framework for benchmarking machine learning in the medical domain. MedPerf will enable federated evaluation in which models are securely distributed to different facilities for evaluation, thereby empowering healthcare organizations to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status, and our roadmap. We call for researchers and organizations to join us in creating the MedPerf open benchmarking platform.

We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. A core challenge is to generalize the manipulation skills to objects in different locations. We hypothesize that modeling the relational information in the environment can significantly improve generalization. To achieve this, we propose to (i) decompose the multi-modal dynamics into elemental movement primitives, (ii) parameterize each primitive using a recurrent graph neural network to capture interactions, and (iii) integrate a high-level planner that composes primitives sequentially and a low-level controller to combine primitive dynamics and inverse kinematics control. Our model is a deep, hierarchical, modular architecture. Compared to baselines, our model generalizes better and achieves higher success rates on several simulated bimanual robotic manipulation tasks. We open source the code for simulation, data, and models at: https://github.com/Rose-STL-Lab/HDR-IL.