Deep learning-enabled fluorescence imaging for surgical guidance: in silico training for oral cancer depth quantification.

Significance: Oral cancer surgery requires accurate margin delineation to balance complete resection with post-operative functionality. Current in vivo fluorescence imaging systems provide two-dimensional margin assessment yet fail to quantify tumor depth prior to resection. Harnessing structured light in combination with deep learning (DL) may provide near real-time three-dimensional margin detection. Aim: A DL-enabled fluorescence spatial frequency domain imaging (SFDI) system trained with in silico tumor models was developed to quantify the depth of oral tumors. Approach: A convolutional neural network was designed to produce tumor depth and concentration maps from SFDI images. Three in silico representations of oral cancer lesions were developed to train the DL architecture: cylinders, spherical harmonics, and composite spherical harmonics (CSHs). Each model was validated with in silico SFDI images of patient-derived tongue tumors, and the CSH model was further validated with optical phantoms. Results: The performance of the CSH model was superior when presented with patient-derived tumors ( P -value < 0.05 ). The CSH model could predict depth and concentration within 0.4 mm and 0.4 µ g / mL , respectively, for in silico tumors with depths less than 10 mm. Conclusions: A DL-enabled SFDI system trained with in silico CSH demonstrates promise in defining the deep margins of oral tumors.

Correction: Won et al. Ex Vivo Perfusion Using a Mathematical Modeled, Controlled Gas Exchange Self-Contained Bioreactor Can Maintain a Mouse Kidney for Seven Days. Cells 2022, 11, 1822.

In the original publication [...].

Ex Vivo Perfusion Using a Mathematical Modeled, Controlled Gas Exchange Self-Contained Bioreactor Can Maintain a Mouse Kidney for Seven Days.

Regenerative medicine requires better pre-clinical tools in order to increase the efficiency of novel therapies transitioning to the clinic. Current monolayer cell culture methods are suboptimal for effectively testing new therapies and live mouse models are expensive, time consuming and require invasive procedures. Fetal organ culture, organoids, microfluidics and culture of thick sections of adult organs all aim to fill the knowledge gap between monolayer culture and live mouse studies. Here we report on an ex vivo organ perfusion system that can support whole adult mouse organs. Ex vivo perfusion of healthy and diseased mouse organs allows for real-time analysis that provides immediate feedback and accurate data collection throughout the experiment. Having a suitable normothermic ex vivo perfusion system for mouse organs provides a tool that will help contribute to our understanding of kidney physiology and disease and can take advantage of the many mouse models of human disease that already exist. Furthermore, an ex vivo kidney perfusion system can be used for testing novel cell therapies, drug screening, drug validation and for the detection of nephrotoxic substances. Critical to the success of mouse ex vivo organ perfusion is having a suitable bioreactor to maintain the organ. Here we have focused on the mouse kidney and mathematically modeled, built and validated a bioreactor that can maintain a kidney for 7 days. The long duration of the ex vivo perfusion will help to advance studies on kidney disease and can rapidly test for new regenerative medicine therapies compared to whole animal studies.