Fully end-to-end deep-learning-based diagnosis of pancreatic tumors.

Artificial intelligence can facilitate clinical decision making by considering massive amounts of medical imaging data. Various algorithms have been implemented for different clinical applications. Accurate diagnosis and treatment require reliable and interpretable data. For pancreatic tumor diagnosis, only 58.5% of images from the First Affiliated Hospital and the Second Affiliated Hospital, Zhejiang University School of Medicine are used, increasing labor and time costs to manually filter out images not directly used by the diagnostic model. Methods: This study used a training dataset of 143,945 dynamic contrast-enhanced CT images of the abdomen from 319 patients. The proposed model contained four stages: image screening, pancreas location, pancreas segmentation, and pancreatic tumor diagnosis. Results: We established a fully end-to-end deep-learning model for diagnosing pancreatic tumors and proposing treatment. The model considers original abdominal CT images without any manual preprocessing. Our artificial-intelligence-based system achieved an area under the curve of 0.871 and a F1 score of 88.5% using an independent testing dataset containing 107,036 clinical CT images from 347 patients. The average accuracy for all tumor types was 82.7%, and the independent accuracies of identifying intraductal papillary mucinous neoplasm and pancreatic ductal adenocarcinoma were 100% and 87.6%, respectively. The average test time per patient was 18.6 s, compared with at least 8 min for manual reviewing. Furthermore, the model provided a transparent and interpretable diagnosis by producing saliency maps highlighting the regions relevant to its decision. Conclusions: The proposed model can potentially deliver efficient and accurate preoperative diagnoses that could aid the surgical management of pancreatic tumor.

Aberration corrections of doughnut beam by adaptive optics in the turbid medium.

The doughnut beam is a spatially structured beam which has been widely used in super-resolution microscopy, laser trapping and so on. However, when it passes through thick scattering medium, aberrations will seriously affect its performance. Currently, adaptive optics (AO) has become one of the most powerful tools to compensate aberrations. However, conventional AO always suffers from limited corrected field of view (FOV). Here, we propose a method with conjugate AO system based on coherent optical adaptive technique. The results show that the corrected FOV can be improved effectively. For a wide range of the optical applications with doughnut beam, our method has potentials in correcting aberrations with high speed in turbid media.(A) Mouse brain slice, (B) the distribution of r PAO , (C) the distribution of r CAO . The vortex beam focus of the blue point in (B) and (C) among a 137.5 × 137.5 µm FOV (D1) ideally, (D2) with scattering, (D3) in pupil AO system and (D4) in conjugate AO system.

Ultrafast optical clearing method for three-dimensional imaging with cellular resolution.

Optical clearing is a versatile approach to improve imaging quality and depth of optical microscopy by reducing scattered light. However, conventional optical clearing methods are restricted in the efficiency-first applications due to unsatisfied time consumption, irreversible tissue deformation, and fluorescence quenching. Here, we developed an ultrafast optical clearing method (FOCM) with simple protocols and common reagents to overcome these limitations. The results show that FOCM can rapidly clarify 300-µm-thick brain slices within 2 min. Besides, the tissue linear expansion can be well controlled by only a 2.12% increase, meanwhile the fluorescence signals of GFP can be preserved up to 86% even after 11 d. By using FOCM, we successfully built the detailed 3D nerve cells model and showed the connection between neuron, astrocyte, and blood vessel. When applied to 3D imaging analysis, we found that the foot shock and morphine stimulation induced distinct c-fos pattern in the paraventricular nucleus of the hypothalamus (PVH). Therefore, FOCM has the potential to be a widely used sample mounting media for biological optical imaging.

Large field of view correction by using conjugate adaptive optics with multiple guide stars.

Adaptive optics has been widely used in the optical microscopy to recover high-resolution images deep into the sample. However, the corrected field of view (FOV) with a single correction is generally limited, which seriously restricts the imaging speed. In this article, we demonstrate a high-speed wavefront correction method by using the conjugate adaptive optical correction with multiple guide stars (CAOMG) based on the coherent optical adaptive technique. The results show that the CAOMG method can greatly improve the corrected FOV. For 120-µm-thick mouse brain tissue, the corrected FOV can be improved up to ~243 times of the conventional pupil adaptive optics (PAO) without additional time consumption. Therefore, this study shows the potential of high-speed imaging through scattering medium in biological science.

Two-photon focal modulation microscopy for high-resolution imaging in deep tissue.

Two-photon microscopy (2PM) is one of the most widely used tools for in vivo deep tissue imaging. However, the spatial resolution and penetration depth are still limited due to the strong scattering background. Here we demonstrate a two-photon focal modulation microscopy. By utilizing the modulation and demodulation techniques, background rejection capability is enhanced, thus spatial resolution and imaging penetration depth are improved. Compared with 2PM, the transverse resolution is increased by 70%, while the axial resolution is increased to 2-fold. Furthermore, when applied in conventional 2PM mode, it can achieve inertial-free scanning in either transverse or axial direction with in principle unlimited scanning speed. Finally, we applied 2PFMM in thick scattering samples to further examine the imaging performance. The results show that the signal-to-background ratio of 2PFMM can be improved up to five times of 2PM at the depth of 500 µm. Fluorescent imaging in the mouse brain tissue. 3D Thy1-GFP hippocampal neurons imaged by (A) 2PM compared with (B) 2PFMM; (C-H) xy maximum-intensity projection imaged by 2PM compared with 2PFMM. Scale bar 50 µm.

Machine learning guided rapid focusing with sensor-less aberration corrections.

Non-invasive, real-time imaging and deep focus into tissue are in high demand in biomedical research. However, the aberration that is introduced by the refractive index inhomogeneity of biological tissue hinders the way forward. A rapid focusing with sensor-less aberration corrections, based on machine learning, is demonstrated in this paper. The proposed method applies the Convolutional Neural Network (CNN), which can rapidly calculate the low-order aberrations from the point spread function images with Zernike modes after training. The results show that approximately 90 percent correction accuracy can be achieved. The average mean square error of each Zernike coefficient in 200 repetitions is 0.06. Furthermore, the aberration induced by 1-mm-thick phantom samples and 300-µm-thick mouse brain slices can be efficiently compensated through loading a compensation phase on an adaptive element placed at the back-pupil plane. The phase reconstruction requires less than 0.2 s. Therefore, this method offers great potential for in vivo real-time imaging in biological science.

Optimization for imaging through scattering media for confocal microscopes with divided elliptical apertures.

We develop a confocal system equipped with optimal elliptical apertures to improve axial point spread function and signal-to-background ratio (SBR) for different detector sizes. By adjusting the parameters of the elliptical apertures, the axial half width at half-maximum can be reduced to 4.986 (described in optical coordinates) and SBR can be improved to 0.176. We evaluate this system with the 1951 USAF resolution test chart and the primary cultured neuron from SD rat stained by Map-2, and observe better imaging performance, which indicates the potential applications in biological science.

Optical Brain Imaging: A Powerful Tool for Neuroscience.

As the control center of organisms, the brain remains little understood due to its complexity. Taking advantage of imaging methods, scientists have found an accessible approach to unraveling the mystery of neuroscience. Among these methods, optical imaging techniques are widely used due to their high molecular specificity and single-molecule sensitivity. Here, we overview several optical imaging techniques in neuroscience of recent years, including brain clearing, the micro-optical sectioning tomography system, and deep tissue imaging.