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.
17 May 2019 in Proceedings of the National Academy of Sciences
Significance: Most biological tissue is opaque, and the inside fine structures are invisible even with a microscope. Optical clearing methods can reduce the scattering and enable us to “look” inside the biological samples. Current optical clearing methods suffer from large time consumption, tissue distortion, and fluorescence quenching, which greatly limit their applications. Here, we describe a nontoxic ultrafast optical clearing method (FOCM), which could clarify 300-µm-thick brain slices within 2 min without morphology distortion. The fluorescence can be preserved up to 86% even after 11 d. Besides, the cheap reagents and easy operation makes our method have great potential to be widely used. Besides the brain slices, our method can also be applied to other biological tissues.
We present a learning-based Shack-Hartmann wavefront sensor (SHWS) to achieve the high-order aberration detection without image segmentation or centroid positioning. Zernike coefficient amplitudes of aberrations measured from biological samples are referred and expanded to generate the training datasets. With one SHWS pattern inputted, up to 120th Zernike modes could be predicted within 10.9 ms with 95.56% model accuracy by a personal computer. The statistical experimental results show that compared with traditional modal-based SHWS, the root mean squared error in phase residuals of this method is reduced by ∼40.54% and the Strehl ratio of the point spread functions is improved by ∼27.31%. The aberration detection performance of this method is also validated on a mouse brain slice with 300 µm thickness and the median improvement of peak-to-background ratio of this method is ∼30% to 40% compared with traditional SHWS. With the high detection accuracy, simple processes, fast prediction speed and good compatibility, this work offers a potential approach to improve the wavefront sensing ability of SHWS, which could be combined with an existing adaptive optics system and be further applied in biological applications.
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.
The amygdala, one of the most studied brain structures, integrates brain-wide heterogeneous inputs and governs multidimensional outputs to control diverse behaviors central to survival, yet how amygdalar input-output neuronal circuits are organized remains unclear. Using a simplified cell-type- and projection-specific retrograde transsynaptic tracing technique, we scrutinized brain-wide afferent inputs of four major output neuronal groups in the amygdalar basolateral complex (BLA) that project to the bed nucleus of the stria terminals (BNST), ventral hippocampus (vHPC), medial prefrontal cortex (mPFC) and nucleus accumbens (NAc), respectively. Brain-wide input-output quantitative analysis unveils that BLA efferent neurons receive a diverse array of afferents with varied input weights and predominant contextual representation. Notably, the afferents received by BNST-, vHPC-, mPFC- and NAc-projecting BLA neurons exhibit virtually identical origins and input weights. These results indicate that the organization of amygdalar BLA input-output neuronal circuits follows the input-dependent and output-independent principles, ideal for integrating brain-wide diverse afferent stimuli to control parallel efferent actions. The data provide the objective basis for improving the virtual reality exposure therapy for anxiety disorders and validate the simplified cell-type- and projection-specific retrograde transsynaptic tracing method.
21 October 2022 in Journal of Biomedical Informatics
Glaucoma is the leading cause of irreversible blindness, and the early detection and timely treatment are essential for glaucoma management. However, due to the interindividual variability in the characteristics of glaucoma onset, a single feature is not yet sufficient for monitoring glaucoma progression in isolation. There is an urgent need to develop more comprehensive diagnostic methods with higher accuracy. In this study, we proposed a multi- feature deep learning (MFDL) system based on intraocular pressure (IOP), color fundus photograph (CFP) and visual field (VF) to classify the glaucoma into four severity levels. We designed a three-phase framework for glaucoma severity diagnosis from coarse to fine, which contains screening, detection and classification. We trained it on 6,131 samples from 3,324 patients and tested it on independent 240 samples from 185 patients. Our results show that MFDL achieved a higher accuracy of 0.842 (95 % CI, 0.795-0.888) than the direct four classification deep learning (DFC-DL, accuracy of 0.513 [0.449-0.576]), CFP-based single-feature deep learning (CFP-DL, accuracy of 0.483 [0.420-0.547]) and VF-based single-feature deep learning (VF-DL, accuracy of 0.725 [0.668-0.782]). Its performance was statistically significantly superior to that of 8 juniors. It also outperformed 3 seniors and 1 expert, and was comparable with 2 glaucoma experts (0.842 vs 0.854, p = 0.663; 0.842 vs 0.858, p = 0.580). With the assistance of MFDL, junior ophthalmologists achieved statistically significantly higher accuracy performance, with the increased accuracy ranged from 7.50 % to 17.9 %, and that of seniors and experts were 6.30 % to 7.50 % and 5.40 % to 7.50 %. The mean diagnosis time per patient of MFDL was 5.96 s. The proposed model can potentially assist ophthalmologists in efficient and accurate glaucoma diagnosis that could aid the clinical management of glaucoma.