In the field of regenerative medicine, tremendous numbers of cells are necessary for tissue/organ regeneration. Today automatic cell-culturing system has been developed. The next step is constructing a non-invasive method to monitor the conditions of cells automatically. As an image analysis method, convolutional neural network (CNN), one of the deep learning method, is approaching human recognition level. We constructed and applied the CNN algorithm for automatic cellular differentiation recognition of myogenic C2C12 cell line. Phase-contrast images of cultured C2C12 are prepared as input dataset. In differentiation process from myoblasts to myotubes, cellular morphology changes from round shape to elongated tubular shape due to fusion of the cells. CNN abstract the features of the shape of the cells and classify the cells depending on the culturing days from when differentiation is induced. Changes in cellular shape depending on the number of days of culture (Day 0, Day 3, Day 6) are classified with 91.3% accuracy. Image analysis with CNN has a potential to realize regenerative medicine industry.
Background: Several studies have used artificial intelligence (AI) to analyze cytology images, but AI has yet to be adopted in clinical practice. The objective of this study was to demonstrate the accuracy of AI‐based image analysis for thyroid fine‐needle aspiration cytology (FNAC) and to propose its application in clinical practice.Methods: In total, 148,395 microscopic images of FNAC were obtained from 393 thyroid nodules to train and validate the data, and EfficientNetV2‐L was used as the image‐classification model. The 35 nodules that were classified as atypia of undetermined significance (AUS) were predicted using AI training.Results: The precision‐recall area under the curve (PR AUC) was >0.95, except for poorly differentiated thyroid carcinoma (PR AUC = 0.49) and medullary thyroid carcinoma (PR AUC = 0.91). Poorly differentiated thyroid carcinoma had the lowest recall (35.4%) and was difficult to distinguish from papillary thyroid carcinoma, medullary thyroid carcinoma, and follicular thyroid carcinoma. Follicular adenomas and follicular thyroid carcinomas were distinguished from each other by 86.7% and 93.9% recall, respectively. For two‐dimensional mapping of the data using t‐distributed stochastic neighbor embedding, the lymphomas, follicular adenomas, and anaplastic thyroid carcinomas were divided into three, two, and two groups, respectively. Analysis of the AUS nodules showed 94.7% sensitivity, 14.4% specificity, 56.3% positive predictive value, and 66.7% negative predictive value.Conclusions: The authors developed an AI‐based approach to analyze thyroid FNAC cases encountered in routine practice. This analysis could be useful for the clinical management of AUS and follicular neoplasm nodules (e.g., an online AI platform for thyroid cytology consultations).
20 August 2012 in IEEE Transactions on Electron Devices
This paper presents a time-resolved CMOS image sensor with draining-only modulation (DOM) pixels, for time-domain fluorescence lifetime imaging. In the DOM pixels using a pinned photodiode (PPD) technology, a time-windowed signal charge transfer from a PPD to a pinned storage diode (PSD) is controlled by a draining gate only, without a transfer gate between the two diodes. This structure allows a potential barrierless and trapless charge transfer from the PPD to the PSD. A 256 × 256 pixel time-resolved CMOS imager with 7.5 × 7.5 μm2 DOM pixels has been implemented using 0.18-μm CMOS image sensor process technology with PPD option. The prototype demonstrates high sensitivity for weak signal of less than one electron per light pulse and accurate measurement of fluorescence decay process with subnanosecond time resolution.
This paper presents a new correlative bioimaging technique using Y2O3:Tm, Yb and Y2O3:Er, Yb nanophosphors (NPs) as imaging probes that emit luminescence excited by both near-infrared (NIR) light and an electron beam. Under 980 nm NIR light irradiation, the Y2O3:Tm, Yb and Y2O3:Er, Yb NPs emitted NIR luminescence (NIRL) around 810 nm and 1530 nm, respectively, and cathodoluminescence at 455 nm and 660 nm under excitation of accelerated electrons, respectively. Multimodalities of the NPs were confirmed in correlative NIRL/CL imaging and their locations were visualized at the same observation area in both NIRL and CL images. Using CL microscopy, the NPs were visualized at the single-particle level and with multicolour. Multiscale NIRL/CL bioimaging was demonstrated through in vivo and in vitro NIRL deep-tissue observations, cellular NIRL imaging, and high-spatial resolution CL imaging of the NPs inside cells. The location of a cell sheet transplanted onto the back muscle fascia of a hairy rat was visualized through NIRL imaging of the Y2O3:Er, Yb NPs. Accurate positions of cells through the thickness (1.5 mm) of a tissue phantom were detected by NIRL from the Y2O3:Tm, Yb NPs. Further, locations of the two types of NPs inside cells were observed using CL microscopy.
To compare results for radiological prediction of pathological invasiveness in lung adenocarcinoma between radiologists and a deep learning (DL) system. Ninety patients (50 men, 40 women; mean age, 66 years; range, 40–88 years) who underwent pre-operative chest computed tomography (CT) with 0.625-mm slice thickness were included in this retrospective study. Twenty-four cases of adenocarcinoma in situ (AIS), 20 cases of minimally invasive adenocarcinoma (MIA), and 46 cases of invasive adenocarcinoma (IVA) were pathologically diagnosed. Three radiologists of different levels of experience diagnosed each nodule by using previously documented CT findings to predict pathological invasiveness. DL was structured using a 3-dimensional (3D) convolutional neural network (3D-CNN) constructed with 2 successive pairs of convolution and max-pooling layers, and 2 fully connected layers. The output layer comprises 3 nodes to recognize the 3 conditions of adenocarcinoma (AIS, MIA, and IVA) or 2 nodes for 2 conditions (AIS and MIA/IVA). Results from DL and the 3 radiologists were statistically compared. No significant differences in pathological diagnostic accuracy rates were seen between DL and the 3 radiologists (P >.11). Receiver operating characteristic analysis demonstrated that area under the curve for DL (0.712) was almost the same as that for the radiologist with extensive experience (0.714; P = .98). Compared with the consensus results from radiologists, DL offered significantly inferior sensitivity (P = .0005), but significantly superior specificity (P = .02). Despite the small training data set, diagnostic performance of DL was almost the same as the radiologist with extensive experience. In particular, DL provided higher specificity than radiologists.