arducamcameracontrol_pyside2

basicgrblcontroller_withgui

baslercameracontrol_pyside2

blocksegmentation_parallelmatrixmultiplication

Blok bölütleme ile matris çarpımı işlemi orijinal bir matrisin bloklar haline dönüştürüldükten sonra blokların matris çarpımı kuralına göre birbirleriyle çarpılma işlemidir.

cancercell_image_enhancement_srcnn

Super resolution convolutional neural network model was trained using A2780 cell images, which is an ovarian cancer cell. With the trained model, resolution and contrast increase were obtained. The training data were created with QuantaCell, an automatic cell counting device produced by Optofil.

celeba_dataset_wgan-gp

cellcounter_embeddedsoftware

cellviabilityapp

covid19_classification_tmempr

Medical images are crucial data sources for not easily diagnosed diseases. X-rays, one of the medical images, have high resolution. Processing high-resolution images leads to a few problems such as the difficulties in data storage, the computational load, and the time required to process high-dimensional data. It is a vital element to be able to diagnose diseases fast and accurately. In this study, a data set consisting of lung X-rays of patients with and without COVID-19 symptoms was taken into consideration and disease diagnosis from these images can be summarized in 2 steps as preprocessing and classification. Preprocessing step is the feature extraction process and in this step, the recently developed decomposition-based method Tridiagonal Matrix Enhanced Multivariance Products Representation (TMEMPR) is proposed as a feature extraction method. Classification of images is the second step where the Random Forest and Support Vector Machine (SVM) is applied as classifiers. Also, X-ray images have been reduced by 99,9\% with TMEMPR and with several state-of-the-art feature extraction methods which are Discrete Wavelet Transform (DWT), Discrete Cosine Transform(DCT) The results are examined under different feature extraction methods. It is observed that a higher accuracy rate of classification is achieved by using the TMEMPR method.

deepcan

Precise and quick monitoring of key cytometric features such as cell count, cell size, cell morphology and DNA content is crucial for life research and development. Cytometry is important for numerous applications in biotechnology, medical sciences, and cell culture research laboratories. Flow cytometry that relies on aligning cell flow and their characterization by optical or electrical detection has been the dom- inant cytometry approach for high throughput applications. Recent advances in digital microscopy revealed image cytometry as a viable alternative that can lead to simpler, more compact and less expensive solutions. Traditionally, image cytome- try relies on the use of a hemocytometer accompanied with visual inspection of an operator under the microscope. This approach is prone to error due to subjective decisions of the operator. Machine learning approaches have recently emerged as powerful tools enabling quick and highly accurate image cytometric analysis that are easily generalizable to different cell types. Here, we demonstrate a modular deep learning system (DeepCAN) that provides a complete solution for automated cell counting and viability analysis. DeepCAN employs three different neural network blocks called Parallel Segmenter, Cluster CNN, and Viability CNN that are trained for initial segmentation, cluster separation, and cell viability analysis, respectively. Parallel Segmenter and Cluster CNN blocks achieve highly accurate segmentation of individual cells while Viability CNN block performs viability classification A modified U-Net network, a well-known deep neural network model for bio-image analysis, is used in Parallel Segmenter while LeNet-5 architecture and itss modifid versions are used for Cluster CNN and Viability CNN, respectively. We trained the Parallel Seg- menter using 15 images of A2780 cells and 5 images of yeasts cells containing 14742 individual cell images. Similarly, 6101 and 5900 A2480 cell images were employed for training of Cluster CNN and Viability CNN models. 2514 individual A2780 cell images were used to test the overall segmentation performance of Parallel Segmenter combined with Cluster CNN, revealing a high precision of 96.52%. Overall cell count- ing/viability analysis performance of DeepCAN was tested with A2780 (2514 cells), A549 (601 cells), Colo (356 cells), and MDA-MB-231 (857 cells) cell images reveal- ing high counting/viability accuracies of 93.82 %/95.93 %, 92.18 %/97.90 %, and 85.32 %/97.40 %, respectively.

eeg_classification_featureextractionmethods

eog_based_laparoscopy_device

falsecolor

FalseColor Python is a rapid digital staining module designed for translating two-channel fluorescence images (i.e. a nuclear and cytoplasmic stain) to the traditional H&E histopathology color space.

fiberscope_app_pyside2_basler

fluorescencemicroscopy_desktopapp

frknrnn

hamamatsucamera_lightcrafter6500_control

keras-segmentationmodels

modernwidgets_pyside2

multiplefiletransfer-socket

python_usefuldecorators

qt_appstore

qt_basicwebsocket

qt_loginui_firebaseauth

qtauthfirebase

structured_illumination_microscopy_app

unetsegmentation-pytorch