Accurate color imaging of pathology slides using holography and absorbance spectrum estimation of histochemical stains

Digital Histopathological Discrimination of Label-Free Tumoral Tissues by Artificial Intelligence Phase-Imaging Microscopy

Histopathology is the gold standard for disease diagnosis. The use of digital histology on fresh samples can reduce processing time and potential image artifacts, as label-free samples do not need to be fixed nor stained. This fact allows for a faster diagnosis, increasing the speed of the process and the impact on patient prognosis. This work proposes, implements, and validates a novel digital diagnosis procedure of fresh label-free histological samples. The procedure is based on advanced phase-imaging microscopy parameters and artificial intelligence. Fresh human histological samples of healthy and tumoral liver, kidney, ganglion, testicle and brain were collected and imaged with phase-imaging microscopy. Advanced phase parameters were calculated from the images. The statistical significance of each parameter for each tissue type was evaluated at different magnifications of 10×, 20× and 40×. Several classification algorithms based on artificial intelligence were applied and evaluated. Artificial Neural Network and Decision Tree approaches provided the best general sensibility and specificity results, with values over 90% for the majority of biological tissues at some magnifications. These results show the potential to provide a label-free automatic significant diagnosis of fresh histological samples with advanced parameters of phase-imaging microscopy. This approach can complement the present clinical procedures.

Wide-Field Pixel Super-Resolution Colour Lensfree Microscope for Digital Pathology

Whole slide imaging enables scanning entire stained-glass slides with high resolution into digital images for the tissue morphology/molecular pathology assessment and analysis, which has increased in adoption for both clinical and research applications. As an alternative to conventional optical microscopy, lensfree holography imaging, which offers high resolution and a wide field of view (FOV) with digital focus, has been widely used in various types of biomedical imaging. However, accurate colour holographic imaging with pixel super-resolution reconstruction has remained a great challenge due to its coherent characteristic. In this work, we propose a wide-field pixel super-resolution colour lensfree microscopy by performing wavelength scanning pixel super-resolution and phase retrieval simultaneously on the three channels of red, green and blue (RGB), respectively. High-resolution RGB three-channel composite colour image is converted to the YUV space for separating the colour component and the brightness component, keeping the brightness component unchanged as well as enhancing the colour component through average filter, which not only eliminates the common rainbow artifacts of holographic colour reconstruction but also maintains the high-resolution details collected under different colour illuminations. We conducted experiments on the reconstruction of a USAF1951, stained lotus root and red bone marrow smear for performance evaluation of the spatial resolution and colour reconstruction with an imaging FOV >40 mm².

Color lens-free imaging using multi-wavelength illumination based phase retrieval

Accurate image reconstruction in color lens-free imaging has proven challenging. The color image reconstruction of a sample is impacted not only by how strongly the illumination intensity is absorbed at a given spectral range, but also by the lack of phase information recorded on the image sensor. We present a compact and cost-effective approach of addressing the need for phase retrieval to enable robust color image reconstruction in lens-free imaging. The amplitude images obtained at transparent wavelength bands are used to estimate the phase in highly absorbed wavelength bands. The accurate phase information, obtained through our iterative algorithm, removes the color artefacts due to twin-image noise in the reconstructed image and improves image reconstruction quality to allow accurate color reconstruction. This could enable the technique to be applied for imaging of stained pathology slides, an important tool in medical diagnostics.

Deep learning-based color holographic microscopy

We report a framework based on a generative adversarial network that performs high-fidelity color image reconstruction using a single hologram of a sample that is illuminated simultaneously by light at three different wavelengths. The trained network learns to eliminate missing-phase-related artifacts, and generates an accurate color transformation for the reconstructed image. Our framework is experimentally demonstrated using lung and prostate tissue sections that are labeled with different histological stains. This framework is envisaged to be applicable to point-of-care histopathology and presents a significant improvement in the throughput of coherent microscopy systems given that only a single hologram of the specimen is required for accurate color imaging.