Mask R-CNN provides efficient and accurate measurement of chondrocyte viability in the label-free assessment of articular cartilage.

Objective: Chondrocyte viability (CV) can be measured with the label-free method using second harmonic generation (SHG) and two-photon excitation autofluorescence (TPAF) imaging. To automate the image processing for the label-free CV measurement, we previously demonstrated a two-step deep-learning method: Step 1 used a U-Net to segment the lacuna area on SHG images; Step 2 used dual CNN networks to count live cells and the total number of cells in extracted cell clusters from TPAF images. This study aims to develop one-step deep learning methods to improve the efficiency of CV measurement. Method: TPAF/SHG images were acquired simultaneously on cartilage samples from rats and pigs using two-photon microscopes and were merged to form RGB color images with red, green, and blue channels assigned to emission bands of oxidized flavoproteins, reduced forms of nicotinamide adenine dinucleotide, and SHG signals, respectively. Based on the Mask R-CNN, we designed a deep learning network and its denoising version using Wiener deconvolution for CV measurement. Results: Using training and test datasets from rat and porcine cartilage, we have demonstrated that Mask R-CNN-based networks can segment and classify individual cells with a single-step processing flow. The absolute error (difference between the measured and the ground-truth CV) of the CV measurement using the Mask R-CNN with or without Wiener deconvolution denoising reaches 0.01 or 0.08, respectively; the error of the previous CV networks is 0.18, significantly larger than that of the Mask R-CNN methods. Conclusions: Mask R-CNN-based deep-learning networks improve efficiency and accuracy of the label-free CV measurement.

Deep learning provides high accuracy in automated chondrocyte viability assessment in articular cartilage using nonlinear optical microscopy.

Chondrocyte viability is a crucial factor in evaluating cartilage health. Most cell viability assays rely on dyes and are not applicable for in vivo or longitudinal studies. We previously demonstrated that two-photon excited autofluorescence and second harmonic generation microscopy provided high-resolution images of cells and collagen structure; those images allowed us to distinguish live from dead chondrocytes by visual assessment or by the normalized autofluorescence ratio. However, both methods require human involvement and have low throughputs. Methods for automated cell-based image processing can improve throughput. Conventional image processing algorithms do not perform well on autofluorescence images acquired by nonlinear microscopes due to low image contrast. In this study, we compared conventional, machine learning, and deep learning methods in chondrocyte segmentation and classification. We demonstrated that deep learning significantly improved the outcome of the chondrocyte segmentation and classification. With appropriate training, the deep learning method can achieve 90% accuracy in chondrocyte viability measurement. The significance of this work is that automated imaging analysis is possible and should not become a major hurdle for the use of nonlinear optical imaging methods in biological or clinical studies.

Comparison and evaluation of biomechanical, electrical, and biological methods for assessment of damage to tissue collagen.

In regard to evaluating tissue banking methods used to preserve or otherwise treat (process) soft allograft tissue, current tests may not be sufficiently sensitive to detect potential damage inflicted before, during, and after processing. Using controlled parameters, we aim to examine the sensitivity of specific biomechanical, electrical, and biological tests in detecting mild damage to collagen. Fresh porcine pulmonary heart valves were treated with an enzyme, collagenase, and incubated using various times. Controls received no incubation. All valves were cryopreserved and stored at -135 °C until being rewarmed for evaluation using biomechanical, permeability, and cell viability tests. Statistically significant time dependent changes in leaflet ultimate stress, (p = 0.006), permeability (p = 0.01), and viability (p ≤ 0.02, four different days of culture) were found between heart valves subjected to 0-15 min of collagenase treatment (ANOVA). However, no statistical significance was found between the tensile modulus of treated and untreated valves (p = 0.07). Furthermore, the trends of decreasing and increasing ultimate stress and viability, respectively, were somewhat inconsistent across treatment times. These results suggest that permeability tests may offer a sensitive, quantitative assay to complement traditional biomechanical and viability tests in evaluating processing methods used for soft tissue allografts, or when making changes to current validated methods. Multiple test evaluation may also offer insight into the mechanism of potential tissue damage such as, as is the case here, reduced collagen content and increased tissue porosity.

Assessment of mitochondrial DNA mutations in Chinese family with essential hypertension.

Mitochondrial DNA (MtDNA) mutations played an important role in the development of essential hypertension. Mitochondrial tRNA point mutations, caused the failure in tRNA metabolism, responsible for the pathogenesis of this complex disease. In this study, we evaluated the possible role of the 4329C >G mutation in the clinical expression of hypertension in a Chinese family. Analysis of the complete mtDNA sequence variants showed that other mutations may play synergic roles in the phenotypic manifestation of hypertension. In addition, other potential pitfalls were also discussed in this context.

Does administering iodine in radiological procedures increase patient doses?

PURPOSE: The authors investigated the changes in the pattern of energy deposition in tissue equivalent phantoms following the introduction of iodinated contrast media. METHODS: The phantom consisted of a small "contrast sphere," filled with water or iodinated contrast, located at the center of a 28 cm diameter water sphere. Monte Carlo simulations were performed using mcnp5 codes, validated by simulating irradiations with analytical solutions. Monoenergetic x-rays ranging from 35 to 150 keV were used to simulate exposures to spheres containing contrast agent with iodine concentrations ranging from 1 to 100 mg/ml. Relative values of energy imparted to the contrast sphere, as well as to the whole phantom, were calculated. Changes in patterns of energy deposition around the contrast sphere were also investigated. RESULTS: Small contrast spheres can increase local absorbed dose by a factor of 13, but the corresponding increase in total energy absorbed was negligible (<1%). The highest localized dose increases were found to occur at incident photon energies of about 60 keV. For a concentration of about 10 mg/ml, typical of clinical practice, localized absorbed doses were generally increased by about a factor of two. At this concentration of 10 mg/ml, the maximum increase in total energy deposition in the phantom was only 6%. These simulations demonstrated that increases in contrast sphere doses were offset by corresponding dose reductions at distal and posterior locations. CONCLUSIONS: Adding iodine can result in values of localized absorbed dose increasing by more than an order of magnitude, but the total energy deposition is generally very modest (i.e., <10%). Their data show that adding iodine primarily changes the pattern of energy deposition in the irradiated region, rather than increasing patient doses per se.