Deep Learning-Based H-Score Quantification of Immunohistochemistry-Stained Images.

Immunohistochemistry (IHC) is a well-established and commonly used staining method for clinical diagnosis and biomedical research. In most IHC images, the target protein is conjugated with a specific antibody and stained using diaminobenzidine (DAB), resulting in a brown coloration, whereas hematoxylin serves as a blue counterstain for cell nuclei. The protein expression level is quantified through the H-score, calculated from DAB staining intensity within the target cell region. Traditionally, this process requires evaluation by 2 expert pathologists, which is both time consuming and subjective. To enhance the efficiency and accuracy of this process, we have developed an automatic algorithm for quantifying the H-score of IHC images. To characterize protein expression in specific cell regions, a deep learning model for region recognition was trained based on hematoxylin staining only, achieving pixel accuracy for each class ranging from 0.92 to 0.99. Within the desired area, the algorithm categorizes DAB intensity of each pixel as negative, weak, moderate, or strong staining and calculates the final H-score based on the percentage of each intensity category. Overall, this algorithm takes an IHC image as input and directly outputs the H-score within a few seconds, significantly enhancing the speed of IHC image analysis. This automated tool provides H-score quantification with precision and consistency comparable to experienced pathologists but at a significantly reduced cost during IHC diagnostic workups. It holds significant potential to advance biomedical research reliant on IHC staining for protein expression quantification.

Enhancing semantic segmentation in chest X-ray images through image preprocessing: ps-KDE for pixel-wise substitution by kernel density estimation.

BACKGROUND: In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and advance disease classification. Among established preprocessing techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving segmentation algorithms across various modalities, such as X-rays and CT. However, there remains a demand for improved contrast enhancement methods considering the heterogeneity of datasets and the various contrasts across different anatomic structures. METHOD: This study proposes a novel preprocessing technique, ps-KDE, to investigate its impact on deep learning algorithms to segment major organs in posterior-anterior chest X-rays. Ps-KDE augments image contrast by substituting pixel values based on their normalized frequency across all images. We evaluate our approach on a U-Net architecture with ResNet34 backbone pre-trained on ImageNet. Five separate models are trained to segment the heart, left lung, right lung, left clavicle, and right clavicle. RESULTS: The model trained to segment the left lung using ps-KDE achieved a Dice score of 0.780 (SD = 0.13), while that of trained on CLAHE achieved a Dice score of 0.717 (SD = 0.19), p<0.01. ps-KDE also appears to be more robust as CLAHE-based models misclassified right lungs in select test images for the left lung model. The algorithm for performing ps-KDE is available at https://github.com/wyc79/ps-KDE. DISCUSSION: Our results suggest that ps-KDE offers advantages over current preprocessing techniques when segmenting certain lung regions. This could be beneficial in subsequent analyses such as disease classification and risk stratification.

The effectiveness of time domain and nonlinear heart rate variability metrics in ultra-short time series.

Ultra short-term (UST) heart rate variability (HRV) has been used to establish normative HRV values. This study aims to investigate whether HRV metrics can capture changes in HRV from external stimuli, and whether these metrics remain effective under various recording length. Participants completed varying stimulating activities including viewing images, arithmetic tasks, and memory recall of viewed images. SDNN, RMSSD, pNN50, SD2, SD1/SD2, and DFA were extracted from the data. Comparing arithmetic calculation and the first minute of memory recall, SDNN, pNN50, SD2, and SD1/SD2 had significant HRV differences; this suggests that these metrics can distinguish the inherently different stimuli participants were exposed to. However, comparing first minute of viewing with that of the second, SDNN, pNN50, and SD2, presented some significant HRV differences during two inherently similar stimuli. Comparing the first 60-120 s during viewing, SDNN, pNN50, and SD2 also presented significant differences. Our results suggest that SDNN, pNN50, and SD2 may not be robust in evaluating UST HRVs in replacement of the standard short-term HRV. It may be beneficial to analyze multiple HRV metrics, particularly SD1/SD2, to achieve a more holistic understanding of the underlying physiology.

Unsupervised domain adaptation for nuclei segmentation: Adapting from hematoxylin & eosin stained slides to immunohistochemistry stained slides using a curriculum approach.

BACKGROUND AND OBJECTIVE: Unsupervised domain adaptation (UDA) is a powerful approach in tackling domain discrepancies and reducing the burden of laborious and error-prone pixel-level annotations for instance segmentation. However, the domain adaptation strategies utilized in previous instance segmentation models pool all the labeled/detected instances together to train the instance-level GAN discriminator, which neglects the differences among multiple instance categories. Such pooling prevents UDA instance segmentation models from learning categorical correspondence between source and target domains for accurate instance classification; METHODS: To tackle this challenge, we propose an Instance Segmentation CycleGAN (ISC-GAN) algorithm for UDA multiclass-instance segmentation. We conduct extensive experiments on the multiclass nuclei recognition task to transfer knowledge from hematoxylin and eosin to immunohistochemistry stained pathology images. Specifically, we fuse CycleGAN with Mask R-CNN to learn categorical correspondence with image-level domain adaptation and virtual supervision. Moreover, we utilize Curriculum Learning to separate the learning process into two steps: (1) learning segmentation only on labeled source data, and (2) learning target domain segmentation with paired virtual labels generated by ISC-GAN. The performance was further improved through experiments with other strategies, including Shared Weights, Knowledge Distillation, and Expanded Source Data. RESULTS: Comparing to the baseline model or the three UDA instance detection and segmentation models, ISC-GAN illustrates the state-of-the-art performance, with 39.1% average precision and 48.7% average recall. The source codes of ISC-GAN are available at https://github.com/sdw95927/InstanceSegmentation-CycleGAN. CONCLUSION: ISC-GAN adapted knowledge from hematoxylin and eosin to immunohistochemistry stained pathology images, suggesting the potential for reducing the need for large annotated pathological image datasets in deep learning and computer vision tasks.

Heart Rate Variability in Healthy Subjects During Monitored, Short-Term Stress Followed by 24-hour Cardiac Monitoring.

Heart Rate Variability (HRV) can be a useful metric to capture meaningful information about heart function. One of the non-linear indices used to analyze HRV, Detrended Fluctuation Analysis (DFA), finds short and long-term correlations in RR intervals to capture quantitative information about variability. This study focuses on the impact of visual and mental stimulation on HRV as expressed via DFA within healthy adults. Visual stimulation can activate the automatic nervous system to directly impact physiological behavior such as heart rate. In this investigation of HRV, 70 participants (21 males) viewed images on a screen followed by a math and recall task. Each viewing segment lasted 2 min and 18 s. The math and memory recall task segment lasted 4 min total. This process was repeated 9 times during which the participants' electrocardiogram was recorded. 37 participants (12 males) opted in for an additional 24-h Holter recording after the viewing and task segments of the study were complete. Participants were randomly assigned to either a pure (organized image presentation) or mixed (random image presentation) image regime for the viewing portion of the study to investigate the impact of the external environment on HRV. DFA α1 was extracted from the RR intervals. Our findings suggest that DFA α1 can differentiate between the viewing [DFA α1 range from 0.96 (SD = 0.25) to 1.08 (SD = 0.22)] and the task segments [DFA α1 range from 1.17 (SD = 0.21) to 1.26 (SD = 0.25)], p < 0.0006 for all comparisons. However, DFA α1 was not able to distinguish between the two image regimes. During the 24-hour follow up, participants had an average DFA α1 = 1.09 (SD = 0.14). In conclusion, our findings suggest a graded response in DFA during short term stimulation and a responsiveness in participants to adjust physiologically to their external environment expressed through the DFA exponent.