Pavel Lazarev

Background/Objectives: Establishing biomarkers is crucial for early cancer detection. Structural biomarkers can be revealed by noninvasive X-ray diffraction. We applied this approach to human nails and observed structural changes in the major nail tissue component, keratin, which coincided with a cancer diagnosis. Methods: X-ray diffraction patterns were obtained from 230 nail samples (control/cancer split: 92/138) belonging to 133 patients (48/85) in wide (WAXS) and small (SAXS) ranges of scattering angles. For both ranges, we obtained one-dimensional scattering profiles in meridional and equatorial directions. We examined these profiles using machine-learning techniques such as logistic regression and linear discriminant analysis. Results: We obtained good classification metrics that allow us to distinguish participants with cancer from controls. The results are similar for both machine-learning methods. Combining all four profiles (WAXS meridional, WAXS equatorial, SAXS meridional, and SAXS equatorial) produced a sensitivity of 0.753 and a specificity of 0.771 for the Linear Discriminant Analysis at the Youden point. For the limited set of patients of the same age, we showed that the patterns can still be distinguished, supporting our hypothesis that the observed aberrations are cancer-induced. Conclusions: Our exploratory research demonstrated the feasibility of cancer detection using the X-ray diffraction of human nails.

Background/Objectives: Establishing biomarkers is crucial for early cancer detection. Structural biomarkers can be revealed by noninvasive X-ray diffraction. We applied this approach to human nails and observed cancer-induced structural changes in the major nail tissue component, keratin. Methods: X-ray diffraction patterns were obtained from 230 nail samples (control/cancer split: 92/138) belonging to 133 patients (48/85) in wide (WAXS) and small (SAXS) ranges of scattering angles. For both ranges, we obtained one-dimensional scattering profiles in meridional and equatorial directions. We examined these profiles using machine-learning techniques such as logistic regression and linear discriminant analysis. Results: We obtained significant classification metrics that allow us to distinguish healthy and cancerous patients. The results are similar for both machine-learning methods. Combining all four profiles (WAXS meridional, WAXS equatorial, SAXS meridional, and SAXS equatorial) produced a sensitivity of 0.753 and a specificity of 0.771. For the limited set of patients of the same age, we showed that the patterns can still be distinguished, supporting our hypothesis that the observed aberrations are cancer-induced. Conclusions: We showed that cancer detection can be achieved by means of X-ray diffraction of human nails.

Background/Objectives: Machine learning approaches are widely used in modern medical diagnostics, including cancer detection. The results can be significantly improved by aggregating individual measurements, and appropriate aggregation methods should be established. Methods: We applied various measurement aggregation strategies both before and after machine learning modeling to two datasets of X-ray diffraction images: human breast biopsy samples and canine claw samples. Two classifiers, Random Forest and Logistic Regression, were used to determine classification metrics: the area under the receiver operating characteristic curve (ROC-AUC) and balanced accuracy. Results: We found that all aggregation types improve classification metrics, with aggregation after modeling yielding better performance. Depending on the dataset and approach, either classifier can produce better results. For human breast samples, Random Forest with the logit aggregation strategy provides an ROC-AUC exceeding 0.9. For the canine dataset, both Random Forest with the logit aggregation strategy and Logistic Regression with the median of cancer probabilities achieve an ROC-AUC of about 0.85. Conclusions: We examined several simple, straightforward aggregation methods for patient diagnosis based on multiple measurements per patient and achieved significant improvements in classification metrics.

Structural biomarkers determined by X-ray scattering of the tissues can complement conventional histopathology and facilitate a fast triage procedure of cancer biopsy samples. It has been shown previously that lipid reflexes can distinguish cancerous from benign samples, except for fibroadenomas. In the present study, we demonstrate that fibroadenoma samples can be recognized using X-ray scattering of collagen. Moreover, we show that modifications in collagen structure are manifested in the water reflexes. Examination of diffraction patterns from water using two-dimensional Fourier transformation and machine learning yields excellent classification metrics in both synchrotron images and laboratory diffractometer data.

Structural biomarkers determined by X-ray scattering of the tissues can complement conventional histopathology and facilitate a fast triage procedure of cancer biopsy samples. It has been shown previously that lipid reflexes can distinguish cancerous from benign samples, except for fibroadenomas. In the present study, we demonstrate that fibroadenoma samples can be recognized using X-ray scattering of collagen. Moreover, we show that modifications in collagen structure are manifested in the water reflexes. Examination of diffraction patterns from water using two-dimensional Fourier transformation and machine learning yields excellent classification metrics in both synchrotron images and laboratory diffractometer data.

Structural biomarkers determined by X-ray scattering of the tissues can complement conventional diagnostics and provide a pathway for early detection of diseases. In the present study, mouse models were utilized to observe the progression of prostate cancer. We induced cancer in the left lobe of the mouse prostate, whilst the right lobe was left uninoculated. The mice were sacrificed at increasing systematic time points, and lobe samples were subsequently analyzed using X-ray scattering. Control samples were also collected from healthy mice sacrificed at the same time points. This investigation revealed that the ratio between the X-ray scattering peaks associated with the lipids and water can serve as a structural biomarker of cancer, and this biomarker develops as the tumor advances. The obtained cancer trajectory can serve as a baseline for the determination of the disease stage, and the biomarker movement along the trajectory can be evidence of the healing or disease progression.

Background/Objectives: With the number of detected breast cancer cases growing every year, there is a need to augment histopathological analysis with fast preliminary screening. We examine the feasibility of using X-ray diffraction measurements for this purpose. Methods: In this work, we obtained more than 6000 diffraction patterns from 211 patients and examined both standard and custom-developed methods, including Fourier coefficient analysis, for their interpretation. Various preprocessing steps and machine learning classifiers were compared to determine the optimal combination. Results: We demonstrated that benign and cancerous clusters are well separated, with specificity and sensitivity exceeding 0.9. For wide-angle scattering, the two-dimensional Fourier method is superior, while for small angles, the conventional analysis based on azimuthal integration of the images provides similar metrics. Conclusions: X-ray diffraction of biopsy tissues, supported by machine learning approaches to data analytics, can be an essential tool for pathological services. The method is rapid and inexpensive, providing excellent metrics for benign/cancer classification.

Background/Objectives: With the number of detected breast cancer cases growing every year, there is a need to augment histopathological analysis with fast preliminary screening. We examine the feasibility of using X-ray diffraction measurements for this purpose; Methods: In this work, we obtained more than 6,000 diffraction patterns from 211 patients and examined both standard and custom-developed methods, including Fourier coefficient analysis, for their interpretation. Various preprocessing steps and machine-learning classifiers were compared to determine the optimal combination; Results: We demonstrated that benign and cancerous clusters are well-separated, with specificity and sensitivity exceeding 0.9. For wide-angle scattering, the two-dimensional Fourier method is superior, while for small angles, the conventional analysis based on azimuthal integration of the images provides similar metrics; Conclusions: X-ray diffraction of biopsy tissues, supported by machine-learning approaches to data analytics, can be an essential tool for pathological services. The method is rapid and inexpensive, providing excellent metrics for benign/cancer classification.

With the growing number of cancer cases and deaths around the world, fast, non-invasive, and inexpensive screening is paramount. We examine the feasibility of such cancer detection using the X-ray scattering properties of nails in the canine model. A total of 945 samples taken from 266 dogs were measured, with 84 animals diagnosed with cancer. To analyze the obtained X-ray diffraction patterns of keratin, we propose a method based on the two-dimensional Fourier transformation of the images. We compare 745 combinations of data preprocessing steps and machine learning classifiers and determine the corresponding performance metrics. Excellent classification results are demonstrated, with sensitivity or specificity achieving 100% and the best value for balanced accuracy being 87.5%. We believe that our approach can be extended to human samples to develop a non-invasive, convenient, and cheap method for early cancer detection.

As the number of cancer cases and deaths growing around the world, fast, non-invasive, and inexpensive screening is paramount. We examine the feasibility of such cancer detection using the X-ray scattering properties of nails in the canine model. 945 samples taken from 266 dogs were measured, with 84 animals diagnosed with cancer. To analyze the obtained X-ray diffraction patterns of keratin, we propose a method based on the two-dimensional Fourier transformation of the images. We compare 745 combinations of data preprocessing steps and machine learning classifiers and determine corresponding performance metrics. Excellent classification results are demonstrated, with sensitivity or specificity achieving 100% and the best value for balanced accuracy being 87.5%. We believe that our approach can be extended to human samples to develop a non-invasive, convenient, and cheap method for early cancer detection.