Detection of cancer using advanced computerized analysis of infrared spectra of peripheral blood

Monitoring the efficacy of antibiotic therapy in febrile pediatric oncology patients with bacteremia using infrared spectroscopy of white blood cells-based machine learning

Bacteremia refers to the presence of bacteria in the bloodstream, which can lead to a serious and potentially life-threatening condition. In oncology patients, individuals undergoing cancer treatment have a higher risk of developing bacteremia due to a weakened immune system resulting from the disease itself or the treatments they receive. Prompt and accurate detection of bacterial infections and monitoring the effectiveness of antibiotic therapy are essential for enhancing patient outcomes and preventing the development and dissemination of multidrug-resistant bacteria. Traditional methods of infection monitoring, such as blood cultures and clinical observations, are time-consuming, labor-intensive, and often subject to limitations. This manuscript presents an innovative application of infrared spectroscopy of leucocytes of pediatric oncology patients with bacteremia combined with machine learning to diagnose the etiology of infection as bacterial and simultaneously monitor the efficacy of the antibiotic therapy in febrile pediatric oncology patients with bacteremia infections. Through the implementation of effective monitoring, it becomes possible to promptly identify any indications of treatment failure. This, in turn, indirectly serves to limit the progression of antibiotic resistance. The logistic regression (LR) classifier was able to differentiate the samples as bacterial or control within an hour, after receiving the blood samples with a success rate of over 95 %. Additionally, initial findings indicate that employing infrared spectroscopy of white blood cells (WBCs) along with machine learning is viable for monitoring the success of antibiotic therapy. Our follow up results demonstrate an accuracy of 87.5 % in assessing the effectiveness of the antibiotic treatment.

NIR spectroscopy combined with 1D-convolutional neural network for breast cancerization analysis and diagnosis

Near-infrared (NIR) spectroscopy with deep penetration can characterize the composition of biological tissue based on the vibration of the X-H group in a rapid and high-specificity way. Deep learning is proven helpful for rapid and automatic identification of tissue cancerization. In this study, NIR spectroscopic detection equipped with the lab-made NIR probe was performed to in situ explore the change of molecular compositions in breast cancerization, where the diffused NIR spectra were efficiently collected at different locations of cancerous and paracancerous areas. The breast cancerous-paracancerous discriminant model was established based on one-dimensional convolutional neural network (1D-CNN). By optimizing the structure of the neural network, the high classification accuracy (94.67%), recall/sensitivity (95.33%), specificity (94.00%), precision (94.08%) and F1 score (0.9470) were achieved, showing the better discrimination ability and reliability than the K-Nearest Neighbor (KNN, 88.34%, 98.21%, 76.11%, 83.59%, 0.9031) and Fisher Discriminant Analysis (FDA, 90.00%, 96.43%, 81.82%, 87.10%, 0.9153) methods. The experimental results indicate that the application of 1D-CNN can discriminate the cancerous and paracancerous breast tissues, and provide an intelligent method for clinical locating, diagnosis and treatment of breast cancer.

Radiomic analysis on magnetic resonance diffusion weighted image in distinguishing triple-negative breast cancer from other subtypes: a feasibility study

PURPOSE

This work aimed to explore whether radiomic features on magnetic resonance diffusion weighted image (MR DWI) can be used to identify triple-negative breast cancer (TNBC) and other subtypes (non-TNBC).

MATERIALS AND METHODS

This retrospective study included 221 unilateral patients who underwent breast MR imaging prior to neoadjuvant chemotherapy. The subtypes of breast cancer include luminal A (n = 63), luminal B (n = 103), human epidermal growth factor receptor-2 (HER2) overexpressing (n = 30), and triple negative (n = 25). Radiomic features were extracted using Omini-Kinetic software on DWI. Student's t-test and Mann-Whitney U test were used to compare the features between TNBC and non-TNBC patients. Logistic regression analysis and receiver operating characteristic (ROC) curve were used to evaluate the diagnostic efficiency of radiomic features. The Fisher discriminant model was employed to distinguish TNBC and non-TNBC patients automatically. An additional validation dataset with 169 patients was utilized to validate the model.

RESULTS

A total of 76 imaging features were extracted from each lesion on DWI images, and 12 radiomic features were statistically significant between TNBC and non-TNBC patients (P < 0.05). The area of receiver operating characteristic curve (AUC) was 0.817 to apply logistic regression analysis. The accuracy of Fisher discriminant model in distinguishing TNBC and non-TNBC patients was 95.4%, and leave-one-out cross validation was achieved with an accuracy of 83.7%. The same classification analysis of the validation dataset showed an accuracy of 83.4% and an AUC of 0.804.

CONCLUSION

Breast lesions exhibit differences in radiomic features from DWI, enabling good discrimination between TNBC and non-TNBC tumors.

Diagnosis of inaccessible infections using infrared microscopy of white blood cells and machine learning algorithms

Physicians diagnose subjectively the etiology of inaccessible infections where sampling is not feasible (such as, pneumonia, sinusitis, cholecystitis, peritonitis), as bacterial or viral. The diagnosis is based on their experience with some medical markers like blood counts and medical symptoms since it is harder to obtain swabs and reliable laboratory results for most cases. In this study, infrared spectroscopy with machine learning algorithms was used for the rapid and objective diagnosis of the etiology of inaccessible infections and enables an assessment of the error for the subjective diagnosis of the etiology of these infections by physicians. Our approach allows for diagnoses of the etiology of both accessible and inaccessible infections as based on an analysis of the innate immune system response through infrared spectroscopy measurements of white blood cell (WBC) samples. In the present study, we examined 343 individuals involving 113 controls, 89 inaccessible bacterial infections, 54 accessible bacterial infections, 60 inaccessible viral infections, and 27 accessible viral infections. Using our approach, the results show that it is possible to differentiate between controls and infections (combined bacterial and viral) with 95% accuracy, and enabling the diagnosis of the etiology of accessible infections as bacterial or viral with >94% sensitivity and > 90% specificity within one hour after the collection of the blood sample with error rate <6%. Based on our approach, the error rate of the physicians' subjective diagnosis of the etiology of inaccessible infections was found to be >23%.

Protein Conformational Changes in Breast Cancer Sera Using Infrared Spectroscopic Analysis

Protein structural alterations, including misfolding and aggregation, are a hallmark of several diseases, including cancer. However, the possible clinical application of protein conformational analysis using infrared spectroscopy to detect cancer-associated structural changes in proteins has not been established yet. The present study investigates the applicability of Fourier transform infrared spectroscopy in distinguishing the sera of healthy individuals and breast cancer patients. The cancer-associated alterations in the protein structure were analyzed by fitting the amide I (1600-1700 cm-1) band of experimental curves, as well as by comparing the ratio of the absorbance values at the amide II and amide III bands, assigning those as the infrared spectral signatures. The snapshot of the breast cancer-associated alteration in circulating DNA and RNA was also evaluated by extending the spectral fitting protocol to the complex region of carbohydrates and nucleic acids, 1140-1000 cm-1. The sensitivity and specificity of these signatures, representing the ratio of the α-helix and β-pleated sheet in proteins, were both 90%. Likewise, the ratio of amides II and amide III (I1556/I1295) had a sensitivity and specificity of 100% and 80%, respectively. Thus, infrared spectroscopy can serve as a powerful tool to understand the protein structural alterations besides distinguishing breast cancer and healthy serum samples.

Rapid diagnosis of infection etiology in febrile pediatric oncology patients using infrared spectroscopy of leukocytes

Rapid diagnosis of the etiology of infection is highly important for an effective treatment of the infected patients. Bacterial and viral infections are serious diseases that can cause death in many cases. The human immune system deals with many viral and bacterial infections that cause no symptoms and pass quietly without treatment. However, oncology patients undergoing chemotherapy have a very weak immune system caused by leukopenia, and even minor pathogen infection threatens their lives. For this reason, physicians tend to prescribe immediately several types of antibiotics for febrile pediatric oncology patients (FPOPs). Uncontrolled use of antibiotics is one of the major contributors to the development of resistant bacteria. Therefore, for oncology patients, a rapid and objective diagnosis of the etiology of the infection is extremely critical. Current identification methods are time-consuming (>24 h). In this study, the potential of midinfrared spectroscopy in tandem with machine learning algorithms is evaluated for rapid and objective diagnosis of the etiology of infections in FPOPs using simple peripheral blood samples. Our results show that infrared spectroscopy enables the diagnosis of the etiology of infection as bacterial or viral within 70 minutes after the collection of the blood sample with 93% sensitivity and 88% specificity.

FTIR bio-spectroscopy scattering correction using natural biological characteristics of different cell lines

Fourier transform infrared (FTIR) spectroscopy is a well-known method of analysis, with various applications, including promising potential for analyzing biological samples. In the bio-spectroscopy of cells, Mie scattering may increase, which then causes spectral distortion, due to the similarity of cell size with the IR medium-wavelength. These changes make the spectrum unreliable. In previous scattering elimination studies, questionable estimations were considered. For instance, all cells were considered as spherical objects or cell size was estimated randomly. In an attempt to provide the best equation based on the natural existence of cells for the FTIR Mie scattering correction, we examined the actual biological data of cells - as opposed to those yielded from mathematical manipulations. So five biological factors: cell size, shape, granularity, circularity, and edge irregularities, for each cell line were considered as factors which cause scattering. For measuring cell size, roundness and edge irregularity, microscopy images were obtained and processed. For evaluating cell line granularity, flow cytometry was used. Finally, by including these factors, an algorithm was designed. To assess the accuracy of the proposed algorithm, the trypsinized cell spectrum was considered as the high scattering spectrum. Cells were also cultured on a MirrIR slide, and their ATR-FTIR spectrum was considered as the minimum scattering spectrum. The algorithm using the abovementioned five characteristics was used for 13 different cell lines, and in some cases the corrected spectrum demonstrated more than 97% resemblance with the ATR spectra of the same cells. A comparison between the results of this algorithm with the Bassan et al. (2017) algorithm for scattering correction that is freely available on the Internet was then conducted on two different cell lines, clearly showing the advantages of our algorithm, in terms of accuracy and precision. Therefore, this method can be viewed as a more suitable solution for scattering correction in cell investigations.

Vibrational Spectroscopy Fingerprinting in Medicine: from Molecular to Clinical Practice

In the last two decades, Fourier Transform Infrared (FTIR) and Raman spectroscopies turn out to be valuable tools, capable of providing fingerprint-type information on the composition and structural conformation of specific molecular species. Vibrational spectroscopy's multiple features, namely highly sensitive to changes at the molecular level, noninvasive, nondestructive, reagent-free, and waste-free analysis, illustrate the potential in biomedical field. In light of this, the current work features recent data and major trends in spectroscopic analyses going from in vivo measurements up to ex vivo extracted and processed materials. The ability to offer insights into the structural variations underpinning pathogenesis of diseases could provide a platform for disease diagnosis and therapy effectiveness evaluation as a future standard clinical tool.

Preliminary Study on Molecular Subtypes of Breast Cancer Based on Magnetic Resonance Imaging Texture Analysis

OBJECTIVE

The aim of the study was to investigate the molecular subtypes of breast cancer based on the texture features derived from magnetic resonance images (MRIs).

METHODS

One hundred seven patients with preoperative confirmed breast cancer were recruited. One hundred eight breast lesions were divided into 4 subtypes according to the status of estrogen receptor, progesterone receptor, human epidermal growth factor receptor type 2, and Ki67. Fisher discriminant analysis was performed on the texture features that extracted from the enhanced high-resolution T1-weighted images and diffusion weighted images to establish the classification model of molecular subtypes.

RESULTS

The differentiation accuracies of Fisher discriminant analysis on the enhanced high-resolution T1-weighted images were 82.8% and 86.4% for 1.5T and 3.0T imaging. Fisher discriminant analysis on diffusion weighted imaging texture features were achieved with a classification ability of 73.4% and 88.6%. The combined discriminant results for 2 kinds magnetic resonance images were 95.0%, 97.7% in 1.5T and 3.0T imaging, respectively.

CONCLUSIONS

The fine results indicated a promising approach to predict the molecular subtypes of breast cancer.

Texture features and pharmacokinetic parameters in differentiating benign and malignant breast lesions by dynamic contrast enhanced magnetic resonance imaging

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) has become a powerful tool for the diagnosis of breast cancer in the clinical setting due to its high sensitivity and specificity. Pharmacokinetic parameters, including Ktrans and area under the curve (AUC), and texture features derived from DCE-MRI have been used to specify the characteristics inside tumors. In the present study, 56 patients (average age 45.3±11.1; range 25-69 years) with histopathologically proved breast tumors were analyzed using the pharmacokinetic parameters and texture features. Malignant tumors displayed higher Ktrans and AUC values than the benign, Ktrans exhibited a significantly difference between the malignant and benign tumors (P=0.001) compared with the AUC values (P=0.029); texture features from DCE-MRI images and pharmacokinetic parameter maps also showed a good diagnostic ability. Alongside the routine method, principal components analysis (PCA) and Fisher discriminant analysis (FDA) were employed on these texture features to differentiate the breast lesions automatically. The Factor-1 scores of PCA were used to divide the patients into two groups, and the diagnosing accuracies of the FDA method on the texture features from DCE-MRI images, Ktrans maps, AUC maps were 93, 98 and 98%, with a cross validation accuracies of 82, 77 and 77%, respectively. To conclude, pharmacokinetic parameters, texture features and the combined computer-assisted classification method were discussed. All method involved in this study may be a potential assisted tool for radiological analysis on breast.

Differential Diagnosis of the Etiologies of Bacterial and Viral Infections Using Infrared Microscopy of Peripheral Human Blood Samples and Multivariate Analysis

Human viral and bacterial infections are responsible for a variety of diseases that are still the main causes of death and economic burden for society across the globe. Despite the different responses of the immune system to these infections, some of them have similar symptoms, such as fever, sneezing, inflammation, vomiting, diarrhea, and fatigue. Thus, physicians usually encounter difficulties in distinguishing between viral and bacterial infections on the basis of these symptoms. Rapid identification of the etiology of infection is highly important for effective treatment and can save lives in some cases. The current methods used for the identification of the nature of the infection are mainly based on growing the infective agent in culture, which is a time-consuming (over 24 h) and usually expensive process. The main objective of this study was to evaluate the potential of the mid-infrared spectroscopic method for rapid and reliable identification of bacterial and viral infections based on simple peripheral blood samples. For this purpose, white blood cells (WBCs) and plasma were isolated from the peripheral blood samples of patients with confirmed viral or bacterial infections. The obtained spectra were analyzed by multivariate analysis: principle component analysis (PCA) followed by linear discriminant analysis (LDA), to identify the infectious agent type as bacterial or viral in a time span of about 1 h after the collection of the blood sample. Our preliminary results showed that it is possible to determine the infectious agent with high success rates of 82% for sensitivity and 80% for specificity, based on the WBC data.

Vibrational Spectroscopy in Body Fluids Analysis

Vibrational spectroscopy offers a unique opportunity to investigate the composition of unknown substances on a molecular basis. The spectroscopy of molecular vibrations using mid-infrared or Raman techniques has been applied to samples of body fluids. This review presents some applications related to body fluids published in the period 2005-2015.

Infrared spectrum blind deconvolution algorithm via learned dictionaries and sparse representation

Band overlap and random noise are a serious problem in infrared spectra, especially for aging spectrometers. In this paper, we have presented a simple method for spectrum restoration. The proposed method is based on local operations, and involves sparse decompositions of each spectrum piece under an evolving overcomplete dictionary, and a simple averaging calculation. The content of the dictionary is of prime importance for the deconvolution process. Quantitative assessments of this technique on simulated and real spectra show significant improvements over the state-of-the-art methods. The proposed method can almost eliminate the effects of instrument aging. The features of these deconvoluted infrared spectra are more easily extracted, aiding the interpretation of unknown chemical mixtures.

A novel method for screening colorectal cancer by infrared spectroscopy of peripheral blood mononuclear cells and plasma

BACKGROUND

Early detection of colorectal cancer (CRC) can reduce mortality and morbidity. Current screening methods include colonoscopy and stool tests, but a simple low-cost blood test would increase compliance. This preliminary study assessed the utility of analyzing the entire bio-molecular profile of peripheral blood mononuclear cells (PBMCs) and plasma using Fourier transform infrared (FTIR) spectroscopy for early detection of CRC.

METHODS

Blood samples were prospectively collected from 62 candidates for CRC screening/diagnostic colonoscopy or surgery for colonic neoplasia. PBMCs and plasma were separated by Ficoll gradient, dried on zinc selenide slides, and placed under a FTIR microscope. FTIR spectra were analyzed for biomarkers and classified by principal component and discriminant analyses. Findings were compared among diagnostic groups.

RESULTS

Significant changes in multiple bands that can serve as CRC biomarkers were observed in PBMCs (p = ~0.01) and plasma (p = ~0.0001) spectra. There were minor but statistically significant differences in both blood components between healthy individuals and patients with benign polyps. Following multivariate analysis, the healthy individuals could be well distinguished from patients with CRC, and the patients with benign polyps were mostly distributed as a distinct subgroup within the overlap region. Leave-one-out cross-validation for evaluating method performance yielded an area under the receiver operating characteristics curve of 0.77, with sensitivity 81.5% and specificity 71.4%.

CONCLUSIONS

Joint analysis of the biochemical profile of two blood components rather than a single biomarker is a promising strategy for early detection of CRC. Additional studies are required to validate our preliminary clinical results.

Discrimination of healthy and osteoarthritic articular cartilage by Fourier transform infrared imaging and Fisher's discriminant analysis

Fourier transform infrared spectroscopic imaging (FTIRI) technique can be used to obtain the quantitative information of content and spatial distribution of principal components in cartilage by combining with chemometrics methods. In this study, FTIRI combining with principal component analysis (PCA) and Fisher's discriminant analysis (FDA) was applied to identify the healthy and osteoarthritic (OA) articular cartilage samples. Ten 10-μm thick sections of canine cartilages were imaged at 6.25μm/pixel in FTIRI. The infrared spectra extracted from the FTIR images were imported into SPSS software for PCA and FDA. Based on the PCA result of 2 principal components, the healthy and OA cartilage samples were effectively discriminated by the FDA with high accuracy of 94% for the initial samples (training set) and cross validation, as well as 86.67% for the prediction group. The study showed that cartilage degeneration became gradually weak with the increase of the depth. FTIRI combined with chemometrics may become an effective method for distinguishing healthy and OA cartilages in future.

Early detection of breast cancer using total biochemical analysis of peripheral blood components: a preliminary study

Background

Most of the blood tests aiming for breast cancer screening rely on quantification of a single or few biomarkers. The aim of this study was to evaluate the feasibility of detecting breast cancer by analyzing the total biochemical composition of plasma as well as peripheral blood mononuclear cells (PBMCs) using infrared spectroscopy.

Methods

Blood was collected from 29 patients with confirmed breast cancer and 30 controls with benign or no breast tumors, undergoing screening for breast cancer. PBMCs and plasma were isolated and dried on a zinc selenide slide and measured under a Fourier transform infrared (FTIR) microscope to obtain their infrared absorption spectra. Differences in the spectra of PBMCs and plasma between the groups were analyzed as well as the specific influence of the relevant pathological characteristics of the cancer patients.

Results

Several bands in the FTIR spectra of both blood components significantly distinguished patients with and without cancer. Employing feature extraction with quadratic discriminant analysis, a sensitivity of ~90 % and a specificity of ~80 % for breast cancer detection was achieved. These results were confirmed by Monte Carlo cross-validation. Further analysis of the cancer group revealed an influence of several clinical parameters, such as the involvement of lymph nodes, on the infrared spectra, with each blood component affected by different parameters.

Conclusion

The present preliminary study suggests that FTIR spectroscopy of PBMCs and plasma is a potentially feasible and efficient tool for the early detection of breast neoplasms. An important application of our study is the distinction between benign lesions (considered as part of the non-cancer group) and malignant tumors thus reducing false positive results at screening. Furthermore, the correlation of specific spectral changes with clinical parameters of cancer patients indicates for possible contribution to diagnosis and prognosis.