Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats.

Introduction: With the increasing prevalence of type 2 diabetes mellitus (T2DM), there is an urgent need to discover effective therapeutic targets for this complex condition. Coding and non-coding RNAs, with traditional biochemical parameters, have shown promise as viable targets for therapy. Machine learning (ML) techniques have emerged as powerful tools for predicting drug responses. Method: In this study, we developed an ML-based model to identify the most influential features for drug response in the treatment of type 2 diabetes using three medicinal plant-based drugs (Rosavin, Caffeic acid, and Isorhamnetin), and a probiotics drug (Z-biotic), at different doses. A hundred rats were randomly assigned to ten groups, including a normal group, a streptozotocin-induced diabetic group, and eight treated groups. Serum samples were collected for biochemical analysis, while liver tissues (L) and adipose tissues (A) underwent histopathological examination and molecular biomarker extraction using quantitative PCR. Utilizing five machine learning algorithms, we integrated 32 molecular features and 12 biochemical features to select the most predictive targets for each model and the combined model. Results and discussion: Our results indicated that high doses of the selected drugs effectively mitigated liver inflammation, reduced insulin resistance, and improved lipid profiles and renal function biomarkers. The machine learning model identified 13 molecular features, 10 biochemical features, and 20 combined features with an accuracy of 80% and AUC (0.894, 0.93, and 0.896), respectively. This study presents an ML model that accurately identifies effective therapeutic targets implicated in the molecular pathways associated with T2DM pathogenesis.

Emerging technology for intraoperative margin assessment and post-operative tissue diagnosis for breast-conserving surgery.

INTRODUCTION: Tissue-preserving surgery is utilized progressively in cancer therapy, where a clear surgical margin is critical to avoid cancer recurrence, specifically in breast cancer (BC) surgery. The Intraoperative pathologic approaches that rely on tissue segmenting and staining have been recognized as the ground truth for BC diagnosis. Nevertheless, these methods are constrained by its complication and timewasting for tissue preparation. OBJECTIVE: We present a non-invasive optical imaging system incorporating a hyperspectral (HS) camera to discriminate between cancerous and non-cancerous tissues in ex-vivo breast specimens, which could be an intraoperative diagnostic technique to aid surgeons during surgery and later a valuable tool to assist pathologists. METHODS: We have established a hyperspectral Imaging (HSI) system comprising a push-broom HS camera at wavelength 380∼1050 nm with source light 390∼980 nm. We have measured the investigated samples' diffuse reflectance (Rd), fixed on slides from 30 distinct patients incorporating mutually normal and ductal carcinoma tissue. The samples were divided into two groups, stained tissues during the surgery (control group) and unstained samples (test group), both captured with the HSI system in the visible and near-infrared (VIS-NIR) range. Then, to address the problem of the spectral nonuniformity of the illumination device and the influence of the dark current, the radiance data were normalized to yield the radiance of the specimen and neutralize the intensity effect to focus on the spectral reflectance shift for each tissue. The selection of the threshold window from the measured Rd is carried out by exploiting the statistical analysis by calculating each region's mean and standard deviation. Afterward, we selected the optimum spectral images from the HS data cube to apply a custom K-means algorithm and contour delineation to identify the regular districts from the BC regions. RESULTS: We noticed that the measured spectral Rd for the malignant tissues of the investigated case studies versus the reference source light varies regarding the cancer stage, as sometimes the Rd is higher for the tumor or vice versa for the normal tissue. Later, from the analysis of the whole samples, we found that the most appropriate wavelength for the BC tissues was 447 nm, which was highly reflected versus the normal tissue. However, the most convenient one for the normal tissue was at 545 nm with high reflection versus the BC tissue. Finally, we implement a moving average filter for noise reduction and a custom K-means clustering algorithm on the selected two spectral images (447, 551 nm) to identify the various regions and effectively-identified spectral tissue variations with a sensitivity of 98.95%, and specificity of 98.44%. A pathologist later confirmed these outcomes as the ground truth for the tissue sample investigations. CONCLUSIONS: The proposed system could help the surgeon and the pathologist identify the cancerous tissue margins from the non-cancerous tissue with a non-invasive, rapid, and minimum time method achieving high sensitivity up to 98.95%.

The influence of low- intensity laser irradiation versus hyperbaric oxygen therapy on transcutaneous oxygen tension in chronic diabetic foot ulcers: a controlled randomized trial.

BACKGROUND AND OBJECTIVE: Evaluation of the stage and severity of the chronic diabetic foot ulcer (CDFU) is vital to increase the healing rate and to select the suitable treatment. We aim to assess the influence of low-intensity laser irradiation (LILI) and hyperbaric oxygenation therapy (HBOT) to accelerate the CDFU healing thru the transcutaneous oxygen tension (TcPO2) measurements. MATERIALS AND METHODS: Seventy-five diabetic patients (type 2) of both genders, their ages ranged from 40-65 years with CDFUs (duration of ulcer < 6 weeks). All patients were randomly assigned into LILI, HBOT, and the control group. Measurement of TcPO2 using transcutaneous oximetry was performed for all patients once in the baseline and consequently in the second, fourth, and sixth- weeks duration. LILI utilized by a 33-diode cluster contact applicator with output power 1440 mW, energy density (fluency) was adjusted for 4 J/Cm2 at 10 kHz, and for 8 min per session, three times per week for a total of consecutive 6 weeks. HBOT was pressurized up to 2.5 ATA and patients delivered 100% oxygen for 60 min per session for 30 sessions. The Control group received conventional wound care only, twice daily, with saline and apply a new bandage after cleaning. RESULTS: MANOVA revealed a statistically insignificant difference in the control group, while statistically significant improvement in both the LILI and HBOT groups. The intergroup comparisons showed an insignificant statistical difference in the pre-test, while highly statistically significant differences for the three post-measures in favor of HBOT and LILI groups. The percentage of improvement of the HBOT group was higher than LILI. Post-hoc test using the least significant difference (LSD) revealed statistically significant differences of HBOT in favor of the LILI group. CONCLUSION: Both LILI and HBOT may be used as adjunctive methods to improve TcPO2 that accelerate healing in CDFUs. HBOT may be favorable in the improvement of TcPO2 than LILI.

Hyperspectral image-based analysis of thermal damage for ex-vivo bovine liver utilizing radiofrequency ablation.

BACKGROUND & OBJECTIVE: Thermal ablation is the predominant methodology to treat liver tumors for segregating patients who are not permitted to have surgical intervention. However, noticing or predicting the size of the thermal strategies is a challenging endeavor. We aim to analyze the effects of ablation district volume following radiofrequency ablation (RFA) of ex-vivo liver exploiting a custom Hyperspectral Imaging (HSI) system. MATERIALS AND METHODS: RFA was conducted on the ex-vivo bovine liver at focal and peripheral blood vessel sites and observed by Custom HSI system, which has been designed to assess the exactness and proficiency using visible and near-infrared wavelengths region for tissue thermal effect. The experiment comprised up to ten trials with RFA. The experiment was carried out in two stages to assess the percentage of the thermal effect on the investigated sample superficially and for the side penetration effect. Measuring the diffuse reflectance (Rd) of the sample to identify the spectral reflectance shift which could differentiate between normal and ablated tissue exploiting the designed cross-correlation algorithm for monitoring of thermal ablation. RESULTS: Determination of the diffuse reflection (Rd) spectral signature responses from normal, thermal effected, and thermal ablation regions of the investigated liver sample. Where the ideal wavelength range at (600-640 nm) could discriminate between these different regions. Then, exploited the converted RGB image of the HS liver tissue after RFA for more validations which shows that the optimum wavelength for differentiation at (530-560 nm and 600-640 nm). Finally, applying statistical analysis to validate our results presenting that wavelength 600 nm had the highest standard deviation (δ) to differentiate between various thermally affected regions regarding the normal tissue and wavelength 640 nm shows the highest (δ) to differentiate between the ablated and normal regions. CONCLUSION: The designed and implemented medical imaging system incorporated the hyperspectral camera capabilities with the associate cross-correlation algorithm that could successfully distinguish between the ablated and thermally affected regions to assist the surgery during the tumor therapy.

Integration of transcriptomes analysis with spectral signature of total RNA for generation of affordable remote sensing of Hepatocellular carcinoma in serum clinical specimens.

Hepatocellular carcinoma (HCC) is a major global health problem with about 841,000 new cases and 782,000 deaths annually, due to lacking early biomarker/s, and centralized diagnosis. Transcriptomes research despite its infancy has proved excellence in its implementation in identifying a coherent specific cancer RNAs differential expression. However, results are sometimes overlapped by other cancer types which negatively affecting specificity, plus the high cost of the equipment used. Hyperspectral imaging (HSI) is an advanced tool with unique, spectroscopic features, is an emerging tool that has widely been used in cancer detection. Herein, a pilot study has been performed for HCC diagnosis, by exploiting HIS properties and the analysis of the transcriptome for the development of non-invasive remote HCC sensing. HSI data cube images of the sera extracted total RNA have been analyzed in HCC, normal subject, liver benign tumor, and chronic HCV with cirrhotic/non-cirrhotic liver groups. Data analyses have revealed a specific spectral signature for all groups and can be easily discriminated; at the computed optimum wavelength. Moreover, we have developed a simple setup based on a commercial laser pointer for sample illumination and a Smartphone CCD camera, with HSI consistent data output. We hypothesized that RNA differential expression and its spatial organization/folding are the key players in the obtained spectral signatures. To the best of our knowledge, we are the first to use HSI for sensing cancer based on total RNA in serum, using a Smartphone CCD camera/laser pointer. The proposed biosensor is simple, rapid (2 min), and affordable with specificity and sensitivity of more than 98% and high accuracy.

Custom optical imaging system for ex-vivo breast cancer detection based on spectral signature.

BACKGROUND AND PURPOSE: Breast cancer is a popular well-known tumor in women globally and the subsequent driving reason for malignancy death. The purpose of the present study is to develop Low cost, commercial, and affordable system that discriminates malignant from normal breast tissues by exploiting the unique properties of Hyperspectral (HS) Imaging. MATERIALS AND METHODS: The difference in the optical properties of the investigated breast tissues gives various reactions to light transmission, absorption, and especially the reflection over the spectral range. A custom optical imaging system (COIS) was designed to assess variable responses to monochromatic LEDs (415, 565, 660 nm) to highlight the differences in the reflectance properties of malignant/normal tissue. Statistical analysis was computed for determining the ideal wavelength to differentiate between normal and malignant regions. The experiment was repeated using the same LEDs, and low-cost CCD camera to examine the capability of such a system to discriminate between normal and malignant tissue. RESULTS: Spectral images obtained by Hyperspectral camera, have been analyzed to reveal the difference of reflectance malignant and normal breast tissue. Superficial spectral reflection image with blue LED (415 nm) showed high variance (10.11). However, a more-depth reflection image with red LED (660 nm) showed low variance (4.44). So the optimum contrast image was produced by combining the three spectral information images from blue, green, and red LED. The COIS using a commercial CCD camera was in agreement with the HS camera. CONCLUSIONS: The novel COIS of the commercial Low-cost CCD Camera is reliable and can be used with endoscopy technique as an assistant tool for surgical doctor to make decision and assess the resection edges in real time during surgery.

Hyperspectral imaging for diagnosis and detection of ex-vivo breast cancer.

BACKGROUND AND PURPOSE: Breast cancer is one of the most widely recognized tumors. .Diagnosis made in the early stage of disease may imporve outcomes. The discovery of malignant growth utilizing noninvasive light intrusive methods in lieu of conventional excisional biopsy may assist in achieving this goal. MATERIALS AND METHODS: The change of the optical properties of ex-vivo breast tissues provides different responses to light transmission, absorption, and particularly the reflection over the spectrum range. We offer the use of Hyperspectral imaging (HSI) with advanced image processing and pattern recognition in order to analyze HSI data for breast cancer detection. The spectral signatures were mined and evaluated in both malignant and normal tissue. K-mean clustering was designed for classifying hyperspectral data in order to evaluate and detection of cancer tissue. This method was used to detect ex-vivo breast cancer. Spatial spectral images were created to high spot the differences in the reflectance properties of malignant versus normal tissue. RESULTS: Trials showed that the superficial spectral reflection images within 500 nm wavelength showed high variance (214.65) between cancerous and normal breast tissues. On the other hand, image within 620 nm wavelength showed low variance (0.0020).However, the superimposed of spectral region 420-620 nm was proposed as the optimum bandwidth. Finally, the proposed HS imaging system was capable to discriminate the tumor region from normal tissue of the ex-vivo breast sample with sensitivity and a specificity of 95 % and 96 %. CONCLUSIONS: High sensitivity and specificity were achieved, which proposes potential for HSI as an edge evaluation method to enhance the surgical outcome compared to the presently available techniques in the clinics.

Tissue characterization utilizing hyperspectral imaging for liver thermal ablation.

BACKGROUND: Thermal ablation is the dominant modality to treat liver tumors for patients who are not surgical candidates. . However, correctly predicting the volume of the subsequent tissue destruction during the Thermal Ablation technique is a difficult undertaking. OBJECTIVE: To examine the impacts of ablation zone volume following Radiofrequency ablation (RFA) of an ex-vivo bovine liver to correlate the impacts of thermal ablation with target organ perfusion; by exploiting the unique properties of Hyperspectral Imaging (HSI). MATERIALS AND METHODS: Radiofrequency ablation was perfused on ex-vivo bovine livers at peripheral and central­vessel­adjacent locations, and monitored by HSI with a spectral range from 400 to 1000 nm. The system contains k-means clustering (K = 8) algorithms combining spectral and spatial information. Labeled spectral signatures datasets were used as training data. Statistical analysis (10 samples) was computed to calculate the highest variance between six spectral images for determining the optimum wavelength for discrimination between the affected regions after thermal ablation (normal, thermal, and ablated liver tissue regions). RESULTS: The change of the optical properties ofex-vivo liver tissues provides different responses to light transmission, scattering, absorption and particularly the reflection over the spectrum range. The produced spectral image from reflection with the highest variance (358.07) empowered us to determine the optimum wavelength spectral image (720 ±â€¯18.92 nm) to distinguish between the normal, ablated, and thermal categories. CONCLUSION: Hyperspectral imaging is a powerful tool in monitoring tissue characterization, which is a useful technique for edge evaluation of liver thermal ablation ..