Early screening of cervical cancer based on tissue Raman spectroscopy combined with deep learning algorithms

An improved cancer diagnosis algorithm for protein mass spectrometry based on PCA and a one-dimensional neural network combining ResNet and SENet

Cancer is one of the most serious health problems worldwide. Because cancer has no specific symptoms in its early stages, it is often not diagnosed until it is in advanced stages, reducing the likelihood of successful treatment. Therefore, early diagnosis of cancer is a formidable challenge. Mass spectrometry-based proteomics offers a robust technical foundation for cancer diagnosis. However, mass spectrometry data are characterized by high dimensionality, large data volume, and noise interference, which can lead to diagnostic errors in clinical applications. To address this challenge, an improved algorithm combining principal component analysis (PCA) with a convolutional neural network (CNN) algorithm (denoted as PCA-1DSE-ResCNN) was proposed to assist in analyzing high-dimensional mass spectral data. The algorithm initially reduced the dimensionality of the data through the PCA technique. Subsequently, the convolutional neural network algorithm (1DSE-ResCNN) integrating residual blocks and squeeze-and-excitation blocks was used as a classifier. This approach can not only alleviate the issues of overfitting and gradient vanishing caused by deep network layers but also reduce redundant information, enabling the algorithm to effectively learn high-dimensional data features and deal with nonlinear relationships. To validate the effectiveness of the algorithm, the high-dimensional ovarian cancer mass spectrometry dataset was selected as an example to examine its application performance in early diagnosis of ovarian cancer. The experimental results demonstrated that the PCA-1DSE-ResCNN algorithm outperforms other methods in terms of accuracy, specificity, and sensitivity on three high-dimensional ovarian cancer datasets. This study will contribute to the rapid diagnosis and early detection of cancer.

Cervical cancer diagnosis model using spontaneous Raman and Coherent anti-Stokes Raman spectroscopy with artificial intelligence

Cervical cancer is the fourth most common cancer worldwide. Histopathology, which is currently considered the gold standard for cervical cancer diagnosis, can be time-consuming and subjective. Therefore, there is an urgent need for a rapid, objective, and non-destructive cervical cancer detection technique. In this study, high-wavenumber spontaneous Raman spectroscopy was used to detect cervical squamous cell carcinoma and normal tissues. The levels of lipids, fatty acids, and proteins in cervical cancerous tissues were found to be higher than those in normal tissues. Raman difference spectroscopy revealed the most significant difference at 2928 cm-1. Additionally, a Coherent anti-Stokes Raman spectroscopy (CARS) instrument was employed to enhance the wavenumber signal intensity and sensitivity. The intrinsic relationship between CARS imaging and cervical lesions was established. The CARS images indicated that the intensity of normal cervical squamous cells was zero, whereas the intensities of keratinized and non-keratinized cervical squamous cell carcinoma tissues were significantly higher. Consequently, diagnostic outcomes could be obtained by observing CARS images with the naked eye. Furthermore, the characteristic structure of keratin pearls in keratinized cervical cancer could serve as a marker for subdividing cervical cancer types. Finally, a ConvNeXt network, a machine-learning model built from CARS images, was utilized to classify different types of tissue images. The results indicated a verification accuracy of 100 %, with a loss function of 0.0927. These findings suggest that the diagnostic model established using CARS images could efficiently diagnose cervical cancer, providing novel insights into the pathological diagnosis of this disease.

A smartphone-based standalone fluorescence spectroscopy tool for cervical precancer diagnosis in clinical conditions

Real-time prediction about the severity of noncommunicable diseases like cancers is a boon for early diagnosis and timely cure. Optical techniques due to their minimally invasive nature provide better alternatives in this context than the conventional techniques. The present study talks about a standalone, field portable smartphone-based device which can classify different grades of cervical cancer on the basis of the spectral differences captured in their intrinsic fluorescence spectra with the help of AI/ML technique. In this study, a total number of 75 patients and volunteers, from hospitals at different geographical locations of India, have been tested and classified with this device. A classification approach employing a hybrid mutual information long short-term memory model has been applied to categorize various subject groups, resulting in an average accuracy, specificity, and sensitivity of 96.56%, 96.76%, and 94.37%, respectively using 10-fold cross-validation. This exploratory study demonstrates the potential of combining smartphone-based technology with fluorescence spectroscopy and artificial intelligence as a diagnostic screening approach which could enhance the detection and screening of cervical cancer.

Enhanced cervical precancerous lesions detection and classification using Archimedes Optimization Algorithm with transfer learning

Cervical cancer (CC) ranks as the fourth most common form of cancer affecting women, manifesting in the cervix. CC is caused by the Human papillomavirus (HPV) infection and is eradicated by vaccinating women from an early age. However, limited medical facilities present a significant challenge in mid- or low-income countries. It can improve the survivability rate and be successfully treated if the CC is detected at earlier stages. Current technological improvements allow for cost-effective, more sensitive, and rapid screening and treatment measures for CC. DL techniques are widely adopted for the automated detection of CC. DL techniques and architectures are used to detect CC and provide higher detection performance. This study offers the design of Enhanced Cervical Precancerous Lesions Detection and Classification using the Archimedes Optimization Algorithm with Transfer Learning (CPLDC-AOATL) algorithm. The CPLDC-AOATL algorithm aims to diagnose cervical cancer using medical images. At the preliminary stage, the CPLDC-AOATL technique involves a bilateral filtering (BF) technique to eliminate the noise in the input images. Besides, the CPLDC-AOATL technique applies the Inception-ResNetv2 model for the feature extraction process, and the use of AOA chose the hyperparameters. The CPLDC-AOATL technique involves a bidirectional long short-term memory (BiLSTM) model for the cancer detection process. The experimental outcome of the CPLDC-AOATL technique emphasized the superior accuracy outcome of 99.53% over other existing approaches under a benchmark dataset.

Wavelet scattering transform and entropy features in fluorescence spectral signal analysis for cervical cancer diagnosis

Cervical cancer is a prevalent malignant tumor within the female reproductive system and is regarded as a prominent cause of female mortality on a global scale. Timely and precise detection of various phases of cervical cancer holds the potential to substantially enhance both the rate of successful treatment and the duration of patient survival. Fluorescence spectroscopy is a highly sensitive method for detecting the biochemical changes that arise during cancer progression. In our study, fluorescence spectral data is collected from a diverse group of 110 subjects. The potential of the scattering transform technique for the purpose of cancer detection is explored. The processed signal undergoes an initial decomposition into scattering coefficients using the wavelet scattering transform (WST). Subsequently, the scattering coefficients are subjected to computation for fuzzy entropy, dispersion entropy, phase entropy, and spectral entropy, for effectively characterizing the fluorescence spectral signals. These combined features generated through the proposed approach are then fed to 1D convolutional neural network (CNN) classifier to classify them into normal, pre-cancerous, and cancerous categories, thereby evaluating the effectiveness of the proposed methodology. We obtained mean classification accuracy of 97% using 5-fold cross-validation. This demonstrates the potential of combining WST and entropic features for analyzing fluorescence spectroscopy signals using 1D CNN classifier that enables early cancer detection in contrast to prevailing diagnostic methods.

Cervical pre-cancer classification using entropic features and CNN: In vivo validation with a handheld fluorescence probe

Cervical cancer is one of the most prevalent forms of cancer, with a lengthy latent period and a gradual onset phase. Conventional techniques are found to be severely lacking in real time detection of disease progression which can greatly enhance the cure rate. Due to their high sensitivity and specificity, optical techniques are emerging as reliable tools, particularly in case of cancer. It has been seen that biochemical changes are better highlighted through intrinsic fluorescence devoid of interference from absorption and scattering. Its effectiveness in in-vivo conditions is affected by the fact that the intrinsic spectral signatures vary from patient to patient, as well as in different population groups. Here, we overcome this limitation by collectively enumerating the subtle changes in the spectral profiles and correlations through an information theory based entropic approach, which significantly amplifies the minute spectral variations. In conjunction with artificial intelligence (AI)/machine learning (ML) tools, it yields high specificity and sensitivity with a small dataset from patients in clinical conditions, without artificial augmentation. We have used an in-house developed handheld probe (i-HHP) for extracting intrinsic fluorescence spectra of human cervix from 110 different subjects drawn from diverse population groups. The average classification accuracy of the proposed methodology using 10-fold cross validation is 93.17%. A combination of polarised fluorescence spectra from i-HHP and the proposed classifier is proven to be minimally invasive with the ability to diagnose patients in real time. This paves the way for effective use of relatively smaller sized sensitive fluorescence data with advanced AI/ML tools for early cervical cancer detection in clinics.

Stratification of tumour cell radiation response and metabolic signatures visualization with Raman spectroscopy and explainable convolutional neural network

Reprogramming of cellular metabolism is a driving factor of tumour progression and radiation therapy resistance. Identifying biochemical signatures associated with tumour radioresistance may assist with the development of targeted treatment strategies to improve clinical outcomes. Raman spectroscopy (RS) can monitor post-irradiation biomolecular changes and signatures of radiation response in tumour cells in a label-free manner. Convolutional Neural Networks (CNN) perform feature extraction directly from data in an end-to-end learning manner, with high classification performance. Furthermore, recently developed CNN explainability techniques help visualize the critical discriminative features captured by the model. In this work, a CNN is developed to characterize tumour response to radiotherapy based on its degree of radioresistance. The model was trained to classify Raman spectra of three human tumour cell lines as radiosensitive (LNCaP) or radioresistant (MCF7, H460) over a range of treatment doses and data collection time points. Additionally, a method based on Gradient-Weighted Class Activation Mapping (Grad-CAM) was used to determine response-specific salient Raman peaks influencing the CNN predictions. The CNN effectively classified the cell spectra, with accuracy, sensitivity, specificity, and F1 score exceeding 99.8%. Grad-CAM heatmaps of H460 and MCF7 cell spectra (radioresistant) exhibited high contributions from Raman bands tentatively assigned to glycogen, amino acids, and nucleic acids. Conversely, heatmaps of LNCaP cells (radiosensitive) revealed activations at lipid and phospholipid bands. Finally, Grad-CAM variable importance scores were derived for glycogen, asparagine, and phosphatidylcholine, and we show that their trends over cell line, dose, and acquisition time agreed with previously established models. Thus, the CNN can accurately detect biomolecular differences in the Raman spectra of tumour cells of varying radiosensitivity without requiring manual feature extraction. Finally, Grad-CAM may help identify metabolic signatures associated with the observed categories, offering the potential for automated clinical tumour radiation response characterization.

For cervical cancer diagnosis: Tissue Raman spectroscopy and multi-level feature fusion with SENet attention mechanism

Cervical cancer ranks among the most prevalent forms of gynecological malignancies. Timely identification of cervical lesions and prompt intervention can effectively prevent the development of cervical cancer or enhance patients' chances of survival. In this study, we propose an innovative method based on Raman spectroscopy, i.e., a multi-level SENet attention mechanism feature fusion architecture (MAFA) for rapid diagnosis of cervical cancer and precancerous lesions. The convolution process of this architecture can extract features from shallow to deep layers, and the attention mechanism is added to achieve the fusion of features from different layers. The added attention mechanism can automatically determine the importance of each layer feature channel and assign weight values to that layer according to the importance of each layer to achieve the purpose of focusing the model on certain waveform features and improve the targeting of model learning. We collected Raman spectra of 212 cervical tissues containing cervical cancer and its precancerous lesions.The experimental results show that MAFA can effectively improve the diagnostic accuracy of VGGNet, GoogLeNet and ResNet models in the validation of Raman spectral data of cervical tissue. Among them, ResNet performed the best, with the highest average accuracy, precision, recall and F1-Score of 82.36%, 84.00%, 82.35% and 82.26%, respectively, when no feature fusion was performed. The evaluation metrics improved by 4.91%, 3.97%, 4.97%, and 5.06%, respectively, after using the MAFA; they also improved by 4.16%, 2.90%, 4.17%, and 4.32%, respectively, compared with the model that directly performs feature fusion without using the attention mechanism. Therefore, the MAFA proposed in this study is better than that of the neural network that directly fuses the features of each convolutional layer. The experimental results show that the performance of the MAFA proposed in this paper is significantly higher than that of traditional deep learning algorithms, indicating that the present architecture can effectively improve the diagnostic accuracy of deep learning networks for cervical cancer.