Diagnosing breast cancer tumors using stacked ensemble model

Deep learning solutions for inverse problems in advanced biomedical image analysis on disease detection

Inverse problems in biomedical image analysis represent a significant frontier in disease detection, leveraging computational methodologies and mathematical modelling to unravel complex data embedded within medical images. These problems include deducing the unknown properties of biological structures or tissues from the observed imaging data, presenting a unique challenge in decoding intricate biological phenomena. Regarding disease detection, this technique has played a critical role in optimizing diagnostic efficiency by extracting meaningful insights from different imaging modalities like molecular imaging, MRI, and CT scans. Inverse problems contribute to uncovering subtle abnormalities by employing iterative optimization techniques and sophisticated algorithms, enabling precise and early disease detection. Deep learning (DL) solutions have emerged as robust mechanisms for addressing inverse problems in biomedical image analysis, especially in disease recognition. Inverse problems involve reconstructing unknown structures or parameters from observed data, and the DL model excels in learning complex representations and mappings. This study develops a DL Solution for Inverse Problems in the Advanced Biomedical Image Analysis on Disease Detection (DLSIP-ABIADD) technique. The DLSIP-ABIADD technique exploits the DL approach to solve inverse problems and detect the presence of diseases on biomedical images. To solve the inverse problem, the DLSIP-ABIADD technique uses a direct mapping approach. Bilateral filtering (BF) is used for image preprocessing. Besides, the MobileNetv2 model derives feature vectors from the input images. Moreover, the Henry gas solubility optimization (HGSO) method is applied for optimal hyperparameter selection of the MobileNetv2 model. Furthermore, a bidirectional long short-term memory (BiLSTM) model is deployed to identify diseases in medical images. Extensive simulations have been involved to illustrate the better performance of the DLSIP-ABIADD technique. The experimentation outcomes stated that the DLSIP-ABIADD technique performs better than other models.

An integrated machine learning-based model for joint diagnosis of ovarian cancer with multiple test indicators

OBJECTIVE

To construct a machine learning diagnostic model integrating feature dimensionality reduction techniques and artificial neural network classifiers to develop the value of clinical routine blood indexes for the auxiliary diagnosis of ovarian cancer.

METHODS

Patients with ovarian cancer clearly diagnosed in our hospital were collected as a case group (n = 185), and three groups of patients with other malignant otolaryngology tumors (n = 138), patients with benign otolaryngology diseases (n = 339) and those with normal physical examination (n = 92) were used as an overall control group. In this paper, a fully automated segmentation network for magnetic resonance images of ovarian cancer is proposed to improve the reproducibility of tumor segmentation results while effectively reducing the burden on radiologists. A pre-trained Res Net50 is used to the three edge output modules are fused to obtain the final segmentation results. The segmentation results of the proposed network architecture are compared with the segmentation results of the U-net based network architecture and the effect of different loss functions and region of interest sizes on the segmentation performance of the proposed network is analyzed.

RESULTS

The average Dice similarity coefficient, average sensitivity, average specificity (specificity) and average hausdorff distance of the proposed network segmentation results reached 83.62%, 89.11%, 96.37% and 8.50, respectively, which were better than the U-net based segmentation method. For ROIs containing tumor tissue, the smaller the size, the better the segmentation effect. Several loss functions do not differ much. The area under the ROC curve of the machine learning diagnostic model reached 0.948, with a sensitivity of 91.9% and a specificity of 86.9%, and its diagnostic efficacy was significantly better than that of the traditional way of detecting CA125 alone. The model was able to accurately diagnose ovarian cancer of different disease stages and showed certain discriminative ability for ovarian cancer in all three control subgroups.

CONCLUSION

Using machine learning to integrate multiple conventional test indicators can effectively improve the diagnostic efficacy of ovarian cancer, which provides a new idea for the intelligent auxiliary diagnosis of ovarian cancer.

Clinical applications of deep learning in breast MRI

Deep learning (DL) is one of the most powerful data-driven machine-learning techniques in artificial intelligence (AI). It can automatically learn from raw data without manual feature selection. DL models have led to remarkable advances in data extraction and analysis for medical imaging. Magnetic resonance imaging (MRI) has proven useful in delineating the characteristics and extent of breast lesions and tumors. This review summarizes the current state-of-the-art applications of DL models in breast MRI. Many recent DL models were examined in this field, along with several advanced learning approaches and methods for data normalization and breast and lesion segmentation. For clinical applications, DL-based breast MRI models were proven useful in five aspects: diagnosis of breast cancer, classification of molecular types, classification of histopathological types, prediction of neoadjuvant chemotherapy response, and prediction of lymph node metastasis. For subsequent studies, further improvement in data acquisition and preprocessing is necessary, additional DL techniques in breast MRI should be investigated, and wider clinical applications need to be explored.

An integrated framework for breast mass classification and diagnosis using stacked ensemble of residual neural networks

A computer-aided diagnosis (CAD) system requires automated stages of tumor detection, segmentation, and classification that are integrated sequentially into one framework to assist the radiologists with a final diagnosis decision. In this paper, we introduce the final step of breast mass classification and diagnosis using a stacked ensemble of residual neural network (ResNet) models (i.e. ResNet50V2, ResNet101V2, and ResNet152V2). The work presents the task of classifying the detected and segmented breast masses into malignant or benign, and diagnosing the Breast Imaging Reporting and Data System (BI-RADS) assessment category with a score from 2 to 6 and the shape as oval, round, lobulated, or irregular. The proposed methodology was evaluated on two publicly available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Comparative experiments were conducted on the individual models and an average ensemble of models with an XGBoost classifier. Qualitative and quantitative results show that the proposed model achieved better performance for (1) Pathology classification with an accuracy of 95.13%, 99.20%, and 95.88%; (2) BI-RADS category classification with an accuracy of 85.38%, 99%, and 96.08% respectively on CBIS-DDSM, INbreast, and the private dataset; and (3) shape classification with 90.02% on the CBIS-DDSM dataset. Our results demonstrate that our proposed integrated framework could benefit from all automated stages to outperform the latest deep learning methodologies.