The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

Renal cancer (RC) represents 3% of all cancers, with a 2% annual increase in incidence worldwide, opening the discussion about the need for screening. However, no established screening tool currently exists for RC. To tackle this issue, we assessed surface-enhanced Raman scattering (SERS) profiling of serum as a liquid biopsy strategy to detect renal cell carcinoma (RCC), the most prevalent histologic subtype of RC. Thus, serum samples were collected from 23 patients with RCC and 27 controls (CTRL) presenting with a benign urological pathology such as lithiasis or benign prostatic hypertrophy. SERS profiling of deproteinized serum yielded SERS band spectra attributed mainly to purine metabolites, which exhibited higher intensities in the RCC group, and Raman bands of carotenoids, which exhibited lower intensities in the RCC group. Principal component analysis (PCA) of the SERS spectra showed a tendency for the unsupervised clustering of the two groups. Next, three machine learning algorithms (random forest, kNN, naïve Bayes) were implemented as supervised classification algorithms for achieving discrimination between the RCC and CTRL groups, yielding an AUC of 0.78 for random forest, 0.78 for kNN, and 0.76 for naïve Bayes (average AUC 0.77 ± 0.01). The present study highlights the potential of SERS liquid biopsy as a diagnostic and screening strategy for RCC. Further studies involving large cohorts and other urologic malignancies as controls are needed to validate the proposed SERS approach.

Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied.