Search

Convolutional Neural Networks (CNN) have received a large share of research in mammography image analysis due to their capability of extracting hierarchical features directly from raw data. Recently, Vision Transformers are emerging as viable alternative to CNNs in medical imaging, in some cases performing on par or better than their convolutional counterparts. In this work, we conduct an extensive experimental study to compare the most recent CNN and Vision Transformer architectures for whole mammograms classification. We selected, trained and tested 33 different models, 19 convolutional- and 14 transformer-based, on the largest publicly available mammography image database OMI-DB. We also performed an analysis of the performance at eight different image resolutions and considering all the individual lesion categories in isolation (masses, calcifications, focal asymmetries, architectural distortions). Our findings confirm the potential of visual transformers, which performed on par with traditional CNNs like ResNet, but at the same time show a superiority of modern convolutional networks like EfficientNet.

In the framework of palaeography, the availability of both effective image analysis algorithms, and high-quality digital images has favored the development of new applications for the study of ancient manuscripts and has provided new tools for decision-making support systems. The quality of the results provided by such applications, however, is strongly influenced by the selection of effective features, which should be able to capture the distinctive aspects to which the paleography expert is interested in. This process is very difficult to generalize due to the enormous variability in the type of ancient documents, produced in different historical periods with different languages and styles. The effect is that it is very difficult to define standard techniques that are general enough to be effectively used in any case, and this is the reason why ad-hoc systems, generally designed according to paleographers' suggestions, have been designed for the analysis of ancient manuscripts. In recent years, there has been a growing scientific interest in the use of techniques based on deep learning (DL) for the automatic processing of ancient documents. This interest is not only due to their capability of designing high-performance pattern recognition systems, but also to their ability of automatically extracting features from raw data, without using any a priori knowledge. Moving from these considerations, the aim of this study is to verify if DL-based approaches may actually represent a general methodology for automatically designing machine learning systems for palaeography applications. To this purpose, we compared the performance of a DL-based approach with that of a "classical" machine learning one, in a particularly unfavorable case for DL, namely that of highly standardized schools. The rationale of this choice is to compare the obtainable results even when context information is present and discriminating: this information is ignored by DL approaches, while it is used by machine learning methods, making the comparison more significant. The experimental results refer to the use of a large sets of digital images extracted from an entire 12th-century Bibles, the "Avila Bible". This manuscript, produced by several scribes who worked in different periods and in different places, represents a severe test bed to evaluate the efficiency of scribe identification systems.

Endometriosis is a condition defined as presence of endometrium outside of the uterine cavity. These endometrial cells are able to attach and invade the peritoneum or ovary, thus forming respectively the deep infiltrating endometriosis (DIE) and the ovarian endometrioma (OMA), the ectopic lesions feature of this pathology. Endometriotic cells display high invasiveness and share some features of malignancy with cancer cells. Indeed, the tissue remodeling underlining lesion formation is achieved by matrix metalloproteinases (MMPs) and their inhibitors. Therefore, these molecules are believed to play a key role in development and pathogenesis of endometriosis. This study investigated the molecular profile of metalloproteinases and their inhibitors in healthy ( n = 15) and eutopic endometrium ( n = 19) in OMA ( n = 10) and DIE ( n = 9); moreover, we firstly validated the most reliable housekeeping genes allowing accurate gene expression analysis in these tissues. Gene expression, Western blot, and immunofluorescence analysis of MMP2, MMP3, and MMP10 and their tissue inhibitors TIMP1 and TIMP2 demonstrated that these enzymes are finely tuned in these tissues. In OMA lesions, all the investigated MMPs and their inhibitors were significantly increased, while DIE expressed high levels of MMP3. Finally, in vitro TNFα treatment induced a significant upregulation of MMP3 , MMP10 , and TIMP2 in both healthy and eutopic endometrial stromal cells. This study, shedding light on MMP and TIMP expression in endometriosis, confirms that these molecules are altered both in eutopic endometrium and endometriotic lesions. Although further studies are needed, these data may help in understanding the molecular mechanisms involved in the extracellular matrix remodeling, a crucial process for the endometrial physiology.