Metric Learning in Histopathological Image Classification: Opening the Black Box.

The application of machine learning techniques to histopathology images enables advances in the field, providing valuable tools that can speed up and facilitate the diagnosis process. The classification of these images is a relevant aid for physicians who have to process a large number of images in long and repetitive tasks. This work proposes the adoption of metric learning that, beyond the task of classifying images, can provide additional information able to support the decision of the classification system. In particular, triplet networks have been employed to create a representation in the embedding space that gathers together images of the same class while tending to separate images with different labels. The obtained representation shows an evident separation of the classes with the possibility of evaluating the similarity and the dissimilarity among input images according to distance criteria. The model has been tested on the BreakHis dataset, a reference and largely used dataset that collects breast cancer images with eight pathology labels and four magnification levels. Our proposed classification model achieves relevant performance on the patient level, with the advantage of providing interpretable information for the obtained results, which represent a specific feature missed by the all the recent methodologies proposed for the same purpose.

Muscle Histopathological Abnormalities in a Patient With a CCT5 Mutation Predicted to Affect the Apical Domain of the Chaperonin Subunit.

Recognition of diseases associated with mutations of the chaperone system genes, e.g., chaperonopathies, is on the rise. Hereditary and clinical aspects are established, but the impact of the mutation on the chaperone molecule and the mechanisms underpinning the tissue abnormalities are not. Here, histological features of skeletal muscle from a patient with a severe, early onset, distal motor neuropathy, carrying a mutation on the CCT5 subunit (MUT) were examined in comparison with normal muscle (CTR). The MUT muscle was considerably modified; atrophy of fibers and disruption of the tissue architecture were prominent, with many fibers in apoptosis. CCT5 was diversely present in the sarcolemma, cytoplasm, and nuclei in MUT and in CTR and was also in the extracellular space; it colocalized with CCT1. In MUT, the signal of myosin appeared slightly increased, and actin slightly decreased as compared with CTR. Desmin was considerably delocalized in MUT, appearing with abnormal patterns and in precipitates. Alpha-B-crystallin and Hsp90 occurred at lower signals in MUT than in CTR muscle, appearing also in precipitates with desmin. The abnormal features in MUT may be the consequence of inactivity, malnutrition, denervation, and failure of protein homeostasis. The latter could be at least in part caused by malfunction of the CCT complex with the mutant CCT5 subunit. This is suggested by the results of the in silico analyses of the mutant CCT5 molecule, which revealed various abnormalities when compared with the wild-type counterpart, mostly affecting the apical domain and potentially impairing chaperoning functions. Thus, analysis of mutated CCT5 in vitro and in vivo is anticipated to provide additional insights on subunit involvement in neuromuscular disorders.

CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification.

BACKGROUND: Nucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data. RESULTS: In this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel levels are devoted to catching both non periodic and periodic DNA string features. A dense layer is devoted to their combination to give a final classification. CONCLUSIONS: Results computed on public data sets of different organisms show that CORENup is a state of the art methodology for nucleosome positioning identification based on a Deep Neural Network architecture. The comparisons have been carried out using two groups of datasets, currently adopted by the best performing methods, and CORENup has shown top performance both in terms of classification metrics and elapsed computation time.

Evaluation of a new method for the measurement of corneal thickness in eye bank posterior corneal lenticules using Anterior Segment Optical Coherence Tomography.

BACKGROUND/AIMS: To preliminarily evaluate the repeatability of central corneal thickness (CCT) measurements performed with Anterior Segment Optical Coherence Tomography (AS-OCT) on eye bank posterior corneal lenticules. METHODS: Six donor lenticules were created with a 350 µm head microkeratome (Moria, Antony, France). All donor tissues were stored at 4°C in Eusol-C solution (Alchimia S.r.l, Ponte S. Nicolò, Italy), without the anterior cornea lamella. The CCT of each lenticule, maintained in the glass phial, was measured using a commercial AS-OCT instrument (Visante, Carl Zeiss Meditec, Dublin, California, USA) and a specially designed adaptor immediately and 4, 24 and 48 hours after dissection. Immediately after AS-OCT, CCT values were measured with the ultrasound pachymetry method used at the Eye Bank. RESULTS: The mean donor cornea central thickness was 647±36 µm and 660 ± 38 µm (p=0.001) as measured by AS-OCT and ultrasound, respectively; immediately after dissection, CCT values of posterior lenticules were 235 ± 43 µm and 248 ± 44 µm, respectively (p=0.001). No statistically significant changes in CCT values of donor lenticules were assessed over the 48 h period with both methods. There was a high level of agreement, evidenced by Bland-Altman analysis, between the two methods of pachymetry. CONCLUSION: AS-OCT, with the corneal tissue in the vial, was revealed to be a repeatable and reliable method for measuring posterior donor lenticule central thickness. Lenticule CCT values measured with the investigational AS-OCT method were on average 10 µm thinner than those measured with the established ultrasound method.

Evaluation of molecular markers in corneal regeneration by means of autologous cultures of limbal cells and keratoplasty.

PURPOSE: To determine the epithelial phenotype in patients with a limbal stem cell deficiency (LSCD) after ocular surface reconstruction with autologous cultured stem cells. To correlate the epithelial phenotype with the clinical outcome. METHODS: Six eyes affected by LSCD, verified and graded by impression cytology, were treated with an autologous fibrin-cultured limbal stem cell graft. The clinical outcome was defined as a "success" or a "failure," depending on ocular surface stability. To improve their visual function, 4 patients underwent lamellar or penetrating keratoplasty after the stem cell graft. The phenotype of the regenerated corneal epithelium was determined by immunofluorescence of the corneal button to detect CK12, CK3, CK19, and Muc1 as corneal and conjunctival markers. RESULTS: After a mean follow-up of 24 months, 5 cases were defined as successes; 1 case presented an epithelial defect 4 months after grafting and was defined as a failure. Immunofluorescence performed on 4 patients after lamellar and penetrating keratoplasty confirmed the presence of epithelial corneal markers (CK12 and CK3) in 2 of the success cases and the presence of conjunctival markers (CK19 and Muc1) in the 1 failure case. In one of the success cases, both corneal and conjunctival markers were detected on the corneal button. All success cases showed maintenance of marker accounting for high proliferative potential (DeltaNp63alpha) after transplantation. CONCLUSIONS: Autologous cultures of limbal stem cells can regenerate a functional corneal epithelium in patients affected by unilateral LSCD. We showed a correlation between the clinical outcome and the molecular marker expression.

Pre-cut donor tissue for Descemet stripping automated keratoplasty: anterior hinged lamella on versus off.

AIMS: To compare two different techniques for preparation of pre-cut lamellar corneal tissue for Descemet stripping automated keratoplasty. BACKGROUND/METHODS: Eight donor lenticules were created with a full pass of the microkeratome blade, which resulted in a posterior lamella and a free cap (anterior lamella off group (AL-off)). Contralateral donor lenticules were created with an incomplete pass of the microkeratome blade, which resulted in a posterior lamella and a hinged anterior cap (anterior lamella on group (AL-on)). Endothelial cell density, cellular viability and corneal thickness were evaluated before dissection, and 4 and 24 h after dissection. RESULTS: Average pre-cut endothelial cell density was 2552.25 (+/-105) and 2572.25 (+/-110) cells/mm(2) in the AL-off group and AL-on group, respectively (p=0.7). At 24 h cell density was 2404.87 (+/-74) in the AL-off group (p<0.01) and 2368.74 (+/-148) in the AL-on group (p=0.01). The mean percentage of trypan blue-stained cells was consistently higher in the hinged AL-on group. Corneal thickness increased by approximately 20% in both groups after 24 h cold storage. CONCLUSION: Eye bank-prepared tissue offers the potential advantage of being screened for mechanical stress damage occurring during the automated dissection.