Unsupervised Feature Extraction via Deep Learning for Histopathological Classification of Colon Tissue Images.

Histopathological examination is today's gold standard for cancer diagnosis. However, this task is time consuming and prone to errors as it requires a detailed visual inspection and interpretation of a pathologist. Digital pathology aims at alleviating these problems by providing computerized methods that quantitatively analyze digitized histopathological tissue images. The performance of these methods mainly relies on the features that they use, and thus, their success strictly depends on the ability of these features by successfully quantifying the histopathology domain. With this motivation, this paper presents a new unsupervised feature extractor for effective representation and classification of histopathological tissue images. This feature extractor has three main contributions: First, it proposes to identify salient subregions in an image, based on domain-specific prior knowledge, and to quantify the image by employing only the characteristics of these subregions instead of considering the characteristics of all image locations. Second, it introduces a new deep learning-based technique that quantizes the salient subregions by extracting a set of features directly learned on image data and uses the distribution of these quantizations for image representation and classification. To this end, the proposed deep learning-based technique constructs a deep belief network of the restricted Boltzmann machines (RBMs), defines the activation values of the hidden unit nodes in the final RBM as the features, and learns the quantizations by clustering these features in an unsupervised way. Third, this extractor is the first example for successfully using the restricted Boltzmann machines in the domain of histopathological image analysis. Our experiments on microscopic colon tissue images reveal that the proposed feature extractor is effective to obtain more accurate classification results compared to its counterparts.

Effects of different suture materials on tissue healing.

PURPOSE: The purpose of this study was to investigate the healing differences in between four different widely used suture materials in the oral surgery practice, including silk (Perma- Hand; Ethicon, INC., Somerville, NJ, USA), polypropylene (Prolene; Ethicon, INC., Somerville, NJ, USA), coated polyglactin 910 (Ethicon, INC., Somerville, NJ, USA). and polyglecaprone 25 (Ethicon, INC., Somerville, NJ, USA ). MATERIALS AND METHODS: 20 male rats were randomly allocated into two groups depending on their sacrification days (post-operative 1st and the 7th days). Four longitudinal incision wounds, each 1cm in size, were created on the dorsum of each animal which were then primarily closed with four different types of sutures. RESULTS: The effects of these suture materials on soft tissue healing were compared histopathologically, by means of density of the cells, necrosis, fibrosis, foreign body reaction, the presence of cells of acute and chronic infection. No statistically significant difference was observed between the groups regarding the density of the cells, necrosis, fibrosis, foreign body reaction, and the presence of the cells of acute and chronic infections. Of note, propylene showed slightly less tissue reaction among the other materials. CONCLUSION: The results of our study showed that there is no only one ideal suture material for surgical practice. The factors related to the patient, the type of the surgery and the quality of the tissue are important to decide an appropriate suture material.

Investigation of the risk factors associated with the survival rate of dental implants.

PURPOSE: The propose of this article was to evaluate the risk factors associated with the survival rate of the dental implants. MATERIAL AND METHODS: This retrospective study evaluated the survival rate of 940 implants placed at the Faculty of Dentistry, Department of Oral and Maxillofacial Surgery, Istanbul University, from January 2003 to January 2011. The potential risk factors associated with the survival rate of the implants were investigated. RESULTS: Fifteen (1.5%) of the 940 implants failed during the follow-up period. Smoking did not affect the survival rate of the implants (log-rank, 1.5; P = 0.219). The survival rate of the implants placed in the maxilla was lower than that of the implants placed in the mandible (log-rank, 4.81; P = 0.028). The 5-year survival rate of the dental implants was 98.5%. CONCLUSIONS: There are still conflicting results about the risk factors associated with the survival rate of the implants. According to the results of this study, it is concluded that only the location of the implants is associated with the survival rates of the implants. All implant systems showed high survival rates.

Immediate implants after enucleation of an odontogenic keratocyst: an early return to function.

An odontogenic keratocyst is a unique cyst because of its locally aggressive behavior, high recurrence rate, and characteristic histologic appearance. In this article we present the case of a 22-year-old male patient with a large odontogenic keratocyst and describe his treatment with immediate dental implants.

Complications associated with the ball, bar and Locator attachmentsfor implant-supported overdentures

Background: The purpose of this clinical study was to evaluate the complications associated with the different attachments used in implant-supported overdentures, including prosthetic problems and implant failures. A comparison of ball, bar and Locator (Zest Anchors, Inc, homepage, Escondido, CA, USA) attachments, in completely edentulous patients with two, three or four implants, was conducted. Material and methods: A total of 36 edentulous patients (20 female, 16 male) with a mean age of 66.3 years, were enrolled in the study. The patients were treated with 95 implants, for the prosthetic restoration of the maxilla or the mandible. The mean follow-up time was 41.17 months. Prosthetic complications including, fractured overdentures,replacements of O-ring attachment and retention clips, implant failures, hygiene problems, mucosal enlargements, attachment fractures, retention loss and dislodgement of the attachments were recorded and evaluated.The recall visits at 3, 6, 12 months and, annually there after.Results: Fourteen complications in the ball attachment group and 7 complications in the bar group were observed.No complications were observed in the locator group. The difference was found to be as statistically significant(p=0,009). Six of the 95 implants had failed. Totally 39 implant overdentures were applied. Three prostheses wererenewed because of fractures.Conclusion: Within the limits of the present study, it was concluded that the locator system showed superior clinical results than the ball and the bar attachments, with regard to the rate of prosthodontic complications and the maintenance of the oral function (AU)

Complications associated with the ball, bar and Locator attachments for implant-supported overdentures.

BACKGROUND: The purpose of this clinical study was to evaluate the complications associated with the different attachments used in implant-supported overdentures, including prosthetic problems and implant failures. A comparison of ball, bar and Locator (Zest Anchors, Inc, homepage, Escondido, CA, USA) attachments, in completely edentulous patients with two, three or four implants, was conducted. MATERIAL AND METHODS: A total of 36 edentulous patients (20 female, 16 male) with a mean age of 66.3 years, were enrolled in the study. The patients were treated with 95 implants, for the prosthetic restoration of the maxilla or the mandible. The mean follow-up time was 41.17 months. Prosthetic complications including, fractured overdentures, replacements of O-ring attachment and retention clips, implant failures, hygiene problems, mucosal enlargements, attachment fractures, retention loss and dislodgement of the attachments were recorded and evaluated. The recall visits at 3, 6, 12 months and, annually thereafter. RESULTS: Fourteen complications in the ballattachment group and 7 complications in the bar group were observed. No complications were observed in the locator group. The difference was found to be as statistically significant (p=0,009). Six of the 95 implants had failed. Totally 39 implant overdentures were applied. Three prostheses were renewed because of fractures. CONCLUSION: Within the limits of the present study, it was concluded that the locator system showed superior clinical results than the ball and the bar attachments, with regard to the rate of prosthodontic complications and the maintenance of the oral function.

Peripheral facial nerve paralysis after upper third molar extraction.

Peripheral facial nerve paralysis (PFNP) after mandibular interventions has been reported in the literature. In most cases, paralysis begins immediately after the injection of the mandibular anesthesia, and duration of facial weakness is less than 12 hours. However, there are few documented cases of PFNP after maxillary dental or surgical procedures. A variety of mechanisms have been associated to PFNP, including viral reactivation, demyelination, edema, vasospasm, and trauma. The purpose of this presentation was to report a rare case of facial paralysis that occurred after an upper third molar extraction. The cause of the PFNP and the importance of the multidisciplinary approach in the management are emphasized.