Automatic Segmentation of Periapical Radiograph Using Color Histogram and Machine Learning for Osteoporosis Detection.

Osteoporosis leads to the loss of cortical thickness, a decrease in bone mineral density (BMD), deterioration in the size of trabeculae, and an increased risk of fractures. Changes in trabecular bone due to osteoporosis can be observed on periapical radiographs, which are widely used in dental practice. This study proposes an automatic trabecular bone segmentation method for detecting osteoporosis using a color histogram and machine learning (ML), based on 120 regions of interest (ROI) on periapical radiographs, and divided into 60 training and 42 testing datasets. The diagnosis of osteoporosis is based on BMD as evaluated by dual X-ray absorptiometry. The proposed method comprises five stages: the obtaining of ROI images, conversion to grayscale, color histogram segmentation, extraction of pixel distribution, and performance evaluation of the ML classifier. For trabecular bone segmentation, we compare K-means and Fuzzy C-means. The distribution of pixels obtained from the K-means and Fuzzy C-means segmentation was used to detect osteoporosis using three ML methods: decision tree, naive Bayes, and multilayer perceptron. The testing dataset was used to obtain the results in this study. Based on the performance evaluation of the K-means and Fuzzy C-means segmentation methods combined with 3 ML, the osteoporosis detection method with the best diagnostic performance was K-means segmentation combined with a multilayer perceptron classifier, with accuracy, specificity, and sensitivity of 90.48%, 90.90%, and 90.00%, respectively. The high accuracy of this study indicates that the proposed method provides a significant contribution to the detection of osteoporosis in the field of medical and dental image analysis.

Deep learning for protein secondary structure prediction: Pre and post-AlphaFold.

This paper aims to provide a comprehensive review of the trends and challenges of deep neural networks for protein secondary structure prediction (PSSP). In recent years, deep neural networks have become the primary method for protein secondary structure prediction. Previous studies showed that deep neural networks had uplifted the accuracy of three-state secondary structure prediction to more than 80%. Favored deep learning methods, such as convolutional neural networks, recurrent neural networks, inception networks, and graph neural networks, have been implemented in protein secondary structure prediction. Methods adapted from natural language processing (NLP) and computer vision are also employed, including attention mechanism, ResNet, and U-shape networks. In the post-AlphaFold era, PSSP studies focus on different objectives, such as enhancing the quality of evolutionary information and exploiting protein language models as the PSSP input. The recent trend to utilize pre-trained language models as input features for secondary structure prediction provides a new direction for PSSP studies. Moreover, the state-of-the-art accuracy achieved by previous PSSP models is still below its theoretical limit. There are still rooms for improvement to be made in the field.

A method for solving scriptio continua in Javanese manuscript transliteration.

Many Javanese manuscripts in Indonesia are stored in museums and libraries. Most of these manuscripts were written using local scripts that are rarely used in everyday life, and hence a software application that can help and improve the reading of these manuscripts is valuable. An essential step in automatic manuscript image transliteration is post-processing, which involves editing and concatenating syllables into words. The main problem of post-processing is that there exists no symbol for space between words in a sentence, which is called the scriptio-continua problem. This paper proposes methods based on the backtracking algorithm to solve the scriptio continua in the post-processing step of Javanese manuscript image transliteration. The proposed methods use a depth-first search in seeking relevant candidate words to determine whether to merge a new syllable or not. The results of the proposed methods to concatenate 17,687 syllables from the Hamong Tani book using a dictionary containing 49,801 words are found to be satisfactory in terms of computation and accuracy. The accuracy of the implemented greedy and brute-force methods is both 81.64%. However, the greedy-based method is more efficient and has a better performance than the brute-force method.

Method for Automated Selection of the Trabecular Area in Digital Periapical Radiographic Images Using Morphological Operations.

OBJECTIVES: The aim of this study is to propose a method that automatically select the trabecular bone area in digital periapical radiographic images using a sequence of morphological operations. METHODS: The study involved 50 digital periapical radiographic images of women aged from 36 to 58 years old. The proposed method consists of three stages: teeth detection, trabecular identification, and validation. A series of morphological operations-top-hat and bottom-hat filtering, automatic thresholding, closing, labeling, global thresholding, and image subtraction-are performed to automatically obtain the trabecular bone area in images. For validation, the results of the proposed method were compared with those of two dentists pixel by pixel. Three parameters were used in the validation: trabecular area, percentage of agreed area, and percentage of disagreed area. RESULTS: The proposed method obtains the trabecular bone area in a polygon. The obtained trabecular bone area is usually larger than that of previous studies, but is usually smaller than the dentists'. On average over all images, the trabecular area produced by the proposed method is 5.83% smaller than that identified by dentists. Furthermore, the average percentage of agreed area and the average percentage of disagreed area of the proposed method against the dentists' results were 75.22% and 8.75%, respectively. CONCLUSIONS: The shape of the trabecular bone area produced by the proposed method is similar and closer to that identified by dentists. The method, which consists of only simple morphological operations on digital periapical radiographic images, can be considered for selecting the trabecular bone area automatically.

Automated Detection of Retinal Nerve Fiber Layer by Texture-Based Analysis for Glaucoma Evaluation.

OBJECTIVES: The retinal nerve fiber layer (RNFL) is a site of glaucomatous optic neuropathy whose early changes need to be detected because glaucoma is one of the most common causes of blindness. This paper proposes an automated RNFL detection method based on the texture feature by forming a co-occurrence matrix and a backpropagation neural network as the classifier. METHODS: We propose two texture features, namely, correlation and autocorrelation based on a co-occurrence matrix. Those features are selected by using a correlation feature selection method. Then the backpropagation neural network is applied as the classifier to implement RNFL detection in a retinal fundus image. RESULTS: We used 40 retinal fundus images as testing data and 160 sub-images (80 showing a normal RNFL and 80 showing RNFL loss) as training data to evaluate the performance of our proposed method. Overall, this work achieved an accuracy of 94.52%. CONCLUSIONS: Our results demonstrated that the proposed method achieved a high accuracy, which indicates good performance.