Search results for: entropy maximization

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 284

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 70

Authors: Roven Tumaneng, Angelica Kristina Monzon, Ralph Sedricke Lapuz, Jose Don De Alban, Jennica Paula Masigan, Joanne Rae Pales, Laila Monera Pornel, Dennis Tablazon, Rizza Karen Veridiano, Jackie Lou Wenceslao, Edmund Leo Rico, Neil Aldrin Mallari

Abstract:

Most protected area management plans in the Philippines, particularly the smaller and more remote islands suffer from insufficient baseline data, which should provide the bases for formulating measureable conservation targets and appropriate management interventions for these protected areas. Attempts to synthesize available data particularly on cultural and socio-economic characteristic of local peoples within and outside protected areas also suffer from the lack of comprehensive and detailed inventories, which should be considered in designing adaptive management interventions to be used for those protected areas. Mt Guiting-guiting Natural Park (MGGNP) located in Sibuyan Island is one of the poorly studied protected areas in the Philippines. In this study, we determined the highly biologically important areas of the protected area using Maximum Entropy approach (MaxEnt) from environmental predictors (i.e., topographic, bioclimatic,land cover, and soil image layers) derived from global remotely sensed data and point occurrence data of species of birds and trees recorded during field surveys on the island. A total of 23 trigger species of birds and trees was modeled and stacked to generate species richness maps for biological high conservation value areas (HCVAs). Forest habitat change was delineated using dual-polarised L-band ALOS-PALSAR mosaic data at 25 meter spatial resolution, taken at two acquisition years 2007 and 2009 to provide information on forest cover ad habitat change in the island between year 2007 and 2009. Determining the livelihood guilds were also conducted using the data gathered from171 household interviews, from which demographic and livelihood variables were extracted (i.e., age, gender, number of household members, educational attainment, years of residency, distance from forest edge, main occupation, alternative sources of food and resources during scarcity months, and sources of these alternative resources).Using Principal Component Analysis (PCA) and Kruskal-Wallis test, the diversity and patterns of forest resource use by people in the island were determined with particular focus on the economic activities that directly and indirectly affect the population of key species as well as to identify levels of forest resource use by people in different areas of the park.Results showed that there are gaps in the area occupied by the natural park, as evidenced by the mismatch of the proposed HCVAs and the existing perimeters of the park. We found out that subsistence forest gathering was the possible main driver for forest degradation out of the eight livelihood guilds that were identified in the park. Determining the high conservation areas and identifyingthe anthropogenic factors that influence the species richness and abundance of key species in the different management zone of MGGNP would provide guidance for the design of a protected area management plan and future monitoring programs. However, through intensive communication and consultation with government stakeholders and local communities our results led to setting conservation targets in local development plans and serve as a basis for the reposition of the boundaries and reconfiguration of the management zones of MGGNP.

Keywords: conservation gaps, livelihood guilds, MaxEnt, protected area

Procedia PDF Downloads 404