Endoscopic Endonasal Transsphenoidal Resection of Pituitary Adenomas in Patients Presenting With Monocular Blindness.

BACKGROUND AND OBJECTIVES: Suprasellar tumors, particularly pituitary adenomas (PAs), commonly present with visual decline, and the endoscopic endonasal transsphenoidal approach (EETA) is the primary management for optic apparatus decompression. Patients presenting with complete preoperative monocular blindness comprise a high-risk subgroup, given concern for complete blindness. This retrospective cohort study evaluates outcomes after EETA for patients with PA presenting with monocular blindness. METHODS: Retrospective analysis of all EETA cases at our institution from June 2012 to August 2023 was performed. Inclusion criteria included adults with confirmed PA and complete monocular blindness, defined as no light perception, and a relative afferent pupillary defect secondary to tumor mass effect. RESULTS: Our cohort includes 15 patients (9 males, 6 females), comprising 2.4% of the overall PA cohort screened. The mean tumor diameter was 3.8 cm, with 6 being giant PAs (>4 cm). The mean duration of preoperative monocular blindness was 568 days. Additional symptoms included contralateral visual field defects (n = 11) and headaches (n = 10). Two patients presented with subacute PA apoplexy. Gross total resection was achieved in 46% of patients, reflecting tumor size and invasiveness. Postoperatively, 2 patients experienced improvement in their effectively blind eye and 2 had improved visual fields of the contralateral eye. Those with improvements were operated within 10 days of presentation, and no patients experienced worsened vision. CONCLUSION: This is the first series of EETA outcomes in patients with higher-risk PA with monocular blindness on presentation. In these extensive lesions, vision remained stable for most without further decline and improvement from monocular blindness was observed in a small subset of patients with no light perception and relative afferent pupillary defect. Timing from vision loss to surgical intervention seemed to be associated with improvement. From a surgical perspective, caution is warranted to protect remaining vision and we conclude that EETA is safe in the management of these patients.

Lethal Complications of Meningiomas: A Case Series.

Background: Meningiomas are the most prevalent type of primary intracranial tumor in adults, comprising nearly one-third of all intracranial tumors. They are typically benign, slow-growing, and asymptomatic but may cause neurological symptoms as they expand due to mass effect. Classification is determined by World Health Organization (WHO) grades 1 to 3 following pathological examination corresponding to benign, atypical, and anaplastic (malignant), respectively, reflecting their rate of growth and risk of recurrence. The vast majority are WHO grade 1 and their slow growth permits timely presentation for elective resection; however, meningiomas in vulnerable locations and coexisting morbidities can result in sudden death. Objectives: We present a series of four adult patients with meningiomas which resulted in death, including a case of fatal seizure, midline hemorrhagic meningioma, postresection meningitis, and compression of the cerebellum. Research design: Retrospective review of the authors' cases was conducted. Available pathology, medical, and autopsy records including gross images were reviewed in each case. The inclusion criteria were adult patients (>18 years old) and that the cause of death had to include meningioma. Subjects: The four patients included a 61-year-old male, an 84-year-old female, a 62-year-old male, and a 37-year-old female. Measures: Qualitative; autopsy reports describing cause of death and pathology report findings including gross and microscopic analysis. Conclusions: Meningiomas are often benign in nature but can rarely result in death. Size and location of the tumor and risk factors are contributory. Autopsy examination can be instrumental in identifying the cause and mechanism of deaths associated with meningiomas.

Clinical Implications of Pituitary Adenomas Exhibiting Dual Transcription Factor Staining: A Case Series of 27 Patients.

OBJECTIVE: According to the 2017 World Health Organization classification of neuro-endocrine tumors, pituitary adenomas (PAs) are classified according to immunoexpression of the pituitary-specific transcription factors (TFs). A small subset of PAs exhibit multiple TF staining on immunohistochemistry and we present a series of 27 pathologically-confirmed cases of dual TF staining PAs (dsTF-PAs), and report clinically relevant implications. METHODS: A retrospective chart review of a multi-institutional database of patients with PAs surgically resected between 2008-2021 was performed. PAs expressing immunopositivity 2+ TFs. Patient demographics, neuro-imaging characteristics, histopathologic findings, and clinical data were collected. RESULTS: Twenty-seven patients had pathologically verified dsTF-PAs, of whom 17 were female (63%), with ages ranging from 20-84 years. Twenty-three (85.2%) patients harbored functional PAs, with acromegaly being the most common functional subtype (86.4%). The most common combination of TFs within a single tumor was PIT-1/SF-1 (85.2%). Six PAs exhibited Knosp cavernous sinus invasion grades of 3 or 4 and the Ki-67 labeling index was ≥3% in 6 patients (24.0%) and all stained for PIT-1/SF-1. Hormonal remission was achieved in 78% of functional dsTF-PAs. No PAs showed evidence of recurrence or progression over the mean follow-up period of 28.5 months. CONCLUSIONS: PAs exhibiting dsTF-PAs represent a small but clinically relevant diagnostic subset of PAs according to the 2021 World Health Organization criteria, as a majority are GH-producing. Precise classification using TF staining plays a key role in understanding the biology of these tumors. Favorable outcomes can be achieved in this subset of PAs with evolving TF classification.

Tumor characteristics guiding selection of channel-based versus open microscopic approaches for resection of atrial intraventricular meningiomas: patient series.

BACKGROUND: Atrial intraventricular meningiomas (AIMs) are relatively rare and typically deep-seated tumors that can mandate resection. Compared with transsulcal or transcortical open microscopic approaches, port- or channel-based exoscopic approaches have facilitated a less invasive alternative of tumor access and resection. The authors present a case series of seven patients with AIMs who underwent open microscopic versus channel-based exoscopic resection by a senior neurosurgeon at their institution between 2012 and 2022 to understand patient and tumor features that lent themselves to selection of a particular approach. OBSERVATIONS: In the patients harboring three AIMs selected for channel-based resection, the average AIM diameter (2.9 vs 5.2 cm) was smaller, the AIMs were deeper from the cortical surface (2.5 vs 1.1 cm), and the patients had a shorter average postoperative length of stay (3.3 vs 5.8 days) compared with the four patients who underwent open resection. Gross-total resection was achieved in all cases. Complications for both groups included transient homonymous hemianopsia and aphasia. No recurrences were identified over the follow-up period. LESSONS: The authors demonstrate that channel-based exoscopic resection is safe and effective for AIMs 3 cm in diameter and over 2 cm deep. This may help guide neurosurgeons in future approach selection based on tumor features, including size/volume, location, and depth from cortical surface.

Comparison of preoperative versus postoperative treatment dosimetry plans of single-fraction stereotactic radiosurgery for surgically resected brain metastases.

OBJECTIVE: Stereotactic radiosurgery (SRS) for operative brain metastasis (BrM) is usually administered 1 to 6 weeks after resection. Preoperative versus postoperative timing of SRS delivery related to surgery remains a critical question, as a pattern of failure is the development of leptomeningeal disease (LMD) in as many as 35% of patients who undergo postoperative SRS or the occurrence of radiation necrosis. As they await level I clinical data from ongoing trials, the authors aimed to bridge the gap by comparing postoperative with simulated preoperative single-fraction SRS dosimetry plans for patients with surgically resected BrM. METHODS: The authors queried their institutional database to retrospectively identify patients who underwent postoperative Gamma Knife SRS (GKSRS) after resection of BrM between January 2014 and January 2021. Exclusion criteria were prior radiation delivered to the lesion, age < 18 years, and prior diagnosis of LMD. Once identified, a simulated preoperative SRS plan was designed to treat the unresected BrM and compared with the standard postoperative treatment delivered to the resection cavity per Radiation Therapy Oncology Group (RTOG) 90-05 guidelines. Numerous comparisons between preoperative and postoperative GKSRS treatment parameters were then made using paired statistical analyses. RESULTS: The authors' cohort included 45 patients with a median age of 59 years who were treated with GKSRS after resection of a BrM. Primary cancer origins included colorectal cancer (27%), non-small cell lung cancer (22%), breast cancer (11%), melanoma (11%), and others (29%). The mean tumor and cavity volumes were 15.06 cm3 and 12.61 cm3, respectively. In a paired comparison, there was no significant difference in the planned treatment volumes between the two groups. When the authors compared the volume of surrounding brain that received 12 Gy or more (V12Gy), an important predictor of radiation necrosis, 64% of patient plans in the postoperative SRS group (29/45, p = 0.008) recorded greater V12 volumes. Preoperative plans were more conformal (p < 0.001) and exhibited sharper dose drop-off at the lesion margins (p = 0.0018) when compared with postoperative plans. CONCLUSIONS: Comparison of simulated preoperative and delivered postoperative SRS plans administered to the BrM or resection cavity suggested that preoperative SRS allows for more highly conformal lesional coverage and sharper dose drop-off compared with postoperative plans. Furthermore, V12Gy was lower in the presurgical GKSRS plans, which may account for the decreased incidence of radiation necrosis seen in prior retrospective studies.

Endoscopic endonasal approach for MRI-Negative Cushing's microadenoma.

A 54-year-old male with a history of diabetes mellitus type 2 for 12 years and hypertension was seen in the clinic due to poorly controlled diabetes. Inferior petrosal sinus sampling (IPSS) confirmed Cushing's disease with primary adrenocorticotropic hormone (ACTH)-secreting pituitary adenoma on the right. However, 3T and subsequent 7T MRI showed no visible tumor. An endoscopic transsphenoidal approach was selected to explore the pituitary gland and resect the presumed microadenoma. Tumor was identified in the lateral recess along the right medial cavernous sinus wall and gross-total resection (GTR) was performed. The normal pituitary gland was preserved, and the patient went into remission. The video can be found here: https://stream.cadmore.media/r10.3171/2023.4.FOCVID2324.

Complete, Fully Automatic Detection and Classification of Benign and Malignant Breast Tumors Based on CT Images Using Artificial Intelligent and Image Processing.

Breast cancer is the most common type of cancer in women, and early detection is important to significantly reduce its mortality rate. This study introduces a detection and diagnosis system that automatically detects and classifies breast tumors in CT scan images. First, the contours of the chest wall are extracted from computed chest tomography images, and two-dimensional image characteristics and three-dimensional image features, together with the application of active contours without edge and geodesic active contours methods, are used to detect, locate, and circle the tumor. Then, the computer-assisted diagnostic system extracts features, quantifying and classifying benign and malignant breast tumors using a greedy algorithm and a support vector machine. The study used 174 breast tumors for experiment and training and performed cross-validation 10 times (k-fold cross-validation) to evaluate performance of the system. The accuracy, sensitivity, specificity, and positive and negative predictive values of the system were 99.43%, 98.82%, 100%, 100%, and 98.89% respectively. This system supports the rapid extraction and classification of breast tumors as either benign or malignant, helping physicians to improve clinical diagnosis.

In Vivo Automatic and Quantitative Measurement of Adult Human Larynx and Vocal Fold Images.

INTRODUCTION: Qualitative laryngoscopy belongs to a diagnostic routine. Nevertheless, quantitative morphometric measurements of laryngeal structures remain challenging. This study aimed to introduce a special laser projection device that can facilitate computer-assisted digitalized analysis and provide important quantitative information for diagnostics and treatment planning. MATERIALS AND METHODS: The laryngeal images were captured with our device, which contained two parallel laser beams in order to provide the scaling reference. The maximum length of the vocal fold during respiration and vibration (phonation), vocal width at midpoint, total fold area, maximum cross-sectional area of the glottic space, and maximum vocal fold angle were determined and calculated. These parameters were analyzed and compared on the basis of age, sex, body height, body weight and body mass index. RESULTS: A total of 87 subjects were enrolled in this study, comprising 39 males and 48 females. The age range for all subjects was 21 to 80 years old. The maximum value of the glottic area and vocal angle showed no significant gender difference. Both the respiration and vibration vocal fold length was significantly longer in males than in females. The vocal width revealed no gender difference, but the fold area during both respiration and phonation was significantly larger in men than in women. As for the respiration-to-vibration ratio of the vocal length, there was a trend, but without statistical significance (P = 0.06), toward a higher length compression ratio in men than in women. Meanwhile, age was found to have a strong relationship with vocal width during phonation. The width of vibration vocal fold decreased with aging significantly. CONCLUSION: Our innovative module can provide reference parameters, which makes it possible to directly estimate the objective absolute values of relevant laryngeal structures. Our non-invasive approach can be used during routine laryngoscopy and the findings easily documented. In future, we can extend its clinical application to measure subtle laryngeal or hypopharyngeal changes, which are difficult to objectively quantify.

Patient-level thyroid cancer classification using attention multiple instance learning on fused multi-scale ultrasound image features.

For patients with thyroid nodules, the ability to detect and diagnose a malignant nodule is the key to creating an appropriate treatment plan. However, assessments of ultrasound images do not accurately represent malignancy, and often require a biopsy to confirm the diagnosis. Deep learning techniques can classify thyroid nodules from ultrasound images, but current methods depend on manually annotated nodule segmentations. Furthermore, the heterogeneity in the level of magnification across ultrasound images presents a significant obstacle to existing methods. We developed a multi-scale, attention-based multiple-instance learning model which fuses both global and local features of different ultrasound frames to achieve patient-level malignancy classification. Our model demonstrates improved performance with an AUROC of 0.785 (p<0.05) and AUPRC of 0.539, significantly surpassing the baseline model trained on clinical features with an AUROC of 0.667 and AUPRC of 0.444. Improved classification performance better triages the need for biopsy.

Improvement in Injection Molding Quality Performance with Innovative Cyclone Mixers Used in Polypropylene with Spherical Silicon Dioxide Composites.

This research proposes an innovative design of a new cyclone mixer for the quality of polymer materials, and it presents a systematic optimization model of process parameters for plastic injection molding. Thermo gravimetric analysis (TGA) and differential scanning calorimetry (DSC) were used to determine the appropriate thermal properties of processing in order to select appropriate control factors and level values for a Taguchi orthogonal array. The injection molding machine was used to make sample test pieces for tensile strength, hardness and impact strength. Significant factors were found by the signal-to-noise (S/N) ratio with an analysis of variation (ANOVA), and the single-quality optimal parameter combination was obtained. The reproducibility of the experiment was evaluated, and various quality weights were evaluated by principal components analysis (PCA). The multi-quality optimal parameter combination was found, and the comprehensive scores were compared. Finally, the process capability indices were combined with a multi-process capability analysis chart (MPCAC) to compare the process yields of cyclone mixing and screw mixing. The mechanical properties of products were evaluated to verify the performance of cyclone mixing and to provide perfect information for the injection molding quality performance of cyclone mixing and screw mixing. It was concluded that the overall quality of the cyclone mixing products is 42.72, and the total quality of the screw mixing products is 41.85. The total number of defects for the cyclone mixing is 9659 ppm, and that of the screw mixing is 10688 ppm. It can be seen that, for the overall product quality performance, cyclone mixing can be applied in the plastic injection molding process instead of screw mixing.

Development of Multifunctional Nano-Graphene-Grafted Polyester to Enhance Thermal Insulation and Performance of Modified Polyesters.

Nano-graphene materials have improved many thermal properties based on polymer systems. The additive polymers' thermal insulation cannot be significantly increased for use as a reinforcement in multifunctional thermally insulating polymer foam. Herein, we present the development of far-infrared emissivity and antistatic properties using multifunctional nano-graphene polyester fibers. Nano-graphene far-infrared thermal insulation polyester was synthesized with 2% nano-graphene and dispersant polypropylene wax-maleic anhydride (PP wax-MA) using the Taguchi method combined with grey relational analysis (GRA) to improve the thermal properties and the performance of the polymer composite. The thermogravimetric analysis (TGA) shows that the pyrolysis temperature of spinning-grade polyester was increased when the nano-graphene powder was added to the polyester. The differential scanning calorimeter (DSC) analysis confirmed the modification of polyester by nano-graphene, showing the effect of the nucleating agent, which ultimately improved the performance of the polyester. The physical properties of the optimized polyester fibers were improved with a yarn count of 76.5 d, tensile strength of 3.3 g/d, and an elongation at break increased from 23.5% to 26.7% compared with unmodified polymer yarn. These far-infrared emission rates increased from 78% to 83%, whereas the far-infrared temperature increased from 4.0 °C to 22 °C, and the surface resistance increased to 108 Ω. The performance of the optimized modified polyester yarn is far better than single-polypropylene-grafted maleic anhydride yarn. The performance of optimized modified polyester yarn, further confirmed using grey correlation analysis (GRA), can improve the yarns' mechanical properties and far-infrared functions. Our findings provide an alternative route for developing nano-graphene polyester fabrics suitable for the fabric industry.

Quality Prediction and Abnormal Processing Parameter Identification in Polypropylene Fiber Melt Spinning Using Artificial Intelligence Machine Learning and Deep Learning Algorithms.

Melt spinning machines must be set up according to the process parameters that result in the best end product quality. In this study, artificial intelligence algorithms were employed to create a system that detects abnormal processing parameters and suggests strategies to improve quality. Polypropylene (PP) was selected as the experimental material, and the quality achieved by adjusting the melt spinning machine's processing parameter settings was used as the basis for judgement. The processing parameters included screw temperature, gear pump temperature, die head temperature, screw speed, gear pump speed, and take-up speed as the six control factors. The four quality characteristics included fineness, breaking strength, elongation at break, and elastic energy modulus. In the first part of our study, we applied fast deep-learning characteristic grid calculations on a 440-item historical data set to train a deep learning neural network and determine methods for multi-quality optimization. In the second part, with the best processing parameters as a benchmark, and given abnormal quality data derived from processing parameter settings deviating from these optimal values, several machine learning and deep learning methods were compared in their ability to find the settings responsible for the abnormal data, which was randomly split into a 210-item training data set and a 210-item verification data set. The random forest method proved to be the best at identifying responsible parameter settings, with accuracy rates of single and double identification classifications together of 100%, for single factor classification of 98.3%, and for double factor classification of 96.0%, thereby confirming that the diagnostic method proposed in this study can effectively predict product abnormality and find the parameter settings responsible for product abnormality.

Quantitative Measurement of Throat and Larynx After Endotracheal Intubation for Palatoplasty.

Introduction: Quantitative morphometric measurements of living human upper airway remain challenging. This study aimed to introduce a special laser projection device that can facilitate computer-assisted, digitalized analysis and provide important information on airway mucosa change, before and after endotracheal intubation for palatoplasty. Materials and Methods: The laryngeal images were captured before and after surgery. Image processing techniques were used to quantize the post-operative laryngeal variation, with its distinct color space and texture features. Meanwhile, the maximum length of the vocal fold, vocal width at the midpoint, maximum cross-sectional area of the glottic space, maximum cross-sectional area of the oropharyngeal inlet (CSAOI) and the depth of the retropalatal space were determined and calculated. These parameters were analyzed and compared before and after surgery. Results: A total of 39 subjects were enrolled in this study. The color space and texture analysis all show trends toward higher measures in post-operative images than in pre-operative images, especially in the interarytenoid region. Furthermore, the glottic area showed a significant decrease of 31.2%, while the vocal width showed a significant increase after intubation. The post-operative retropalatal depth and CSAOI were significantly deeper and larger than the baseline, reaching their peak in the 4th week after the surgery, and then slightly reduced in the 12th week. Conclusion: For the first time we present a series of changes in upper airway after surgery, by using a laser module with quantitative measurement. Our equipment and processing can measure subtle mucosal changes that would allow a clinician to diagnose post-operative airway inflammation in a simpler and less invasive way. Here additional information collected by different imaging modalities would help to solve multiple current unmet needs in post-operative airway inflammation.

Quantitative Measurement of Adult Human Larynx post General Anesthesia with Intubation.

Introduction: Post-anaesthetic sore throat (PAST) is a well-recognized consequence of tracheal intubation; however, quantitative morphometric measurements remain challenging. This study aimed to introduce a special laser projection device that can facilitate computer-assisted, digitalized analysis and provide important information on laryngeal mucosa change, pre and post-surgery under general anesthesia with intubation. Materials and methods: The laryngeal images were captured and divided into the control group and the intubation group. Image processing techniques were used to quantify the post-extubation laryngeal variation, with its distinct color space and texture features. Meanwhile, the maximum length of the vocal fold, vocal width at the midpoint, and maximum cross-sectional area of the glottic space were determined and calculated. These parameters were analyzed and compared pre and post-surgery. Results: A total of 69 subjects were enrolled in this study, comprising 32 subjects in the healthy group and 37 subjects in the intubation group. The color space and texture analysis with contrast and correlation profiles all shows trend toward higher measures in the intubation group than in the healthy group, with statistical significance and outstanding discrimination ability, especially in the interarytenoid region. The incidence of PAST was approximately 46% (17 patients). The gender difference, type of surgery, and the fixation position of the tube were not significantly related to the PAST occurrence. All the eigenvalues showed significant differences pre and post-surgery in the interarytenoid region and a significant trend toward red and increased contrast texture profiles was revealed. Furthermore, the glottic area showed a significant decrease of 25.29%, while the vocal width showed a significant increase post extubation. Conclusion: Our equipment and processing can measure subtle laryngeal changes that would allow a clinician to diagnose postoperative laryngeal inflammation in a simpler and less invasive way. The trend toward red, the increased contrast texture and vocal width, and the reduced glottic space were all compatible with post-intubation inflammatory response, especially in the interarytenoid region. This is important to know so that one can take appropriate steps to alleviate PAST in the future.

Semi-Supervised Deep Learning Semantic Segmentation for 3D Volumetric Computed Tomographic Scoring of Chronic Rhinosinusitis: Clinical Correlations and Comparison with Lund-Mackay Scoring.

BACKGROUND: The traditional Lund-Mackay score (TLMs) is unable to subgrade the volume of inflammatory disease. We aimed to propose an effective modification and calculated the volume-based modified LM score (VMLMs), which should correlate more strongly with clinical symptoms than the TLMs. METHODS: Semi-supervised learning with pseudo-labels used for self-training was adopted to train our convolutional neural networks, with the algorithm including a combination of MobileNet, SENet, and ResNet. A total of 175 CT sets, with 50 participants that would undergo sinus surgery, were recruited. The Sinonasal Outcomes Test-22 (SNOT-22) was used to assess disease-specific symptoms before and after surgery. A 3D-projected view was created and VMLMs were calculated for further comparison. RESULTS: Our methods showed a significant improvement both in sinus classification and segmentation as compared to state-of-the-art networks, with an average Dice coefficient of 91.57%, an MioU of 89.43%, and a pixel accuracy of 99.75%. The sinus volume exhibited sex dimorphism. There was a significant positive correlation between volume and height, but a trend toward a negative correlation between maxillary sinus and age. Subjects who underwent surgery had significantly greater TLMs (14.9 vs. 7.38) and VMLMs (11.65 vs. 4.34) than those who did not. ROC-AUC analyses showed that the VMLMs had excellent discrimination at classifying a high probability of postoperative improvement with SNOT-22 reduction. CONCLUSIONS: Our method is suitable for obtaining detailed information, excellent sinus boundary prediction, and differentiating the target from its surrounding structure. These findings demonstrate the promise of CT-based volumetric analysis of sinus mucosal inflammation.

Synthesis of novel CuNb2O6/g-C3N4 binary photocatalyst towards efficient visible light reduction of Cr (VI) and dyes degradation for environmental remediation.

The further development of an efficient and sustainable water treatment requires the development of a very active and controllable photocatalyst. The heterojunction is a promising site where the activity of such a photocatalyst can be enhanced. Organic dyes have become a severe concern in recent years owing to their significant presence in wastewater. Hexavalent Chromium (Cr (VI)) is a potential carcinogen also exhibiting great persistence in wastewater. So, a low-waste, high-performance materials is required to eliminate organic dyes and Cr (VI) from wastewater. In this study, CNO/g-CN (CuNb2O6/g-C3N4) photocatalyst synthesized via co-precipitation, followed by calcination which were characterized using physiochemical and photo-electrochemical approaches to identify their structural, photochemical and optical traits. The uniqueness of the synthesized photocatalyst is due to both its efficient photo-reduction of Cr (VI) and photo-degradation of Rhodamine B (RhB), Methylene Blue (MB) and Methyl Orange (MO) under visible light. The CNO/g-CN composite with 30% CNO heterojunctions exhibited the highest photocatalytic activity with Cr (VI) 92.80% photoreduction and efficiency degradation for RhB, MB, MO of 99.6%, 98.50%, 99.0%, respectively, with constant rate (k). This efficient photocatalytic activity is attributed to the lower recombination rate of electron-hole pairs. Free radical trapping experiments showed that •O2- and h+ play an important role in the photodegradation. The study, therefore, opens an alternative route in the synthesis of very efficient binary photocatalysts for application in environmental remediation.

Quantitative laryngoscopy with computer-aided diagnostic system for laryngeal lesions.

Laryngoscopes are widely used in the clinical diagnosis of laryngeal lesions, but such diagnosis relies heavily on the physician's subjective experience. The purpose of this study was to develop a computer-aided diagnostic system for the detection of laryngeal lesions based on objective criteria. This study used the distinct features of the image contour to find the clearest image in the laryngoscopic video. First to reduce the illumination problem caused by the laryngoscope lens, which could not fix the position of the light source, this study proposed image compensation to provide the image with a consistent brightness range for better performance. Second, we also proposed a method to automatically screen clear images from laryngoscopic film. Third, we used ACM to segment automatically them based on structural features of the pharynx and larynx, using hue and geometric analysis in the vocal cords and other zones. Finally, the support vector machine was used to classify laryngeal lesions based on a decision tree. This study evaluated the performance of the proposed system by assessing the laryngeal images of 284 patients. The accuracy of the detection for vocal cord polyps, cysts, leukoplakia, tumors, and healthy vocal cords were 93.15%, 95.16%, 100%, 96.42%, and 100%, respectively. The cross-validation accuracy for the five classes were 93.1%, 94.95%, 99.4%, 96.01% and 100%, respectively, and the average test accuracy for the laryngeal lesions was 93.33%. Our results showed that it was feasible to take the hue and geometric features of the larynx as signs to identify laryngeal lesions and that they could effectively assist physicians in diagnosing laryngeal lesions.

Laryngopharyngeal reflux image quantization and analysis of its severity.

Laryngopharyngeal reflux (LPR) is a prevalent disease affecting a high proportion of patients seeking laryngology consultation. Diagnosis is made subjectively based on history, symptoms, and endoscopic assessment. The results depend on the examiner's interpretation of endoscopic images. There are still no consistent objective diagnostic methods. The aim of this study is to use image processing techniques to quantize the laryngeal variation caused by LPR, to judge and analyze its severity. This study proposed methods of screening sharp images automatically from laryngeal endoscopic images and using throat eigen structure for automatic region segmentation. The proposed image compensation improved the illumination problems from the use of laryngoscope lens. Fisher linear discriminant was used to find out features and classification performance while support vector machine was used as the classifier for judging LPR. Evaluation results were 97.16% accuracy, 98.11% sensitivity, and 3.77% false positive rate. To evaluate the severity, quantized data of the laryngeal variation was used. LPR images were combined with reflux symptom index score chart, and severity was graded using a neural network. The results indicated 96.08% accuracy. The experiment indicated that laryngeal variation induced by LPR could be quantized by using image processing techniques to assist in diagnosing and treating LPR.

Prognostic value of tumor volume for patients with advanced lung cancer treated with chemotherapy.

BACKGROUND AND OBJECTIVE: We aim to develop a reference system utilizing computed tomography to calculate changes in tumor volume of lung cancer patients after chemotherapy to assist physicians in clinical treatment and evaluation. METHODS: Image processing techniques were used to analyze the computed tomography of lung cancer, locate the tumor, and calculate the tumor volume. The medical indicator was then evaluated and analyzed. We examined the correlation between reduced tumor volume and survival duration of 88 patients after chemotherapy at Tri-Service General Hospital, Taiwan. The innovative survival prediction index was obtained by four statistical methods: receiver operating characteristic curve, Youden index, Kaplan-Meier method, and log rank test. RESULTS: From the image processing techniques, tumor volume from each patient were obtained within an average of 7.25 seconds. The proposed method was shown to achieve rapid positioning of lung tumors and volume reconstruction with an estimation error of 1.92% when calibrated with an irregularly shaped stone. In medical indicator evaluation and analysis, the area below the receiver operating characteristic curve is greater than 0.8, indicating good predictability of the medical index used herein. The Youden index spotted the best cut-off point of volume, and the correlation between the volume's cut-off point and survival time was confirmed again by Kaplan-Meier and log rank test. The p-values were all less than 0.05, presenting a high degree of correlation between the two, indicating that this medical indicator is highly reliable. CONCLUSIONS: The proposed techniques can automatically find the location of tumors in the lung, reconstruct the volume, and calculate changes in volume before and after treatment, thus obtaining an innovative survival prediction index. This will help facilitate early and accurate predictions of disease outcomes during the course of therapy, and categorize patient stratification into risk groups for more efficient therapies.

Automatic recognizing of vocal fold disorders from glottis images.

The laryngeal video stroboscope is an important instrument to test glottal diseases and read vocal fold images and voice quality for physician clinical diagnosis. This study is aimed to develop a medical system with functionality of automatic intelligent recognition of dynamic images. The static images of glottis opening to the largest extent and closing to the smallest extent were screened automatically using color space transformation and image preprocessing. The glottal area was also quantized. As the tongue base movements affected the position of laryngoscope and saliva would result in unclear images, this study used the gray scale adaptive entropy value to set the threshold in order to establish an elimination system. The proposed system can improve the effect of automatically captured images of glottis and achieve an accuracy rate of 96%. In addition, the glottal area and area segmentation threshold were calculated effectively. The glottis area segmentation was corrected, and the glottal area waveform pattern was drawn automatically to assist in vocal fold diagnosis. When developing the intelligent recognition system for vocal fold disorders, this study analyzed the characteristic values of four vocal fold patterns, namely, normal vocal fold, vocal fold paralysis, vocal fold polyp, and vocal fold cyst. It also used the support vector machine classifier to identify vocal fold disorders and achieved an identification accuracy rate of 98.75%. The results can serve as a very valuable reference for diagnosis.