• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.51-59
• /
• 2012

We describe the framework of a data-fuelled, interdisciplinary team-led learning system. The idea is to build models using patients from one's own institution whose features are similar to an index patient as regards an outcome of interest, in order to predict the utility of diagnostic tests and interventions, as well as inform prognosis. The Laboratory of Computational Physiology at the Massachusetts Institute of Technology developed and maintains MIMIC-II, a public deidentified high- resolution database of patients admitted to Beth Israel Deaconess Medical Center. It hosts teams of clinicians (nurses, doctors, pharmacists) and scientists (database engineers, modelers, epidemiologists) who translate the day-to-day questions during rounds that have no clear answers in the current medical literature into study designs, perform the modeling and the analysis and publish their findings. The studies fall into the following broad categories: identification and interrogation of practice variation, predictive modeling of clinical outcomes within patient subsets and comparative effectiveness research on diagnostic tests and therapeutic interventions. Clinical databases such as MIMIC-II, where recorded health care transactions - clinical decisions linked with patient outcomes - are constantly uploaded, become the centerpiece of a learning system.

• Korean Journal of Digital Imaging in Medicine
• /
• v.11 no.2
• /
• pp.63-68
• /
• 2009

Among various physical or subjective assessments of the quality of X-ray images, physical assessments can be quantitative but they are eventually judged by the view of observers thus subjective assessments including the aspect of observers are required. The changes in the ability to detect lesions caused by changes in the thickness of acrylic plates were tested with the ROC interpretation method that has taken into consideration, all the features of physical assessments as well as observers' ability to observe and mental stages and even surrounding environments using an Alvim phantom and the result indicated that as the thickness of acrylic plates increased, the amount of noises occurred increased compared to signals and thus the ability to detect signals as well as the sensitivity that is an ability to signals accurately and the ability to distinguish noises from signals thus it is considered that more efforts of radiologic technologists will be required to detect small lesions of fat patients with diagnostic X-ray generating apparatus.

• The Plant Pathology Journal
• /
• v.27 no.2
• /
• pp.120-127
• /
• 2011

While many isolates of Alternaria alternata are common saprophytes on trees and shrubs, this study clearly demonstrated that A. alternata is a primary pathogen in lilac (Syringa sp.), causing a leaf-blight that affects different Syringa species. Isolates of Alternaria sp. were collected from leaf blight samples of lilacs in the field. The internal transcribed spacer (ITS) region and morphological characterization were used to identify lilac blight pathogen. Based on 100% ITS nucleotide sequence identities to the Alternaria genus in the GenBank and morphological features, these isolates were identified as A. alternata. Disease symptoms were reproduced in lilac plants inoculated with A. alternata mycelial plugs and sprayed with a fungus-free culture filtrate, indicating that pathogenesis in lilac involves secondary metabolites or toxins. Diagnostic primers were developed to detect Alternaria sp. and A. alternata in lilac leaf blight based on ITS region and four known genes associated with pathogenesis in A. alternata: mixed-linked glucanase precursor, endopolygalacturonase, hsp70, and histone genes. The results from our study indicated A. alternata is a primary pathogen in lilac leaf blight, and these diagnostic primers can be used as a tool for the fast detection of A. alternata associated with lilac leaf blight.

• Journal of Veterinary Clinics
• /
• v.27 no.4
• /
• pp.468-473
• /
• 2010

A 6-year-old intact male Doberman pinscher presented with a thin soft stool and urinary signs. On radiography, three masses were observed in the caudal abdomen. One mass was described as a large, round, mineralized mass, with an "eggshell" appearance. The second mass was located caudal to the mineralized mass, and the third mass was located between the two masses. The second and the third masses had a soft tissue density. Ultrasonography was performed to identify the features and the origins of the masses. The first mass contained a large amount of anechoic fluid and had a thin wall; it was determined to be a cyst. Strong acoustic shadowing artifact was created by the mineralized cystic wall. Caudal to the cyst, the second mass was shown to be the prostate. A hypoechoic stalk connected the prostate and the cyst, which represented the cyst as a paraprostatic cyst with mineralization. The third mass was the normal urinary bladder. The cyst was removed surgically and confirmed by histopathologic examination. This report described typical clinical findings, diagnostic imaging, and treatment of a paraprostatic cyst.

• The Korean Journal of Cytopathology
• /
• v.5 no.2
• /
• pp.130-136
• /
• 1994

Urinary cytology is increasingly accepted as a diagnostic tool in the detection and follow-up of patients with bladder cancer. However, its value is reduced by several limitations, especially by the lack of cytologic criteria specifically reflecting the morphology of low-grade urothelial neoplasm. We reviewed histologically proven 50 cases of urine cytology with emphasis on cytologic findings of benign atypia and differential findings of urothelial neoplasm according to the grade. The diagnoses included 17 benign lesions(including 5 cases of urine calculi) and 33 malignant lesions (including 28 transitional cell carcinomas, 3 squamous cell carcinomas, 1 adenocarcinoma and 1 prostate adenocarcinoma), Diagnostic accuracy was 92%. Important cytodiagnostic criteria for benign atypia and low grade malignancy were cellularity, number of cell clusters, and morphology and arrangement of urothelial cells. The cytologic findings of urothelial neoplasms according to histologic grade were relatively well correlated with the histologic findings. However, the cytologic criteria were not sufficient to readily distinguish grade I from grade II. In view of this, we think that cytologic nomenclature "low-grade" and "high-grade" is a more reliable criterion. Recognition of subtle cellular morphologic features specific for urothelial lesions(including benign or malignancy) and proper fixation, processing and staining of specimen can expand the role of urinary cytology In detection and follow-up of patients.

• The Korean Journal of Cytopathology
• /
• v.5 no.2
• /
• pp.106-112
• /
• 1994

Fine needle aspiration biopsy has been proved as a safe, accurate and cost-effective diagnostic modality in palpable breast lesions. Cytologically, fibrocystic disease can be classified into 3 categories as nonproliferative breast disease, proliferative breast disease without atypia, and proliferative breast disease with atypia. This terminology for fine needle aspirates is compatible with that of diagnostic histopathology. Cytologic differentiation of nonproliferative disease from proliferative breast disease is important, since the risk of cancer development in cases of atypical hyperplasia is 4-5 times higher than that of general population. Twenty five fine needle aspirates of fibrocystic disease confirmed by subsequent histopathology were re-evaluated and classified into 3 categories depending on their architectural and nuclear features. In addition, these aspirates were scored according to the cytologic grading system, devised by Masood et al. and based on six cytologic criteria. Concordance rates between cytomorpholgic diagnosis and cytologic diagnosis using the cytologic criteria grading system and histologic diagnosis were 88% and 92%, respectively.

• The Korean Journal of Cytopathology
• /
• v.5 no.2
• /
• pp.79-89
• /
• 1994

This study was performed in order to evaluate the accuracy and the usefulness of the cytology of crush preparation in central nervous system (CNS) lesions. Forty four intraoperative biopsies were performed at the time of craniotomy including 34 benign and 10 malignant lesions. Crush preparations were prepared from tiny tissue fragments of craniotomy products. All cases were stained with toluidine blue. Intraoperative diagnoses made on cytologic examination were compared with the final paraffin section diagnoses. Comparison between the results of the cytologic and histologic findings revealed an overall diagnostic accuracy of 88.6%. This study attests to the diagnostic accuracy of cytologic examination in CNS lesions. The detailed cytologic features are described and important criteria for the cytodiagnosis of CNS lesions are discussed. This review leads us to think that cytologic examination by crush preparation in CNS lesions is considered as a simple, safe and highly diagnostically accurate method.

• Archives of Craniofacial Surgery
• /
• v.21 no.3
• /
• pp.202-205
• /
• 2020

Trichoepithelioma is a benign hair follicle tumor that can undergo malignant transformation into basal cell carcinoma in rare cases. Due to the similar clinical and histological features of trichoepithelioma and basal cell carcinoma, distinguishing between these types of tumors can be a diagnostic challenge. Punch biopsy obtains only a small sample of the entire lesion, and thus inherently involves a risk of misdiagnosis between histologically similar diseases. Therefore, if the possibility of misdiagnosis can reasonably be suspected, clinicians should conduct an excisional biopsy or immunohistochemical staining (e.g., CD10 and Bcl-2) to ensure an exact diagnosis. Although trichoepithelioma is benign, the surgical excision of solitary trichoepithelioma should be considered in order to avoid the possibility of malignant transformation, which has occasionally been documented for multiple familial trichoepitheliomas. Herein, we report a case that was initially misdiagnosed as trichoepithelioma before ultimately being diagnosed as basal cell carcinoma through excision and immunohistochemical staining.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.178-184
• /
• 2009

An efficient fault diagnosis system is needed for industry because it can optimize the resources management and improve the performance of the system. In this study, a fault diagnostic system is proposed for rotating machine using wavelet packet transform (WPT) and elman neural network (ENN) techniques. In most fault diagnosis for mechanical systems, WPT is a well-known signal processing technique for fault detection and identification. In previous work, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the extracted features from the WPT are used as inputs in an Elman neural network. The results show that the scheme can reliably diagnose four different conditions and can be considered as an improvement of previous works in this field.

• Journal of Communications and Networks
• /
• v.13 no.2
• /
• pp.149-159
• /
• 2011

In this paper, we study the problem of how to design a medical-grade wireless local area network (WLAN) for healthcare facilities. First, unlike the IEEE 802.11e MAC, which categorizes traffic primarily by their delay constraints, we prioritize medical applications according to their medical urgency. Second, we propose a mechanism that can guarantee absolute priority to each traffic category, which is critical for medical-grade quality of service (QoS), while the conventional 802.11e MAC only provides relative priority to each traffic category. Based on absolute priority, we focus on the performance of real-time patient monitoring applications, and derive the optimal contention window size that can significantly improve the throughput performance. Finally, for proper performance evaluation from a medical viewpoint, we introduce the weighted diagnostic distortion (WDD) as a medical QoS metric to effectively measure the medical diagnosability by extracting the main diagnostic features of medical signal. Our simulation result shows that the proposed mechanism, together with medical categorization using absolute priority, can significantly improve the medical-grade QoS performance over the conventional IEEE 802.11e MAC.