Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition.
Morphological characterization of Mycobacterium tuberculosis in a MODS culture for an automatic diagnostics through pattern recognition.
复制标题
DOI：
10.1371/journal.pone.0082809
复制
发表时间：
2013
期刊：
影响因子：
3.7
通讯作者：
Zimic M
中科院分区：
文献类型：
--
作者：
Alva A;Aquino F;Gilman RH;Olivares C;Requena D;Gutiérrez AH;Caviedes L;Coronel J;Larson S;Sheen P;Moore DA;Zimic M
诊断技术的不匹配阻碍了结核病控制工作：在最需要的贫困地区，现代最佳诊断测试最少可用。缺乏足够的早期诊断和耐多药检测是控制工作中的一个关键问题。显微镜观察药敏试验(MODS)利用对结核分枝杆菌(MTB)编码模式的视觉识别，以低成本直接从痰标本中诊断结核病感染和药敏。发展中世界的实验室在实施MODS时面临的一个重要限制是缺乏具有读取MODS专门知识的长期技术人员。我们开发了一种模式识别算法来自动解释数字图像中的MODS结果。该算法使用图像处理、特征提取和模式识别来确定用于物体模型和照片模型的几何和光照特征，以对TB阳性图像进行分类。对765张MODS数字照片进行了处理。单目标模型对结核分枝杆菌的诊断灵敏度为96.9%，特异度为96.3%，对非结核分枝杆菌的诊断特异度为97.1%(禽分枝杆菌、99.1%的龟分枝杆菌、93.8%的甘肃分枝杆菌)。照片模型识别结核阳性样本的敏感度为99.1%，特异度为99.7%。该算法是一个有价值的工具，它将使用互联网或手机电话实现自动远程诊断。这一算法的使用及其在远程诊断平台中的进一步实施将有助于更快地发现结核病和确定耐多药结核病，从而更早地开始适当的治疗。
Tuberculosis control efforts are hampered by a mismatch in diagnostic technology: modern optimal diagnostic tests are least available in poor areas where they are needed most. Lack of adequate early diagnostics and MDR detection is a critical problem in control efforts. The Microscopic Observation Drug Susceptibility (MODS) assay uses visual recognition of cording patterns from Mycobacterium tuberculosis (MTB) to diagnose tuberculosis infection and drug susceptibility directly from a sputum sample in 7–10 days with a low cost. An important limitation that laboratories in the developing world face in MODS implementation is the presence of permanent technical staff with expertise in reading MODS. We developed a pattern recognition algorithm to automatically interpret MODS results from digital images. The algorithm using image processing, feature extraction and pattern recognition determined geometrical and illumination features used in an object-model and a photo-model to classify TB-positive images. 765 MODS digital photos were processed. The single-object model identified MTB (96.9% sensitivity and 96.3% specificity) and was able to discriminate non-tuberculous mycobacteria with a high specificity (97.1% M. avium, 99.1% M. chelonae, and 93.8% M. kansasii). The photo model identified TB-positive samples with 99.1% sensitivity and 99.7% specificity. This algorithm is a valuable tool that will enable automatic remote diagnosis using Internet or cellphone telephony. The use of this algorithm and its further implementation in a telediagnostics platform will contribute to both faster TB detection and MDR TB determination leading to an earlier initiation of appropriate treatment.
登录
查看更多内容
DOI：
10.1016/j.trstmh.2008.10.015
发表时间：
2009-06-01
影响因子：
2.2
作者：
Zimic, Mirko;Coronel, Jorge;Moore, David A. J.
通讯作者：
Moore, David A. J.
影响因子：
2
作者：
Forero, M. G.;Cristobal, G.;Desco, M.
通讯作者：
Desco, M.
影响因子：
1.1
作者：
Costa, LD;Estrozi, LF
通讯作者：
Estrozi, LF
DOI：
10.1109/titb.2009.2028339
发表时间：
2010-07
期刊：
IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society
影响因子：
--
作者：
Khutlang R;Krishnan S;Dendere R;Whitelaw A;Veropoulos K;Learmonth G;Douglas TS
通讯作者：
Douglas TS
开发低成本倒置显微镜来检测 MODS 培养物中结核分枝杆菌的早期生长。
影响因子：
3.7
作者：
Zimic M;Velazco A;Comina G;Coronel J;Fuentes P;Luna CG;Sheen P;Gilman RH;Moore DA
通讯作者：
Moore DA